The Community for Technology Leaders
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Boston, MA, USA
June 7, 2015 to June 12, 2015
ISSN: 1063-6919
ISBN: 978-1-4673-6963-3
TABLE OF CONTENTS

Going deeper with convolutions (Abstract)

Christian Szegedy , Google Inc., USA
Wei Liu , University of North Carolina, Chapel Hill, USA
Yangqing Jia , Google Inc., USA
Pierre Sermanet , Google Inc., USA
Scott Reed , University of Michigan, Ann Arbor, USA
Dragomir Anguelov , Google Inc., USA
Dumitru Erhan , Google Inc., USA
Vincent Vanhoucke , Google Inc., USA
Andrew Rabinovich , Magic Leap Inc., USA
pp. 1-9

Propagated image filtering (Abstract)

Jen-Hao Rick Chang , Dept. Electrical and Computer Engineering, Carnegie Mellon University, USA
Yu-Chiang Frank Wang , Research Center for IT Innovation, Academia Sinica, USA
pp. 10-18

Web scale photo hash clustering on a single machine (Abstract)

Yunchao Gong , Facebook, USA
Marcin Pawlowski , Facebook, USA
Fei Yang , Facebook, USA
Louis Brandy , Facebook, USA
Lubomir Boundev , Facebook, USA
Rob Fergus , Facebook, USA
pp. 19-27

Expanding object detector's Horizon: Incremental learning framework for object detection in videos (Abstract)

Alina Kuznetsova , Leibniz University Hannover, Germany
Sung Ju Hwang , UNIST, South Korea
Bodo Rosenhahn , Leibniz University Hannover, Germany
Leonid Sigal , Disney Research Pittsburgh, USA
pp. 28-36

Supervised Discrete Hashing (Abstract)

Fumin Shen , University of Electronic Science and Technology of China, China
Chunhua Shen , University of Adelaide, Australia
Wei Liu , IBM Research, USA
Heng Tao Shen , The University of Queensland, Australia
pp. 37-45

What do 15,000 object categories tell us about classifying and localizing actions? (Abstract)

Mihir Jain , University of Amsterdam, The Netherlands
Jan C. van Gemert , University of Amsterdam, The Netherlands
Cees G. M. Snoek , University of Amsterdam, The Netherlands
pp. 46-55

Landmarks-based kernelized subspace alignment for unsupervised domain adaptation (Abstract)

Rahaf Aljundi , CNRS, UMR 5516, Laboratoire Hubert Curien, F-42000, Saint-Étienne, France
Remi Emonet , CNRS, UMR 5516, Laboratoire Hubert Curien, F-42000, Saint-Étienne, France
Damien Muselet , CNRS, UMR 5516, Laboratoire Hubert Curien, F-42000, Saint-Étienne, France
Marc Sebban , CNRS, UMR 5516, Laboratoire Hubert Curien, F-42000, Saint-Étienne, France
pp. 56-63

Blur kernel estimation using normalized color-line priors (Abstract)

Wei-Sheng Lai , National Taiwan University, Taiwan
Jian-Jiun Ding , National Taiwan University, Taiwan
Yen-Yu Lin , Academia Sinica, Taiwan
Yung-Yu Chuang , National Taiwan University, Taiwan
pp. 64-72

A light transport model for mitigating multipath interference in Time-of-flight sensors (Abstract)

Nikhil Naik , MIT Media Lab, USA
Achuta Kadambi , MIT Media Lab, USA
Christoph Rhemann , Microsoft Research, USA
Shahram Izadi , Microsoft Research, USA
Ramesh Raskar , MIT Media Lab, USA
Sing Bing Kang , Microsoft Research, USA
pp. 73-81

Traditional saliency reloaded: A good old model in new shape (Abstract)

Simone Frintrop , Institute of Computer Science III, Rheinische Friedrich-Wilhelms-Universität Bonn, Germany
Thomas Werner , Institute of Computer Science III, Rheinische Friedrich-Wilhelms-Universität Bonn, Germany
German M. Garcia , Institute of Computer Science III, Rheinische Friedrich-Wilhelms-Universität Bonn, Germany
pp. 82-90

Automatic construction Of robust spherical harmonic subspaces (Abstract)

Patrick Snape , Imperial College London, UK
Yannis Panagakis , Imperial College London, UK
Stefanos Zafeiriou , Imperial College London, UK
pp. 91-100

Leveraging stereo matching with learning-based confidence measures (Abstract)

Min-Gyu Park , Computer Vision Laboratory, GIST, South Korea
Kuk-Jin Yoon , Computer Vision Laboratory, GIST, South Korea
pp. 101-109

Saliency detection via Cellular Automata (Abstract)

Yao Qin , Dalian University of Technology, China
Huchuan Lu , Dalian University of Technology, China
Yiqun Xu , Dalian University of Technology, China
He Wang , Dalian University of Technology, China
pp. 110-119

Efficient sparse-to-dense optical flow estimation using a learned basis and layers (Abstract)

Jonas Wulff , Max Planck Institute for Intelligent Systems, Tübingen, Germany
Michael J. Black , Max Planck Institute for Intelligent Systems, Tübingen, Germany
pp. 120-130

Learning multiple visual tasks while discovering their structure (Abstract)

Carlo Ciliberto , Laboratory for Computational and Statistical Learning, Istituto Italiano di Tecnologia, Genova, Italy
Lorenzo Rosasco , Poggio Lab, Massachusetts Institute of Technology, Cambridge, USA
Silvia Villa , DIBRIS, Universita' degli studi di Genova, Genoa, Italy
pp. 131-139

Projection Metric Learning on Grassmann Manifold with Application to Video based Face Recognition (Abstract)

Zhiwu Huang , Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China
Ruiping Wang , Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China
Shiguang Shan , Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China
Xilin Chen , Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China
pp. 140-149

Structural Sparse Tracking (Abstract)

Tianzhu Zhang , Advanced Digital Sciences Center, Singapore
Si Liu , Institute of Information Engineering, CAS, China
Changsheng Xu , Institute of Automation, CAS, China
Shuicheng Yan , National University of Singapore, Singapore
Bernard Ghanem , Advanced Digital Sciences Center, Singapore
Narendra Ahuja , Advanced Digital Sciences Center, Singapore
Ming-Hsuan Yang , University of California at Merced, USA
pp. 150-158

Data-driven depth map refinement via multi-scale sparse representation (Abstract)

HyeokHyen Kwon , KAIST, Korea
Yu-Wing Tai , KAIST, Korea
Stephen Lin , Microsoft Research, USA
pp. 159-167

Uncalibrated photometric stereo based on elevation angle recovery from BRDF symmetry of isotropic materials (Abstract)

Feng Lu , The University of Tokyo, Japan
Imari Sato , National Institute of Informatics, Japan
Yoichi Sato , The University of Tokyo, Japan
pp. 168-176

Attributes and categories for generic instance search from one example (Abstract)

Ran Tao , ISLA, Informatics Institute, University of Amsterdam, The Netherlands
Arnold W.M. Smeulders , ISLA, Informatics Institute, University of Amsterdam, The Netherlands
Shih-Fu Chang , Department of Electrical Engineering, Columbia University, USA
pp. 177-186

Heat diffusion over weighted manifolds: A new descriptor for textured 3D non-rigid shapes (Abstract)

Mostafa Abdelrahman , Electrical Engineering Department, Assiut University, 71516, Egypt
Aly Farag , CVIP Lab, University of Louisville, KY 40292, USA
David Swanson , Department of Mathematics, University of Louisville, KY 40292, USA
Moumen T. El-Melegy , Electrical Engineering Department, Assiut University, 71516, Egypt
pp. 187-195

A dynamic programming approach for fast and robust object pose recognition from range images (Abstract)

Christopher Zach , Toshiba Research Europe, Cambridge, UK
Adrian Penate-Sanchez , CSIC-UPC, Barcelona, Spain
Minh-Tri Pham , Toshiba Research Europe, Cambridge, UK
pp. 196-203

Beyond Gaussian Pyramid: Multi-skip Feature Stacking for action recognition (Abstract)

Zhenzhong Lan , School of Computer Science, Carnegie Mellon University, USA
Ming Lin , School of Computer Science, Carnegie Mellon University, USA
Xuanchong Li , School of Computer Science, Carnegie Mellon University, USA
Alexander G. Hauptmann , School of Computer Science, Carnegie Mellon University, USA
Bhiksha Raj , School of Computer Science, Carnegie Mellon University, USA
pp. 204-212

A geodesic-preserving method for image warping (Abstract)

Dongping Li , Zhejiang University, China
Kaiming He , Microsoft Research, USA
Jian Sun , Microsoft Research, USA
Kun Zhou , Zhejiang University, China
pp. 213-221

Shape driven kernel adaptation in Convolutional Neural Network for robust facial trait recognition (Abstract)

Shaoxin Li , Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China
Junliang Xing , National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, 100190, China
Zhiheng Niu , Department of Electrical and Computer Engineering, National University of Singapore, Singapore
Shiguang Shan , Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China
Shuicheng Yan , Department of Electrical and Computer Engineering, National University of Singapore, Singapore
pp. 222-230

From categories to subcategories: Large-scale image classification with partial class label refinement (Abstract)

Marko Ristin , ETH Zurich, Switzerland
Juergen Gall , University of Bonn, Germany
Matthieu Guillaumin , ETH Zurich, Switzerland
Luc Van Gool , ETH Zurich, Switzerland
pp. 231-239

Combination features and models for human detection (Abstract)

Yunsheng Jiang , Department of Information Science, School of Mathematical Sciences and LMAM, Peking University, Beijing, 100871, China
Jinwen Ma , Department of Information Science, School of Mathematical Sciences and LMAM, Peking University, Beijing, 100871, China
pp. 240-248

Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction (Abstract)

Yuting Zhang , Department of Computer Science, Zhejiang University, Hangzhou, China
Kihyuk Sohn , Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, USA
Ruben Villegas , Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, USA
Gang Pan , Department of Computer Science, Zhejiang University, Hangzhou, China
Honglak Lee , Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, USA
pp. 249-258

A metric parametrization for trifocal tensors with non-colinear pinholes (Abstract)

Spyridon Leonardos , GRASP Laboratory, University of Pennsylvania, Philadelphia, 19104, USA
Roberto Tron , GRASP Laboratory, University of Pennsylvania, Philadelphia, 19104, USA
Kostas Daniilidis , GRASP Laboratory, University of Pennsylvania, Philadelphia, 19104, USA
pp. 259-267

An efficient volumetric framework for shape tracking (Abstract)

Benjamin Allain , Inria Grenoble Rhône-Alpes - LJK, Grenoble Universities, France
Jean-Sebastien Franco , Inria Grenoble Rhône-Alpes - LJK, Grenoble Universities, France
Edmond Boyer , Inria Grenoble Rhône-Alpes - LJK, Grenoble Universities, France
pp. 268-276

Structured Sparse Subspace Clustering: A unified optimization framework (Abstract)

Chun-Guang Li , SICE, Beijing University of Posts and Telecommunications, China
Rene Vidal , Center for Imaging Science, Johns Hopkins University, USA
pp. 277-286

Delving into egocentric actions (Abstract)

Yin Li , School of Interactive Computing, Georgia Institute of Technology, USA
Zhefan Ye , School of Interactive Computing, Georgia Institute of Technology, USA
James M. Rehg , School of Interactive Computing, Georgia Institute of Technology, USA
pp. 287-295

Latent trees for estimating intensity of Facial Action Units (Abstract)

Sebastian Kaltwang , Imperial College London, UK
Sinisa Todorovic , Oregon State University, USA
Maja Pantic , Imperial College London, UK
pp. 296-304

Robust regression on image manifolds for ordered label denoising (Abstract)

Hui Wu , University of North Carolina at Charlotte, USA
Richard Souvenir , University of North Carolina at Charlotte, USA
pp. 305-313

Privacy preserving optics for miniature vision sensors (Abstract)

Francesco Pittaluga , University of Florida, Electrical and Computer Engineering Dept., 216 Larsen Hall Gainesville, 32611-6200, USA
Sanjeev J. Koppal , University of Florida, Electrical and Computer Engineering Dept., 216 Larsen Hall Gainesville, 32611-6200, USA
pp. 314-324

Deep transfer metric learning (Abstract)

Junlin Hu , School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore
Jiwen Lu , Advanced Digital Sciences Center, Singapore
Yap-Peng Tan , School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore
pp. 325-333

Small-variance nonparametric clustering on the hypersphere (Abstract)

Julian Straub , CSAIL and LIDS, Massachusetts Institute of Technology, USA
Trevor Campbell , CSAIL and LIDS, Massachusetts Institute of Technology, USA
Jonathan P. How , CSAIL and LIDS, Massachusetts Institute of Technology, USA
John W. Fisher , CSAIL and LIDS, Massachusetts Institute of Technology, USA
pp. 334-342

DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time (Abstract)

Richard A. Newcombe , University of Washington, Seattle, USA
Dieter Fox , University of Washington, Seattle, USA
Steven M. Seitz , University of Washington, Seattle, USA
pp. 343-352

Reliable Patch Trackers: Robust visual tracking by exploiting reliable patches (Abstract)

Yang Li , College of Computer Science, Zhejiang University, China
Jianke Zhu , College of Computer Science, Zhejiang University, China
Steven C.H. Hoi , School of Information System, Singapore Management University, Singapore
pp. 353-361

Predicting eye fixations using convolutional neural networks (Abstract)

Nian Liu , Northwestern Polytechnical University, China
Junwei Han , Northwestern Polytechnical University, China
Dingwen Zhang , Northwestern Polytechnical University, China
Shifeng Wen , Northwestern Polytechnical University, China
Tianming Liu , University of Georgia, USA
pp. 362-370

Kernel fusion for better image deblurring (Abstract)

Long Mai , Portland State University, USA
Feng Liu , Portland State University, USA
pp. 371-380

Direction matters: Depth estimation with a surface normal classifier (Abstract)

Christian Hane , Department of Computer Science, ETH Zürich, Switzerland
L'ubor Ladicky , Department of Computer Science, ETH Zürich, Switzerland
Marc Pollefeys , Department of Computer Science, ETH Zürich, Switzerland
pp. 381-389

Grasp type revisited: A modern perspective on a classical feature for vision (Abstract)

Yezhou Yang , Computer Vision Lab, University of Maryland, College Park, USA
Cornelia Fermuller , Computer Vision Lab, University of Maryland, College Park, USA
Yi Li , NICTA and ANU, Australia
Yiannis Aloimonos , Computer Vision Lab, University of Maryland, College Park, USA
pp. 400-408

Learning Hypergraph-regularized Attribute Predictors (Abstract)

Sheng Huang , Chongqing University, China
Mohamed Elhoseiny , Rutgers University, USA
Ahmed Elgammal , Rutgers University, USA
Dan Yang , Chongqing University, China
pp. 409-417

A coarse-to-fine model for 3D pose estimation and sub-category recognition (Abstract)

Roozbeh Mottaghi , Allen Institute for AI, USA
Yu Xiang , University of Michigan-Ann Arbor, USA
Silvio Savarese , Stanford University, USA
pp. 418-426

Deep neural networks are easily fooled: High confidence predictions for unrecognizable images (Abstract)

Anh Nguyen , University of Wyoming, USA
Jason Yosinski , Cornell University, USA
Jeff Clune , University of Wyoming, USA
pp. 427-436

Deformable part models are convolutional neural networks (Abstract)

Ross Girshick , Microsoft Research, USA
Forrest Iandola , UC Berkeley, USA
Trevor Darrell , UC Berkeley, USA
Jitendra Malik , UC Berkeley, USA
pp. 437-446

Hypercolumns for object segmentation and fine-grained localization (Abstract)

Bharath Hariharan , University of California, Berkeley, USA
Pablo Arbelaez , Universidad de los Andes, Colombia, USA
Ross Girshick , Microsoft Research, Redmond, USA
Jitendra Malik , University of California, Berkeley, USA
pp. 447-456

Mapping visual features to semantic profiles for retrieval in medical imaging (Abstract)

Johannes Hofmanninger , Department of Biomedical Imaging and Image-guided Therapy, Computational Imaging Research Lab, Medical University of Vienna, Austria
Georg Langs , Department of Biomedical Imaging and Image-guided Therapy, Computational Imaging Research Lab, Medical University of Vienna, Austria
pp. 457-465

Event-driven stereo matching for real-time 3D panoramic vision (Abstract)

Stephan Schraml , AIT Austrian Institute of Technology, Digital Safety & Security Department, New Sensor Technologies, Donau-City-Straße 1, 1220 Vienna, Austria
Ahmed Nabil Belbachir , AIT Austrian Institute of Technology, Digital Safety & Security Department, New Sensor Technologies, Donau-City-Straße 1, 1220 Vienna, Austria
Horst Bischof , Graz University of Technology, Institute for Computer Graphics and Vision, 8010, Austria
pp. 466-474

Graph-based simplex method for pairwise energy minimization with binary variables (Abstract)

Daniel Prusa , Center for Machine Perception, Faculty of Electrical Engineering, Czech Technical University, Karlovo náměstí 13, 121 35 Prague, Czech Republic
pp. 475-483

Image denoising via adaptive soft-thresholding based on non-local samples (Abstract)

Hangfan Liu , Institute of Digital Media, Peking University, Beijing 100871, China
Ruiqin Xiong , Institute of Digital Media, Peking University, Beijing 100871, China
Jian Zhang , Institute of Digital Media, Peking University, Beijing 100871, China
Wen Gao , Institute of Digital Media, Peking University, Beijing 100871, China
pp. 484-492

3D scanning deformable objects with a single RGBD sensor (Abstract)

Mingsong Dou , Department of Computer Science, UNC-Chapel Hill, USA
Jonathan Taylor , Microsoft Research, USA
Henry Fuchs , Department of Computer Science, UNC-Chapel Hill, USA
Andrew Fitzgibbon , Microsoft Research, USA
Shahram Izadi , Microsoft Research, USA
pp. 493-501

Nested motion descriptors (Abstract)

Jeffrey Byrne , University of Pennsylvania, GRASP Lab, Systems and Technology Research, USA
pp. 502-510

Efficient minimal-surface regularization of perspective depth maps in variational stereo (Abstract)

Gottfried Graber , Graz University of Technology, Austria
Jonathan Balzer , UCLA, USA
Stefano Soatto , UCLA, USA
Thomas Pock , Graz University of Technology, Austria
pp. 511-520

Maximum persistency via iterative relaxed inference with graphical models (Abstract)

Alexander Shekhovtsov , TU Graz, Austria
Paul Swoboda , Heidelberg University, Germany
Bogdan Savchynskyy , TU Dresden, Germany
pp. 521-529

Deep hierarchical parsing for semantic segmentation (Abstract)

Abhishek Sharma , Computer Science Department, University of Maryland, USA
Oncel Tuzel , MERL, Cambridge, USA
David W. Jacobs , Computer Science Department, University of Maryland, USA
pp. 530-538

Designing deep networks for surface normal estimation (Abstract)

Xiaolong Wang , Robotics Institute, Carnegie Mellon University, USA
David F. Fouhey , Robotics Institute, Carnegie Mellon University, USA
Abhinav Gupta , Robotics Institute, Carnegie Mellon University, USA
pp. 539-547

Layered RGBD scene flow estimation (Abstract)

Deqing Sun , Harvard University, USA
Erik B. Sudderth , Brown University, USA
Hanspeter Pfister , Harvard University, USA
pp. 548-556

Hashing with binary autoencoders (Abstract)

Miguel A. Carreira-Perpinan , EECS, University of California, Merced, USA
Ramin Raziperchikolaei , EECS, University of California, Merced, USA
pp. 557-566

SUN RGB-D: A RGB-D scene understanding benchmark suite (Abstract)

Shuran Song , Princeton University, USA
Samuel P. Lichtenberg , Princeton University, USA
Jianxiong Xiao , Princeton University, USA
pp. 567-576

Collaborative feature learning from social media (Abstract)

Chen Fang , Dartmouth College, USA
Hailin Jin , Adobe Research, USA
Jianchao Yang , Snapchat, USA
Zhe Lin , Adobe Research, USA
pp. 577-585

Diversity-induced Multi-view Subspace Clustering (Abstract)

Xiaochun Cao , School of Computer Science and Technology, Tianjin University, 300072, China
Changqing Zhang , School of Computer Science and Technology, Tianjin University, 300072, China
Huazhu Fu , School of Computer Engineering, Nanyang Technological University, Nanyang Avenue 639798, Singapore
Si Liu , State Key Laboratory of Information Security, IIE, Chinese Academy of Sciences, Beijing, 100093, China
Hua Zhang , School of Computer Science and Technology, Tianjin University, 300072, China
pp. 586-594

Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection (Abstract)

Grant Van Horn , Caltech, USA
Steve Branson , Caltech, USA
Ryan Farrell , BYU, USA
Scott Haber , Cornell Lab of Ornithology, USA
Jessie Barry , Cornell Lab of Ornithology, USA
Panos Ipeirotis , NYU, USA
Pietro Perona , Caltech, USA
Serge Belongie , Cornell Tech, USA
pp. 595-604

Early burst detection for memory-efficient image retrieval (Abstract)

Miaojing Shi , Peking University, USA
Yannis Avrithis , University of Athens, NTUA, Greece
Herve Jegou , Inria, France
pp. 605-613

Indoor scene structure analysis for single image depth estimation (Abstract)

Wei Zhuo , Australian National University, Canberra, Australia
Mathieu Salzmann , Australian National University, Canberra, Australia
Xuming He , Australian National University, Canberra, Australia
Miaomiao Liu , Australian National University, Canberra, Australia
pp. 614-622

Light field layer matting (Abstract)

Juliet Fiss , University of Washington, USA
Brian Curless , University of Washington, USA
Richard Szeliski , Microsoft Research, USA
pp. 623-631

Depth camera tracking with contour cues (Abstract)

Qian-Yi Zhou , Intel Labs, USA
Vladlen Koltun , Intel Labs, USA
pp. 632-638

Radial distortion homography (Abstract)

Zuzana Kukelova , Microsoft Research Ltd, 21 Station Road, Cambridge CB1 2FB, UK
Jan Heller , Czech Technical University in Prague, 166 27 Praha 6, Technická 2, Czech Republic
Martin Bujnak , Capturing Reality s.r.o., Syslia 46, 821 05, Bratislava, Slovakia
Tomas Pajdla , Czech Technical University in Prague, 166 27 Praha 6, Technická 2, Czech Republic
pp. 639-647

Efficient object localization using Convolutional Networks (Abstract)

Jonathan Tompson , New York University, USA
Ross Goroshin , New York University, USA
Arjun Jain , New York University, USA
Yann LeCun , New York University, USA
Christoph Bregler , New York University, USA
pp. 648-656

Just noticeable defocus blur detection and estimation (Abstract)

Jianping Shi , The Chinese University of Hong Kong, China
Li Xu , Image & Visual Computing Lab, Lenovo R&T, China
Jiaya Jia , The Chinese University of Hong Kong, China
pp. 657-665

How do we use our hands? Discovering a diverse set of common grasps (Abstract)

De-An Huang , The Robotics Institute, Carnegie Mellon University, USA
Minghuang Ma , The Robotics Institute, Carnegie Mellon University, USA
Wei-Chiu Ma , The Robotics Institute, Carnegie Mellon University, USA
Kris M. Kitani , The Robotics Institute, Carnegie Mellon University, USA
pp. 666-675

Rotating your face using multi-task deep neural network (Abstract)

Junho Yim , School of Electrical Engineering, KAIST, South Korea
Heechul Jung , School of Electrical Engineering, KAIST, South Korea
ByungIn Yoo , School of Electrical Engineering, KAIST, South Korea
Changkyu Choi , Samsung Advanced Institute of Technology, Korea
Dusik Park , Samsung Advanced Institute of Technology, Korea
Junmo Kim , School of Electrical Engineering, KAIST, South Korea
pp. 676-684

Is object localization for free? - Weakly-supervised learning with convolutional neural networks (Abstract)

Maxime Oquab , INRIA Paris, France
Leon Bottou , MSR, New York, USA
Ivan Laptev , INRIA, Paris, France
Josef Sivic , INRIA, Paris, France
pp. 685-694

Super-resolution Person re-identification with semi-coupled low-rank discriminant dictionary learning (Abstract)

Xiao-Yuan Jing , State Key Laboratory of Software Engineering, School of Computer, Wuhan University, China
Xiaoke Zhu , State Key Laboratory of Software Engineering, School of Computer, Wuhan University, China
Fei Wu , State Key Laboratory of Software Engineering, School of Computer, Wuhan University, China
Xinge You , School of Electronic Information and Communications, Huazhong University of Science and Technology, China
Qinglong Liu , State Key Laboratory of Software Engineering, School of Computer, Wuhan University, China
Dong Yue , College of Automation, Nanjing University of Posts and Telecommunications, China
Ruimin Hu , National Engineering Research Center for Multimedia Software, School of Computer, Wuhan University, China
Baowen Xu , State Key Laboratory of Software Engineering, School of Computer, Wuhan University, China
pp. 695-704

Region-based temporally consistent video post-processing (Abstract)

Xuan Dong , Tsinghua University, China
Boyan Bonev , UC Los Angeles, USA
Yu Zhu , Northwestern Polytechnical University, USA
Alan L. Yuille , UC Los Angeles, USA
pp. 714-722

Global refinement of random forest (Abstract)

Shaoqing Ren , University of Science and Technology of China, China
Xudong Cao , University of Science and Technology of China, China
Yichen Wei , Microsoft Research, USA
Jian Sun , Microsoft Research, USA
pp. 723-730

Adaptive region pooling for object detection (Abstract)

Yi-Hsuan Tsai , UC Merced, USA
Onur C. Hamsici , Qualcomm Research, San Diego, USA
Ming-Hsuan Yang , UC Merced, USA
pp. 731-739

Discriminative and consistent similarities in instance-level Multiple Instance Learning (Abstract)

Mohammad Rastegari , University of Maryland, USA
Hannaneh Hajishirzi , University of Wasington, USA
Ali Farhadi , University of Wasington, USA
pp. 740-748

MUlti-Store Tracker (MUSTer): A cognitive psychology inspired approach to object tracking (Abstract)

Zhibin Hong , Centre for Quantum Computation and Intelligent Systems, Faculty of Engineering and Information Technology, University of Technology, Sydney, NSW 2007, Australia
Zhe Chen , Centre for Quantum Computation and Intelligent Systems, Faculty of Engineering and Information Technology, University of Technology, Sydney, NSW 2007, Australia
Chaohui Wang , Laboratoire d'Informatique Gaspard Monge, UMR CNRS 8049, Université Paris-Est, 77454 Marne-la-Vallée, France
Xue Mei , Toyota Research Institute, North America, Ann Arbor, MI 48105, USA
Danil Prokhorov , Toyota Research Institute, North America, Ann Arbor, MI 48105, USA
Dacheng Tao , Centre for Quantum Computation and Intelligent Systems, Faculty of Engineering and Information Technology, University of Technology, Sydney, NSW 2007, Australia
pp. 749-758

Finding action tubes (Abstract)

Georgia Gkioxari , UC Berkeley, USA
Jitendra Malik , UC Berkeley, USA
pp. 759-768

Learning a convolutional neural network for non-uniform motion blur removal (Abstract)

Jian Sun , Xi'an Jiaotong University, China
Wenfei Cao , Xi'an Jiaotong University, China
Zongben Xu , Xi'an Jiaotong University, China
Jean Ponce , École Normale Supérieure / PSL Research University, France
pp. 769-777

Complexity-adaptive distance metric for object proposals generation (Abstract)

Yao Xiao , The Hong Kong University of Science and Technology, China
Cewu Lu , The Hong Kong University of Science and Technology, China
Efstratios Tsougenis , The Hong Kong University of Science and Technology, China
Yongyi Lu , The Hong Kong University of Science and Technology, China
Chi-Keung Tang , The Hong Kong University of Science and Technology, China
pp. 778-786

High-fidelity Pose and Expression Normalization for face recognition in the wild (Abstract)

Xiangyu Zhu , Center for Biometrics and Security Research & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 95 Zhongguancun Donglu, Beijing 100190, China
Zhen Lei , Center for Biometrics and Security Research & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 95 Zhongguancun Donglu, Beijing 100190, China
Junjie Yan , Center for Biometrics and Security Research & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 95 Zhongguancun Donglu, Beijing 100190, China
Dong Yi , Center for Biometrics and Security Research & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 95 Zhongguancun Donglu, Beijing 100190, China
Stan Z. Li , Center for Biometrics and Security Research & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 95 Zhongguancun Donglu, Beijing 100190, China
pp. 787-796

Transformation of Markov Random Fields for marginal distribution estimation (Abstract)

Masaki Saito , Tohoku University, Japan
Takayuki Okatani , Tohoku University, Japan
pp. 797-805

Sparse Convolutional Neural Networks (Abstract)

Baoyuan Liu , Computational Imaging Lab, Computer Science, University of Central Florida, Orlando, USA
Min Wang , Computational Imaging Lab, Computer Science, University of Central Florida, Orlando, USA
Hassan Foroosh , Computational Imaging Lab, Computer Science, University of Central Florida, Orlando, USA
Marshall Tappen , Amazon.com, Seattle, WA 98109, USA
Marianna Penksy , Department of Mathematics, University of Central Florida, Orlando, USA
pp. 806-814

FaceNet: A unified embedding for face recognition and clustering (Abstract)

Florian Schroff , Google Inc., USA
Dmitry Kalenichenko , Google Inc., USA
James Philbin , Google Inc., USA
pp. 815-823

Cascaded hand pose regression (Abstract)

Xiao Sun , Chinese University of Hong Kong, China
Yichen Wei , Microsoft Research, USA
Shuang Liang , Tongji University, China
Xiaoou Tang , Chinese University of Hong Kong, China
Jian Sun , Microsoft Research, USA
pp. 824-832

Cross-scene crowd counting via deep convolutional neural networks (Abstract)

Cong Zhang , Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, China
Hongsheng Li , Department of Electronic Engineering, The Chinese University of Hong Kong, China
Xiaogang Wang , Department of Electronic Engineering, The Chinese University of Hong Kong, China
Xiaokang Yang , Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, China
pp. 833-841

The application of two-level attention models in deep convolutional neural network for fine-grained image classification (Abstract)

Tianjun Xiao , Institute of Computer Science and Technology, Peking University, China
Yichong Xu , Microsoft Research, Beijing, China
Kuiyuan Yang , Microsoft Research, Beijing, China
Jiaxing Zhang , Microsoft Research, Beijing, China
Yuxin Peng , Institute of Computer Science and Technology, Peking University, China
Zheng Zhang , New York University Shanghai, China
pp. 842-850

End-to-end integration of a Convolutional Network, Deformable Parts Model and non-maximum suppression (Abstract)

Li Wan , Dept. of Computer Science, Courant Institute, New York University, 251 Mercer Street, 10012, USA
David Eigen , Dept. of Computer Science, Courant Institute, New York University, 251 Mercer Street, 10012, USA
Rob Fergus , Dept. of Computer Science, Courant Institute, New York University, 251 Mercer Street, 10012, USA
pp. 851-859

A mixed bag of emotions: Model, predict, and transfer emotion distributions (Abstract)

Kuan-Chuan Peng , Cornell University, USA
Tsuhan Chen , Cornell University, USA
Amir Sadovnik , Lafayette College, USA
Andrew Gallagher , Google Inc., USA
pp. 860-868

Neuroaesthetics in fashion: Modeling the perception of fashionability (Abstract)

Edgar Simo-Serra , Institut de Robòtica i Informàtica Industrial (CSIC-UPC), Spain
Sanja Fidler , University of Toronto, Canada
Francesc Moreno-Noguer , Institut de Robòtica i Informàtica Industrial (CSIC-UPC), Spain
Raquel Urtasun , University of Toronto, Canada
pp. 869-877

Part-based modelling of compound scenes from images (Abstract)

Anton van den Hengel , The University of Adelaide, Australia
Chris Russell , University College London, UK
Anthony Dick , The University of Adelaide, Australia
John Bastian , The University of Adelaide, Australia
Daniel Pooley , The University of Adelaide, Australia
Lachlan Fleming , The University of Adelaide, Australia
Lourdes Agapito , University College London, UK
pp. 878-886

Efficient parallel optimization for potts energy with hierarchical fusion (Abstract)

Olga Veksler , University of Western Ontario, London, Canada
pp. 887-895

Pooled motion features for first-person videos (Abstract)

M. S. Ryoo , Jet Propulsion Laboratory, California Institute of Technology, Pasadena, USA
Brandon Rothrock , Jet Propulsion Laboratory, California Institute of Technology, Pasadena, USA
Larry Matthies , Jet Propulsion Laboratory, California Institute of Technology, Pasadena, USA
pp. 896-904

Functional correspondence by matrix completion (Abstract)

Artiom Kovnatsky , Faculty of Informatics, Università della Svizzera italiana (USI), Italy
Michael M. Bronstein , Faculty of Informatics, Università della Svizzera italiana (USI), Italy
Xavier Bresson , Signal Processing Lab, École Polytechnique Fédérale de Lausanne (EPFL), Switzerland
Pierre Vandergheynst , Signal Processing Lab, École Polytechnique Fédérale de Lausanne (EPFL), Switzerland
pp. 905-914

Elastic-net regularization of singular values for robust subspace learning (Abstract)

Eunwoo Kim , Department of ECE, ASRI, Seoul National University, Korea
Minsik Lee , Division of EE, Hanyang University, Korea
Songhwai Oh , Department of ECE, ASRI, Seoul National University, Korea
pp. 915-923

Hardware compliant approximate image codes (Abstract)

Da Kuang , Georgia Institute of Technology, Atlanta, 30332, United States
Alex Gittens , University of California, Berkeley, 94720, United States
Raffay Hamid , DigitalGlobe Inc, Seattle, WA 98103, United States
pp. 924-932

Photometric refinement of depth maps for multi-albedo objects (Abstract)

Avishek Chatterjee , Indian Institute of Science, Bengaluru 560012, India
Venu Madhav Govindu , Indian Institute of Science, Bengaluru 560012, India
pp. 933-941

Classifier based graph construction for video segmentation (Abstract)

Anna Khoreva , Max Planck Institute for Informatics, Germany
Fabio Galasso , OSRAM Corporate Technology, Germany
Matthias Hein , Saarland University, Germany
Bernt Schiele , Max Planck Institute for Informatics, Germany
pp. 951-960

ActivityNet: A large-scale video benchmark for human activity understanding (Abstract)

Fabian Caba Heilbron , Universidad del Norte, Colombia
Victor Escorcia , Universidad del Norte, Colombia
Bernard Ghanem , King Abdullah University of Science and Technology (KAUST), Saudi Arabia
Juan Carlos Niebles , Universidad del Norte, Colombia
pp. 961-970

Mid-level deep pattern mining (Abstract)

Yao Li , The University of Adelaide, SA 5005, Australia
Lingqiao Liu , The University of Adelaide, SA 5005, Australia
Chunhua Shen , The University of Adelaide, SA 5005, Australia
Anton van den Hengel , The University of Adelaide, SA 5005, Australia
pp. 971-980

Prediction of search targets from fixations in open-world settings (Abstract)

Hosnieh Sattar , Perceptual User Interfaces Group, Max Planck Institute for Informatics, Saarbrücken, Germany
Sabine Muller , Perceptual User Interfaces Group, Max Planck Institute for Informatics, Saarbrücken, Germany
Mario Fritz , Scalable Learning and Perception Group, Max Planck Institute for Informatics, Saarbrücken, Germany
Andreas Bulling , Perceptual User Interfaces Group, Max Planck Institute for Informatics, Saarbrücken, Germany
pp. 981-990

Understanding image representations by measuring their equivariance and equivalence (Abstract)

Karel Lenc , Department of Engineering Science, University of Oxford, Parks Road, OX1 3PJ, United Kingdom
Andrea Vedaldi , Department of Engineering Science, University of Oxford, Parks Road, OX1 3PJ, United Kingdom
pp. 991-999

Effective learning-based illuminant estimation using simple features (Abstract)

Dongliang Cheng , National University of Singapore, 21 Lower Kent Ridge Rd, Singapore 119077
Brian Price , Adobe Research, Tucson, AZ 85712, United States
Scott Cohen , Adobe Research, Tucson, AZ 85712, United States
Michael S. Brown , National University of Singapore, 21 Lower Kent Ridge Rd, Singapore 119077
pp. 1000-1008

PAIGE: PAirwise Image Geometry Encoding for improved efficiency in Structure-from-Motion (Abstract)

Johannes L. Schonberger , Department of Computer Science, The University of North Carolina at Chapel Hill, 27514, United States
Alexander C. Berg , Department of Computer Science, The University of North Carolina at Chapel Hill, 27514, United States
Jan-Michael Frahm , Department of Computer Science, The University of North Carolina at Chapel Hill, 27514, United States
pp. 1009-1018

Dense, accurate optical flow estimation with piecewise parametric model (Abstract)

Jiaolong Yang , Beijing Lab of Intelligent Information Technology, Beijing Institute of Technology, China
Hongdong Li , Research School of Engineering, The Australian National University (ANU) and NICTA, Canberra ACT 0200, Australia
pp. 1019-1027

Single-image estimation of the camera response function in near-lighting (Abstract)

Pedro Rodrigues , Institute of Systems and Robotics, University of Coimbra, Portugal
Joao P. Barreto , Institute of Systems and Robotics, University of Coimbra, Portugal
pp. 1028-1036

Multispectral pedestrian detection: Benchmark dataset and baseline (Abstract)

Soonmin Hwang , Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
Jaesik Park , Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
Namil Kim , Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
Yukyung Choi , Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
In So Kweon , Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
pp. 1037-1045

A low-dimensional step pattern analysis algorithm with application to multimodal retinal image registration (Abstract)

Jimmy Addison Lee , Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), 1 Fusionopolis Way, Connexis (South Tower), Singapore 138632
Jun Cheng , Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), 1 Fusionopolis Way, Connexis (South Tower), Singapore 138632
Beng Hai Lee , Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), 1 Fusionopolis Way, Connexis (South Tower), Singapore 138632
Ee Ping Ong , Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), 1 Fusionopolis Way, Connexis (South Tower), Singapore 138632
Guozhen Xu , Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), 1 Fusionopolis Way, Connexis (South Tower), Singapore 138632
Damon Wing Kee Wong , Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), 1 Fusionopolis Way, Connexis (South Tower), Singapore 138632
Jiang Liu , Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), 1 Fusionopolis Way, Connexis (South Tower), Singapore 138632
Augustinus Laude , National Healthcare Group, Eye Institute, Tan Tock Seng Hospital, 11 Jalan Singapore 308433
Tock Han Lim , National Healthcare Group, Eye Institute, Tan Tock Seng Hospital, 11 Jalan Singapore 308433
pp. 1046-1053

Bilinear heterogeneous information machine for RGB-D action recognition (Abstract)

Yu Kong , Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA
Yun Fu , Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA
pp. 1054-1062

MRF optimization by graph approximation (Abstract)

Wonsik Kim , Department of ECE, ASRI, Seoul National University, 151-742, Korea
Kyoung Mu Lee , Department of ECE, ASRI, Seoul National University, 151-742, Korea
pp. 1063-1071

SALICON: Saliency in Context (Abstract)

Ming Jiang , Department of Electrical and Computer Engineering, National University of Singapore, Singapore 117583
Shengsheng Huang , Department of Electrical and Computer Engineering, National University of Singapore, Singapore 117583
Juanyong Duan , Department of Electrical and Computer Engineering, National University of Singapore, Singapore 117583
Qi Zhao , Department of Electrical and Computer Engineering, National University of Singapore, Singapore 117583
pp. 1072-1080

Weakly supervised object detection with convex clustering (Abstract)

Hakan Bilen , ESAT-PSI / iMinds, KU Leuven, Belgium
Marco Pedersoli , ESAT-PSI / iMinds, KU Leuven, Belgium
Tinne Tuytelaars , ESAT-PSI / iMinds, KU Leuven, Belgium
pp. 1081-1089

Interleaved text/image Deep Mining on a large-scale radiology database (Abstract)

Hoo-Chang Shin , Imaging Biomarkers and Computer-Aided Diagnosis Laboratory Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD 20892-1182, United States
Le Lu , Imaging Biomarkers and Computer-Aided Diagnosis Laboratory Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD 20892-1182, United States
Lauren Kim , Imaging Biomarkers and Computer-Aided Diagnosis Laboratory Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD 20892-1182, United States
Ari Seff , Imaging Biomarkers and Computer-Aided Diagnosis Laboratory Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD 20892-1182, United States
Jianhua Yao , Imaging Biomarkers and Computer-Aided Diagnosis Laboratory Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD 20892-1182, United States
Ronald M. Summers , Imaging Biomarkers and Computer-Aided Diagnosis Laboratory Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD 20892-1182, United States
pp. 1090-1099

Learning semantic relationships for better action retrieval in images (Abstract)

Vignesh Ramanathan , Stanford University, 450 Serra Mall, California 94305, United States
Congcong Li , Google, California, United States
Jia Deng , University of Michigan, 500 S State St, Ann Arbor, 48109, United States
Wei Han , Google, California, United States
Zhen Li , Google, California, United States
Kunlong Gu , Google, California, United States
Yang Song , Google, California, United States
Samy Bengio , Google, California, United States
Chuck Rossenberg , Google, California, United States
Li Fei-Fei , Stanford University, 450 Serra Mall, California 94305, United States
pp. 1100-1109

Hierarchical recurrent neural network for skeleton based action recognition (Abstract)

Yong Du , Center for Research on Intelligent Perception and Computing, CRIPAC, Nat'l Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China
Wei Wang , Center for Research on Intelligent Perception and Computing, CRIPAC, Nat'l Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China
Liang Wang , Center for Research on Intelligent Perception and Computing, CRIPAC, Nat'l Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China
pp. 1110-1118

Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs (Abstract)

Bo Li , Northwestern Polytechnical University, China
Chunhua Shen , University of Adelaide, Australia
Yuchao Dai , Australian National University, Canberra ACT 0200, Australia
Anton van den Hengel , University of Adelaide, Australia
Mingyi He , Northwestern Polytechnical University, China
pp. 1119-1127

Discriminative shape from shading in uncalibrated illumination (Abstract)

Stephan R. Richter , Department of Computer Science, TU Darmstadt, Germany
Stefan Roth , Department of Computer Science, TU Darmstadt, Germany
pp. 1128-1136

Multi-manifold deep metric learning for image set classification (Abstract)

Jiwen Lu , Advanced Digital Sciences Center, Singapore
Gang Wang , Advanced Digital Sciences Center, Singapore
Weihong Deng , School of ICE, Beijing University of Posts and Telecommunications, China
Pierre Moulin , Advanced Digital Sciences Center, Singapore
Jie Zhou , Department of Automation, Tsinghua University, Beijing, China
pp. 1137-1145

Target Identity-aware Network Flow for online multiple target tracking (Abstract)

Afshin Dehghan , Center for Research in Computer Vision, University of Central Florida, United States
Yicong Tian , Center for Research in Computer Vision, University of Central Florida, United States
Philip. H. S. Torr , Department of Engineering Science, University of Oxford, Parks Road, OX1 3PJ, United Kingdom
Mubarak Shah , Center for Research in Computer Vision, University of Central Florida, United States
pp. 1146-1154

Adaptive as-natural-as-possible image stitching (Abstract)

Chung-Ching Lin , IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, NY 10598, United States
Sharathchandra U. Pankanti , IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, NY 10598, United States
Karthikeyan Natesan Ramamurthy , IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, NY 10598, United States
Aleksandr Y. Aravkin , IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, NY 10598, United States
pp. 1155-1163

EpicFlow: Edge-preserving interpolation of correspondences for optical flow (Abstract)

Jerome Revaud , Inria, 59650 Villeneuve-d'Ascq, France
Philippe Weinzaepfel , Inria, 59650 Villeneuve-d'Ascq, France
Zaid Harchaoui , Inria, 59650 Villeneuve-d'Ascq, France
Cordelia Schmid , Inria, 59650 Villeneuve-d'Ascq, France
pp. 1164-1172

Learning coarse-to-fine sparselets for efficient object detection and scene classification (Abstract)

Gong Cheng , School of Automation, Northwestern Polytechnical University, Xi'an, China
Junwei Han , School of Automation, Northwestern Polytechnical University, Xi'an, China
Lei Guo , School of Automation, Northwestern Polytechnical University, Xi'an, China
Tianming Liu , Department of Computer Science, The University of Georgia, Athens, United States
pp. 1173-1181

Continuous Visibility Feature (Abstract)

Guilin Liu , Department of Computer Science, George Mason University, Fairfax, VA, USA, 22030
Yotam Gingold , Department of Computer Science, George Mason University, Fairfax, VA, USA, 22030
Jyh-Ming Lien , Department of Computer Science, George Mason University, Fairfax, VA, USA, 22030
pp. 1182-1190

FlowWeb: Joint image set alignment by weaving consistent, pixel-wise correspondences (Abstract)

Tinghui Zhou , UC Berkeley, California, United States
Yong Jae Lee , UC Davis, 1 Shields Ave, Davis, CA 95616, United States
Stella X. Yu , UC Berkeley/ICSI, California, United States
Alexei A. Efros , UC Berkeley, California, United States
pp. 1191-1200

Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals (Abstract)

Minsu Cho , Inria, 59650 Villeneuve-d'Ascq, France
Suha Kwak , Inria, 59650 Villeneuve-d'Ascq, France
Cordelia Schmid , Inria, 59650 Villeneuve-d'Ascq, France
Jean Ponce , École Normale Supérieure / PSL Research University, France
pp. 1201-1210

Supervised descriptor learning for multi-output regression (Abstract)

Xiantong Zhen , University of Western Ontario, London, Canada
Zhijie Wang , GE Healthcare, London, ON, Canada
Mengyang Yu , Northumbria University, Newcastle, United Kingdom
Shuo Li , GE Healthcare, London, ON, Canada
pp. 1211-1218

A statistical model of Riemannian metric variation for deformable shape analysis (Abstract)

Andrea Gasparetto , Dipartimento di Scienze Ambientali, Informatica e Statistica, Universitá Ca' Foscari Venezia - via Torino, 155 - 30172 Venice Italy
Andrea Torsello , Dipartimento di Scienze Ambientali, Informatica e Statistica, Universitá Ca' Foscari Venezia - via Torino, 155 - 30172 Venice Italy
pp. 1219-1228

Temporally coherent interpretations for long videos using pattern theory (Abstract)

Fillipe Souza , University of South Florida, Tampa, USA
Sudeep Sarkar , University of South Florida, Tampa, USA
Anuj Srivastava , Florida State University, Tallahassee, USA
Jingyong Su , Texas Tech University, Lubbock, USA
pp. 1229-1237

Line-sweep: Cross-ratio for wide-baseline matching and 3D reconstruction (Abstract)

Srikumar Ramalingam , Mitsubishi Electric Research Laboratories (MERL), Cambridge, USA
Michel Antunes , Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg
Daniel Snow , Mitsubishi Electric Research Laboratories (MERL), Cambridge, USA
Gim Hee Lee , Mitsubishi Electric Research Laboratories (MERL), Cambridge, USA
Sudeep Pillai , Massachussetts Institute of Technology (MIT), Cambridge, USA
pp. 1238-1246

Simplified mirror-based camera pose computation via rotation averaging (Abstract)

Gucan Long , College of Aerospace Science and Engineering, National University of Defense Technology, China
Laurent Kneip , Research School of Engineering, Australian National University, Acton ACT 2601, Australia
Xin Li , College of Aerospace Science and Engineering, National University of Defense Technology, China
Xiaohu Zhang , College of Aerospace Science and Engineering, National University of Defense Technology, China
Qifeng Yu , College of Aerospace Science and Engineering, National University of Defense Technology, China
pp. 1247-1255

On the relationship between visual attributes and convolutional networks (Abstract)

Victor Escorcia , King Abdullah University of Science and Technology (KAUST), Saudi Arabia
Juan Carlos Niebles , Universidad del Norte, Colombia
Bernard Ghanem , King Abdullah University of Science and Technology (KAUST), Saudi Arabia
pp. 1256-1264

Saliency detection by multi-context deep learning (Abstract)

Rui Zhao , Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Chuangyeyuan Rd, Longgang, Guangdong, China
Wanli Ouyang , Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong
Hongsheng Li , Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong
Xiaogang Wang , Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Chuangyeyuan Rd, Longgang, Guangdong, China
pp. 1265-1274

Deepshape: Deep learned shape descriptor for 3D shape matching and retrieval (Abstract)

Jin Xie , Department of Electrical and Computer Engineering, New York University Abu Dhabi, United Arab Emirates
Yi Fang , Department of Electrical and Computer Engineering, New York University Abu Dhabi, United Arab Emirates
Fan Zhu , Department of Electrical and Computer Engineering, New York University Abu Dhabi, United Arab Emirates
Edward Wong , Polytechnic School of Engineering, New York University, 11201, United States
pp. 1275-1283

Bayesian adaptive matrix factorization with automatic model selection (Abstract)

Peixian Chen , The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong
Naiyan Wang , The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong
Nevin L. Zhang , The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong
Dit-Yan Yeung , The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong
pp. 1284-1292

Joint action recognition and pose estimation from video (Abstract)

Bruce Xiaohan Nie , Center for Vision, Cognition, Learning and Art, University of California, Los Angeles, USA
Caiming Xiong , Center for Vision, Cognition, Learning and Art, University of California, Los Angeles, USA
Song-Chun Zhu , Center for Vision, Cognition, Learning and Art, University of California, Los Angeles, USA
pp. 1293-1301

Fast action proposals for human action detection and search (Abstract)

Gang Yu , School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore
Junsong Yuan , School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore
pp. 1302-1311

Joint multi-feature spatial context for scene recognition in the semantic manifold (Abstract)

Xinhang Song , Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computer Technology, Beijing, 100190, China
Shuqiang Jiang , Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computer Technology, Beijing, 100190, China
Luis Herranz , Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computer Technology, Beijing, 100190, China
pp. 1312-1320

Large-scale damage detection using satellite imagery (Abstract)

Lionel Gueguen , DigitalGlobe Inc., 12076 Grant Street, Thornton, Colorado, USA
Raffay Hamid , DigitalGlobe Inc., 12076 Grant Street, Thornton, Colorado, USA
pp. 1321-1328

A novel locally linear KNN model for visual recognition (Abstract)

Qingfeng Liu , New Jersey Institute of Technology, Newark, USA
Chengjun Liu , New Jersey Institute of Technology, Newark, USA
pp. 1329-1337

Bilinear random projections for locality-sensitive binary codes (Abstract)

Saehoon Kim , Department of Computer Science and Engineering, Pohang University of Science and Technology, Korea
Seungjin Choi , Department of Computer Science and Engineering, Pohang University of Science and Technology, Korea
pp. 1338-1346

Combining local appearance and holistic view: Dual-Source Deep Neural Networks for human pose estimation (Abstract)

Xiaochuan Fan , Department of Computer Science & Engineering, University of South Carolina, Columbia, 29208, USA
Kang Zheng , Department of Computer Science & Engineering, University of South Carolina, Columbia, 29208, USA
Yuewei Lin , Department of Computer Science & Engineering, University of South Carolina, Columbia, 29208, USA
Song Wang , Department of Computer Science & Engineering, University of South Carolina, Columbia, 29208, USA
pp. 1347-1355

Superpixel segmentation using Linear Spectral Clustering (Abstract)

Zhengqin Li , Department of Electronic Engineering, Tsinghua University, Beijing, China
Jiansheng Chen , Department of Electronic Engineering, Tsinghua University, Beijing, China
pp. 1356-1363

Person count localization in videos from noisy foreground and detections (Abstract)

Sheng Chen , Oregon State University, Corvallis, 97331, United States
Alan Fern , Oregon State University, Corvallis, 97331, United States
Sinisa Todorovic , Oregon State University, Corvallis, 97331, United States
pp. 1364-1372

Good features to track for visual SLAM (Abstract)

Guangcong Zhang , School of ECE, Georgia Tech., United States
Patricio A. Vela , School of ECE, Georgia Tech., United States
pp. 1373-1382

Discovering states and transformations in image collections (Abstract)

Phillip Isola , Massachusetts Institute of Technology, 77 Massachusetts Ave, Cambridge, 02139, United States
Joseph J. Lim , Massachusetts Institute of Technology, 77 Massachusetts Ave, Cambridge, 02139, United States
Edward H. Adelson , Massachusetts Institute of Technology, 77 Massachusetts Ave, Cambridge, 02139, United States
pp. 1383-1391

Generalized Deformable Spatial Pyramid: Geometry-preserving dense correspondence estimation (Abstract)

Junhwa Hur , Center for Imaging Media Research, Robot & Media Institute, KIST, Seoul, Korea
Hwasup Lim , Center for Imaging Media Research, Robot & Media Institute, KIST, Seoul, Korea
Changsoo Park , Center for Imaging Media Research, Robot & Media Institute, KIST, Seoul, Korea
Sang Chul Ahn , Center for Imaging Media Research, Robot & Media Institute, KIST, Seoul, Korea
pp. 1392-1400

Classifier adaptation at prediction time (Abstract)

Amelie Royer , ENS Rennes, France
Christoph H. Lampert , IST Austria
pp. 1401-1409

Phase-based frame interpolation for video (Abstract)

Simone Meyer , ETH Zurich, 8092, Switzerland
Oliver Wang , Disney Research Zurich, Switzerland
Henning Zimmer , Disney Research Zurich, Switzerland
Max Grosse , Disney Research Zurich, Switzerland
Alexander Sorkine-Hornung , Disney Research Zurich, Switzerland
pp. 1410-1418

Matching-CNN meets KNN: Quasi-parametric human parsing (Abstract)

Si Liu , SKLOIS, IIE, Chinese Academy of Sciences, China
Xiaodan Liang , National University of Singapore, Singapore
Luoqi Liu , National University of Singapore, Singapore
Xiaohui Shen , Adobe Research, Tucson, AZ 85712, United States
Jianchao Yang , Adobe Research, Tucson, AZ 85712, United States
Changsheng Xu , IA, Chinese Academy of Sciences, China
Liang Lin , Sun Yat-sen University, Guangzhou, Guangdong, China
Xiaochun Cao , SKLOIS, IIE, Chinese Academy of Sciences, China
Shuicheng Yan , National University of Singapore, Singapore
pp. 1419-1427

Absolute pose for cameras under flat refractive interfaces (Abstract)

Sebastian Haner , Centre for Mathematical Sciences, Lund University, Sweden
Kalle Astrom , Centre for Mathematical Sciences, Lund University, Sweden
pp. 1428-1436

Protecting against screenshots: An image processing approach (Abstract)

Alex Yong-Sang Chia , Rakuten Institute of Technology, Tokyo, Japan
Udana Bandara , Rakuten Institute of Technology, Tokyo, Japan
Xiangyu Wang , Institute of Infocomm Research, A*STAR, Singapore
Hiromi Hirano , Rakuten Institute of Technology, Tokyo, Japan
pp. 1437-1445

Pose-conditioned joint angle limits for 3D human pose reconstruction (Abstract)

Ijaz Akhter , Max Planck Institute for Intelligent Systems, Tübingen, Germany
Michael J. Black , Max Planck Institute for Intelligent Systems, Tübingen, Germany
pp. 1446-1455

VisKE: Visual knowledge extraction and question answering by visual verification of relation phrases (Abstract)

Fereshteh Sadeghi , University of Washington, Seattle, United States
Santosh K. Divvala , The Allen Institute for AI, 2157 N Northlake Way Suite 110, Seattle, WA 98103, United States
Ali Farhadi , University of Washington, Seattle, United States
pp. 1456-1464

A graphical model approach for matching partial signatures (Abstract)

Xianzhi Du , UMIACS, University of Maryland, College Park, United States
David Doermann , UMIACS, University of Maryland, College Park, United States
Wael AbdAlmageed , Information Sciences Institute, University of Southern California, United States
pp. 1465-1472

From captions to visual concepts and back (Abstract)

Hao Fang , Microsoft Research, Beijing 100080, China
Saurabh Gupta , Microsoft Research, Beijing 100080, China
Forrest Iandola , Microsoft Research, Beijing 100080, China
Rupesh K. Srivastava , Microsoft Research, Beijing 100080, China
Li Deng , Microsoft Research, Beijing 100080, China
Piotr Dollar , Microsoft Research, Beijing 100080, China
Jianfeng Gao , Microsoft Research, Beijing 100080, China
Xiaodong He , Microsoft Research, Beijing 100080, China
Margaret Mitchell , Microsoft Research, Beijing 100080, China
John C. Platt , Microsoft Research, Beijing 100080, China
C. Lawrence Zitnick , Microsoft Research, Beijing 100080, China
Geoffrey Zweig , Microsoft Research, Beijing 100080, China
pp. 1473-1482

Semi-supervised low-rank mapping learning for multi-label classification (Abstract)

Liping Jing , Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, China
Liu Yang , Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, China
Jian Yu , Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, China
Michael K. Ng , Department of Mathematics, Hong Kong Baptist Unviersity, Hong Kong
pp. 1483-1491

ConceptLearner: Discovering visual concepts from weakly labeled image collections (Abstract)

Bolei Zhou , MIT, Cambridge, 02139, United States
Vignesh Jagadeesh , eBay Research Labs, United States
Robinson Piramuthu , eBay Research Labs, United States
pp. 1492-1500

Computationally bounded retrieval (Abstract)

Mohammad Rastegari , University of Maryland, College Park, 20742, United States
Cem Keskin , Microsoft Research, Beijing 100080, China
Pushmeet Kohli , Microsoft Research, Beijing 100080, China
Shahram Izadi , Microsoft Research, Beijing 100080, China
pp. 1501-1509

Viewpoints and keypoints (Abstract)

Shubham Tulsiani , University of California, Berkeley, 94720, United States
Jitendra Malik , University of California, Berkeley, 94720, United States
pp. 1510-1519

Discrete hyper-graph matching (Abstract)

Junchi Yan , Shanghai Jiao Tong University, Minhang, China
Chao Zhang , IBM Research, 650 Harry Rd, San Jose, CA 95120, United States
Hongyuan Zha , Georgia Institute of Technology, North Ave NW, Atlanta, 30332, United States
Wei Liu , IBM Research, 650 Harry Rd, San Jose, CA 95120, United States
Xiaokang Yang , Shanghai Jiao Tong University, Minhang, China
Stephen M. Chu , IBM Research, 650 Harry Rd, San Jose, CA 95120, United States
pp. 1520-1528

Rolling shutter motion deblurring (Abstract)

Shuochen Su , University of British Columbia, 2329 West Mall, Vancouver, V6T 1Z4, Canada
Wolfgang Heidrich , KAUST, Thuwal Saudi Arabia
pp. 1529-1537

Learning to generate chairs with convolutional neural networks (Abstract)

Alexey Dosovitskiy , Department of Computer Science, University of Freiburg, Germany
Jost Tobias Springenberg , Department of Computer Science, University of Freiburg, Germany
Thomas Brox , Department of Computer Science, University of Freiburg, Germany
pp. 1538-1546

Accurate depth map estimation from a lenslet light field camera (Abstract)

Hae-Gon Jeon , Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
Jaesik Park , Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
Gyeongmin Choe , Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
Jinsun Park , Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
Yunsu Bok , Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
Yu-Wing Tai , Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
In So Kweon , Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
pp. 1547-1555

Deep semantic ranking based hashing for multi-label image retrieval (Abstract)

Fang Zhao , Center for Research on Intelligent Perception and Computing, Institute of Automation, Chinese Academy of Sciences, China
Yongzhen Huang , Center for Research on Intelligent Perception and Computing, Institute of Automation, Chinese Academy of Sciences, China
Liang Wang , Center for Research on Intelligent Perception and Computing, Institute of Automation, Chinese Academy of Sciences, China
Tieniu Tan , Center for Research on Intelligent Perception and Computing, Institute of Automation, Chinese Academy of Sciences, China
pp. 1556-1564

Similarity learning on an explicit polynomial kernel feature map for person re-identification (Abstract)

Dapeng Chen , Xi'an Jiaotong University, China
Zejian Yuan , Xi'an Jiaotong University, China
Gang Hua , Stevens Institute of Technology, 1 Castle Point Terrace, Hoboken, New Jersey 07030, United States
Nanning Zheng , Xi'an Jiaotong University, China
Jingdong Wang , Microsoft Research, Beijing 100080, China
pp. 1565-1573

Learning to propose objects (Abstract)

Philipp Krahenbuhl , UC Berkeley, California, United States
Vladlen Koltun , Intel Labs, 4720 Forbes Ave, Pittsburgh, PA 15213, United States
pp. 1574-1582

Basis mapping based boosting for object detection (Abstract)

Haoyu Ren , Vision and Media Lab, School of Computing Science, Simon Fraser University, Vancouver, BC, Canada
Ze-Nian Li , Vision and Media Lab, School of Computing Science, Simon Fraser University, Vancouver, BC, Canada
pp. 1583-1591

Computing the stereo matching cost with a convolutional neural network (Abstract)

Jure Zbontar , University of Ljubljana, Kongresni trg 12, 1000, Slovenia
Yann LeCun , New York University, United States
pp. 1592-1599

Recognize complex events from static images by fusing deep channels (Abstract)

Yuanjun Xiong , Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong
Kai Zhu , Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong
Dahua Lin , Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong
Xiaoou Tang , Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong
pp. 1600-1609

Multi-feature max-margin hierarchical Bayesian model for action recognition (Abstract)

Shuang Yang , NLPR, Institution of Automation, CAS, Beijing, China
Chunfeng Yuan , NLPR, Institution of Automation, CAS, Beijing, China
Baoxin Wu , NLPR, Institution of Automation, CAS, Beijing, China
Weiming Hu , NLPR, Institution of Automation, CAS, Beijing, China
Fangshi Wang , Beijing Jiaotong University, China
pp. 1610-1618

Model recommendation: Generating object detectors from few samples (Abstract)

Yu-Xiong Wang , Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, United States
Martial Hebert , Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, United States
pp. 1619-1628

A linear least-squares solution to elastic Shape-from-Template (Abstract)

Abed Malti , Fluminance/INRIA, Rennes, France
Adrien Bartoli , ALCoV/ISIT, UMR 6284 CNRS/Université d'Auvergne, Clermont-Ferrand, France
Richard Hartley , Australian National University and NICTA, Canberra, Australia
pp. 1629-1637

Robust large scale monocular visual SLAM (Abstract)

Guillaume Bourmaud , Univ. Bordeaux, CNRS, IMS, UMR 5218, F-33400 Talence, France
Remi Megret , Univ. Bordeaux, CNRS, IMS, UMR 5218, F-33400 Talence, France
pp. 1638-1647

Membership representation for detecting block-diagonal structure in low-rank or sparse subspace clustering (Abstract)

Minsik Lee , Division of EE, Hanyang University, Korea
Jieun Lee , Department of ECE, Ajou University, Korea
Hyeogjin Lee , Graduate School of CST, Seoul National University, Korea
Nojun Kwak , Graduate School of CST, Seoul National University, Korea
pp. 1648-1656

Bayesian inference for neighborhood filters with application in denoising (Abstract)

Chao-Tsung Huang , National Tsing Hua University, Taiwan
pp. 1657-1665

Deep LAC: Deep localization, alignment and classification for fine-grained recognition (Abstract)

Di Lin , The Chinese University of Hong Kong, Hong Kong
Xiaoyong Shen , The Chinese University of Hong Kong, Hong Kong
Cewu Lu , Hong Kong University of Science and Technology, Hong Kong
Jiaya Jia , The Chinese University of Hong Kong, Hong Kong
pp. 1666-1674

Unconstrained realtime facial performance capture (Abstract)

Pei-Lun Hsieh , University of Southern California, Los Angeles, United States
Chongyang Ma , University of Southern California, Los Angeles, United States
Jihun Yu , Industrial Light & Magic, 1110 Gorgas Ave, San Francisco, CA 94129, United States
Hao Li , University of Southern California, Los Angeles, United States
pp. 1675-1683

Blind optical aberration correction by exploring geometric and visual priors (Abstract)

Tao Yue , Department of Automation, Tsinghua University, Beijing, China
Jinli Suo , Department of Automation, Tsinghua University, Beijing, China
Jue Wang , Adobe Research, Tucson, AZ 85712, United States
Xun Cao , School of Electronic Science and Engineering, Nanjing University, China
Qionghai Dai , Department of Automation, Tsinghua University, Beijing, China
pp. 1684-1692

Ontological supervision for fine grained classification of Street View storefronts (Abstract)

Yair Movshovitz-Attias , Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA 15213, United States
Qian Yu , Google, California, United States
Martin C. Stumpe , Google, California, United States
Vinay Shet , Google, California, United States
Sacha Arnoud , Google, California, United States
Liron Yatziv , Google, California, United States
pp. 1693-1702

Finding distractors in images (Abstract)

Ohad Fried , Princeton University, New Jersey 08544, United States
Eli Shechtman , Adobe Research, Tucson, AZ 85712, United States
Dan B Goldman , Adobe Research, Tucson, AZ 85712, United States
Adam Finkelstein , Princeton University, New Jersey 08544, United States
pp. 1703-1712

From image-level to pixel-level labeling with Convolutional Networks (Abstract)

Pedro O. Pinheiro , Idiap Research Institute, Martigny, Switzerland
Ronan Collobert , Idiap Research Institute, Martigny, Switzerland
pp. 1713-1721

Semantic alignment of LiDAR data at city scale (Abstract)

Fisher Yu , Princeton University, New Jersey 08544, United States
Jianxiong Xiao , Princeton University, New Jersey 08544, United States
Thomas Funkhouser , Princeton University, New Jersey 08544, United States
pp. 1722-1731

Oriented edge forests for boundary detection (Abstract)

Sam Hallman , Department of Computer Science, University of California, Irvine, United States
Charless C. Fowlkes , Department of Computer Science, University of California, Irvine, United States
pp. 1732-1740

Query-adaptive late fusion for image search and person re-identification (Abstract)

Liang Zheng , State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing 100084, China
Shengjin Wang , State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing 100084, China
Lu Tian , State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing 100084, China
Fei He , State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing 100084, China
Ziqiong Liu , State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing 100084, China
Qi Tian , University of Texas at San Antonio, 78249, USA
pp. 1741-1750

Filtered channel features for pedestrian detection (Abstract)

Shanshan Zhang , Max Planck Institute for Informatics, Saarbrücken, Germany
Rodrigo Benenson , Max Planck Institute for Informatics, Saarbrücken, Germany
Bernt Schiele , Max Planck Institute for Informatics, Saarbrücken, Germany
pp. 1751-1760

GRSA: Generalized range swap algorithm for the efficient optimization of MRFs (Abstract)

Kangwei Liu , Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), China
Junge Zhang , Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), China
Peipei Yang , Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), China
Kaiqi Huang , Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), China
pp. 1761-1769

PatchCut: Data-driven object segmentation via local shape transfer (Abstract)

Jimei Yang , UC Merced, 5200 Lake Rd, California 95343, United States
Brian Price , Adobe Research, Tucson, AZ 85712, United States
Scott Cohen , Adobe Research, Tucson, AZ 85712, United States
Zhe Lin , Adobe Research, Tucson, AZ 85712, United States
Ming-Hsuan Yang , UC Merced, 5200 Lake Rd, California 95343, United States
pp. 1770-1778

Illumination and reflectance spectra separation of a hyperspectral image meets low-rank matrix factorization (Abstract)

Yinqiang Zheng , National Institute of Informatics, Chiyoda-ku, Tokyo, Japan
Imari Sato , National Institute of Informatics, Chiyoda-ku, Tokyo, Japan
Yoichi Sato , The University of Tokyo, Bunkyo, 113-8654, Japan
pp. 1779-1787

Semantic part segmentation using compositional model combining shape and appearance (Abstract)

Jianyu Wang , University of California, Los Angeles, United States
Alan Yuille , University of California, Los Angeles, United States
pp. 1788-1797

A discriminative CNN video representation for event detection (Abstract)

Zhongwen Xu , QCIS, University of Technology, Sydney, Australia
Yi Yang , QCIS, University of Technology, Sydney, Australia
Alexander G. Hauptmann , SCS, Carnegie Mellon University, Pittsburgh, PA 15213, United States
pp. 1798-1807

24/7 place recognition by view synthesis (Abstract)

Akihiko Torii , Department of Mechanical and Control Engineering, Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan
Relja Arandjelovic , WILLOW project, Laboratoire d'Informatique de l'École Normale Supérieure, ENS/INRIA/CNRS UMR 8548, France
Josef Sivic , WILLOW project, Laboratoire d'Informatique de l'École Normale Supérieure, ENS/INRIA/CNRS UMR 8548, France
Masatoshi Okutomi , Department of Mechanical and Control Engineering, Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan
Tomas Pajdla , Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Enginnering, Czech Technical University in Prague, Czech Republic
pp. 1808-1817

Understanding image virality (Abstract)

Arturo Deza , UC Santa Barbara, California 93106, United States
Devi Parikh , Virginia Tech, Blacksburg, 24061, United States
pp. 1818-1826

Book2Movie: Aligning video scenes with book chapters (Abstract)

Makarand Tapaswi , Karlsruhe Institute of Technology, 76131, Germany
Martin Bauml , Karlsruhe Institute of Technology, 76131, Germany
Rainer Stiefelhagen , Karlsruhe Institute of Technology, 76131, Germany
pp. 1827-1835

3D model-based continuous emotion recognition (Abstract)

Hui Chen , Beijing Key Lab of Human-computer Interaction, Institute of Software, Chinese Academy of Sciences, China, 100190
Jiangdong Li , University of Chinese Academy of Sciences, Beijing 100049, China
Fengjun Zhang , State Key Lab of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China, 100190
Yang Li , Beijing Key Lab of Human-computer Interaction, Institute of Software, Chinese Academy of Sciences, China, 100190
Hongan Wang , University of Chinese Academy of Sciences, Beijing 100049, China
pp. 1836-1845

Learning to rank in person re-identification with metric ensembles (Abstract)

Sakrapee Paisitkriangkrai , The University of Adelaide, Australia
Chunhua Shen , The University of Adelaide, Australia
Anton van den Hengel , The University of Adelaide, Australia
pp. 1846-1855

Making better use of edges via perceptual grouping (Abstract)

Yonggang Qi , Beijing University of Posts and Telecommunications, China
Yi-Zhe Song , Queen Mary University of London, UK
Tao Xiang , Queen Mary University of London, UK
Honggang Zhang , Beijing University of Posts and Telecommunications, China
Timothy Hospedales , Queen Mary University of London, UK
Yi Li , Queen Mary University of London, UK
Jun Guo , Beijing University of Posts and Telecommunications, China
pp. 1856-1865

Real-time joint estimation of camera orientation and vanishing points (Abstract)

Jeong-Kyun Lee , Computer Vision Laboratory, Gwangju Institute of Science and Technology, Korea
Kuk-Jin Yoon , Computer Vision Laboratory, Gwangju Institute of Science and Technology, Korea
pp. 1866-1874

Sketch-based 3D shape retrieval using Convolutional Neural Networks (Abstract)

Fang Wang , NICTA and ANU, USA
Le Kang , ECE, University of Maryland at College Park, USA
Yi Li , NICTA and ANU, USA
pp. 1875-1883

Salient object detection via bootstrap learning (Abstract)

Na Tong , Dalian University of Technology, China
Huchuan Lu , Dalian University of Technology, China
Xiang Ruan , OMRON Corporation, Japan
Ming-Hsuan Yang , University of California at Merced, USA
pp. 1884-1892

Towards Open World Recognition (Abstract)

Abhijit Bendale , University of Colorado at Colorado Springs, USA
Terrance Boult , University of Colorado at Colorado Springs, USA
pp. 1893-1902

Data-driven 3D Voxel Patterns for object category recognition (Abstract)

Yu Xiang , Stanford University, USA
Wongun Choi , NEC Laboratories America, Inc., USA
Yuanqing Lin , NEC Laboratories America, Inc., USA
Silvio Savarese , Stanford University, USA
pp. 1903-1911

3D ShapeNets: A deep representation for volumetric shapes (Abstract)

Zhirong Wu , Princeton University, USA
Shuran Song , Princeton University, USA
Aditya Khosla , Massachusetts Institute of Technology, USA
Fisher Yu , Princeton University, USA
Linguang Zhang , Princeton University, USA
Xiaoou Tang , Chinese University of Hong Kong, China
Jianxiong Xiao , Princeton University, USA
pp. 1912-1920

Robust image alignment with multiple feature descriptors and matching-guided neighborhoods (Abstract)

Kuang-Jui Hsu , Academia Sinica, Taiwan
Yen-Yu Lin , Academia Sinica, Taiwan
Yung-Yu Chuang , National Taiwan University, Taiwan
pp. 1921-1930

Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A (Abstract)

Brendan F. Klare , Noblis, Falls Church, VA, U.S.A.
Ben Klein , Noblis, Falls Church, VA, U.S.A.
Emma Taborsky , Noblis, Falls Church, VA, U.S.A.
Austin Blanton , Noblis, Falls Church, VA, U.S.A.
Jordan Cheney , Noblis, Falls Church, VA, U.S.A.
Kristen Allen , Noblis, Falls Church, VA, U.S.A.
Patrick Grother , National Institute of Standards and Technology (NIST), Gaithersburg, MD, U.S.A.
Alan Mah , Washington, DC, U.S.A.
Mark Burge , Intelligence Advanced Research Projects Activity (IARPA), McLean, VA, U.S.A.
Anil K. Jain , Michigan State University, East Lansing, U.S.A.
pp. 1931-1939

Depth from shading, defocus, and correspondence using light-field angular coherence (Abstract)

Pratul P. Srinivasan , University of California, Berkeley, USA
Szymon Rusinkiewicz , Princeton University, USA
Ravi Ramamoorthi , University of California, San Diego, USA
pp. 1940-1948

New insights into Laplacian similarity search (Abstract)

Xiao-Ming Wu , Department of Electrical Engineering, Columbia University, USA
Zhenguo Li , Huawei Noah's Ark Lab, Hong Kong
Shih-Fu Chang , Department of Electrical Engineering, Columbia University, USA
pp. 1949-1957

Feature-independent context estimation for automatic image annotation (Abstract)

Amara Tariq , The Computational Imaging Lab., Computer Science, University of Central Florida, Orlando, USA
Hassan Foroosh , The Computational Imaging Lab., Computer Science, University of Central Florida, Orlando, USA
pp. 1958-1965

Category-specific object reconstruction from a single image (Abstract)

Abhishek Kar , University of California, Berkeley, 94720, USA
Shubham Tulsiani , University of California, Berkeley, 94720, USA
Joao Carreira , University of California, Berkeley, 94720, USA
Jitendra Malik , University of California, Berkeley, 94720, USA
pp. 1966-1974

Active sample selection and correction propagation on a gradually-augmented graph (Abstract)

Hang Su , Department of Computer Science and Technology, Tsinghua Univelrsity, China
Zhaozheng Yin , Department of Computer Science, Missouri University of Science and Technology, USA
Takeo Kanade , Robotics Institute, Carnegie Mellon University, USA
Seungil Huh , Department of Computer Science and Technology, Tsinghua Univelrsity, China
pp. 1975-1983

Efficient and accurate approximations of nonlinear convolutional networks (Abstract)

Xiangyu Zhang , Xi'an Jiaotong University, China
Jianhua Zou , Xi'an Jiaotong University, China
Xiang Ming , Xi'an Jiaotong University, China
Kaiming He , Microsoft Research, USA
Jian Sun , Microsoft Research, USA
pp. 1984-1992

Ranking and retrieval of image sequences from multiple paragraph queries (Abstract)

Gunhee Kim , Seoul National University, Korea
Seungwhan Moon , Carnegie Mellon University, USA
Leonid Sigal , Disney Research Pittsburgh, USA
pp. 1993-2001

Casual stereoscopic panorama stitching (Abstract)

Fan Zhang , Department of Computer Science, USA
Feng Liu , Department of Computer Science, USA
pp. 2002-2010

Superpixel meshes for fast edge-preserving surface reconstruction (Abstract)

Andras Bodis-Szomoru , Computer Vision Lab, ETH Zurich, Switzerland
Hayko Riemenschneider , Computer Vision Lab, ETH Zurich, Switzerland
Luc Van Gool , Computer Vision Lab, ETH Zurich, Switzerland
pp. 2011-2020

Best-Buddies Similarity for robust template matching (Abstract)

Tali Dekel , MIT CSAIL, USA
Shaul Oron , Tel Aviv University, Israel
Michael Rubinstein , Google Research, USA
Shai Avidan , Tel Aviv University, Israel
William T. Freeman , MIT CSAIL, USA
pp. 2021-2029

Superdifferential cuts for binary energies (Abstract)

Tatsunori Taniai , University of Tokyo, Japan
Yasuyuki Matsushita , Osaka University, Japan
Takeshi Naemura , University of Tokyo, Japan
pp. 2030-2038

The S-HOCK dataset: Analyzing crowds at the stadium (Abstract)

Davide Conigliaro , University of Verona, Italy
Paolo Rota , Vienna University of Technology, Austria
Francesco Setti , ISTC-CNR (Trento), Italy
Chiara Bassetti , ISTC-CNR (Trento), Italy
Nicola Conci , University of Trento, Italy
Nicu Sebe , University of Trento, Italy
Marco Cristani , University of Verona, Italy
pp. 2039-2047

Discriminant analysis on Riemannian manifold of Gaussian distributions for face recognition with image sets (Abstract)

Wen Wang , Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China
Ruiping Wang , Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China
Zhiwu Huang , Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China
Shiguang Shan , Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China
Xilin Chen , Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China
pp. 2048-2057

Texture representations for image and video synthesis (Abstract)

Georgios Georgiadis , UCLA Vision Lab, University of California, Los Angeles, 90095, USA
Alessandro Chiuso , Dept. of Information Eng., University of Padova, 35131, Italy
Stefano Soatto , UCLA Vision Lab, University of California, Los Angeles, 90095, USA
pp. 2058-2066

Shadow optimization from structured deep edge detection (Abstract)

Li Shen , Institute for Infocomm Research, Singapore
Teck Wee Chua , Institute for Infocomm Research, Singapore
Karianto Leman , Institute for Infocomm Research, Singapore
pp. 2067-2074

Total variation regularization of shape signals (Abstract)

Maximilian Baust , Computer Aided Medical Procedures and Augmented Reality, Technische Universität München, Germany
Laurent Demaret , Institute of Computational Biology, Helmholtz Zentrum München, Germany
Martin Storath , Biomedical Imaging Group, EPFL, Lausanne, 4Johns Hopkins University, Baltimore, USA
Nassir Navab , Computer Aided Medical Procedures and Augmented Reality, Technische Universität München, Germany
Andreas Weinmann , Institute of Computational Biology, Helmholtz Zentrum München, Germany
pp. 2075-2083

Learning similarity metrics for dynamic scene segmentation (Abstract)

Damien Teney , Carnegie Mellon University, USA
Matthew Brown , University of Bath, UK
Dimitry Kit , University of Bath, UK
Peter Hall , University of Bath, UK
pp. 2084-2093

Subspace clustering by Mixture of Gaussian Regression (Abstract)

Baohua Li , Dalian University of Technology, China
Ying Zhang , Dalian University of Technology, China
Zhouchen Lin , Key Laboratory of Machine Perception (MOE), School of EECS, Peking University, China
Huchuan Lu , Dalian University of Technology, China
pp. 2094-2102

DASC: Dense adaptive self-correlation descriptor for multi-modal and multi-spectral correspondence (Abstract)

Seungryong Kim , Yonsei University, Korea
Dongbo Min , Chungnam Nat. University, Korea
Bumsub Ham , Inria, France
Seungchul Ryu , Yonsei University, Korea
Minh N. Do , UIUC, USA
Kwanghoon Sohn , Yonsei University, Korea
pp. 2103-2112

In defense of color-based model-free tracking (Abstract)

Horst Possegger , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Thomas Mauthner , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Horst Bischof , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
pp. 2113-2120

Best of both worlds: Human-machine collaboration for object annotation (Abstract)

Olga Russakovsky , Stanford University, USA
Li-Jia Li , Snapchat, USA
Li Fei-Fei , Stanford University, USA
pp. 2121-2131

Robust multiple homography estimation: An ill-solved problem (Abstract)

Zygmunt L. Szpak , School of Computer Science, The University of Adelaide, SA 5005, Australia
Wojciech Chojnacki , School of Computer Science, The University of Adelaide, SA 5005, Australia
Anton van den Hengel , School of Computer Science, The University of Adelaide, SA 5005, Australia
pp. 2132-2141

Semi-supervised Domain Adaptation with Subspace Learning for visual recognition (Abstract)

Ting Yao , Microsoft Research, Beijing, China
Yingwei Pan , University of Science and Technology of China, Hefei, China
Chong-Wah Ngo , City University of Hong Kong, Kowloon, Hong Kong
Houqiang Li , University of Science and Technology of China, Hefei, China
Tao Mei , Microsoft Research, Beijing, China
pp. 2142-2150

Articulated motion discovery using pairs of trajectories (Abstract)

Luca Del Pero , University of Edinburgh, Scotland
Susanna Ricco , Google Research, USA
Rahul Sukthankar , Google Research, USA
Vittorio Ferrari , University of Edinburgh, Scotland
pp. 2151-2160

A solution for multi-alignment by transformation synchronisation (Abstract)

Florian Bernard , Centre Hospitalier de Luxembourg, Luxembourg
Johan Thunberg , Luxembourg Centre for Systems Biomedicine, University of Luxembourg, Luxembourg
Peter Gemmar , Trier University of Applied Sciences, Germany
Frank Hertel , Centre Hospitalier de Luxembourg, Luxembourg
Andreas Husch , Centre Hospitalier de Luxembourg, Luxembourg
Jorge Goncalves , Luxembourg Centre for Systems Biomedicine, University of Luxembourg, Luxembourg
pp. 2161-2169

A convex optimization approach to robust fundamental matrix estimation (Abstract)

Y. Cheng , Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
J. A. Lopez , Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
O. Camps , Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
M. Sznaier , Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
pp. 2170-2178

Simultaneous pose and non-rigid shape with particle dynamics (Abstract)

Antonio Agudo , Instituto de Investigación en Ingeniería de Aragón (I3A), Universidad de Zaragoza, Spain
Francesc Moreno-Noguer , Institut de RobÒtica i Informàtica Industrial (CSIC-UPC), Barcelona, Spain
pp. 2179-2187

Semi-supervised learning with explicit relationship regularization (Abstract)

Kwang In Kim , Lancaster University, UK
James Tompkin , Harvard SEAS, USA
Hanspeter Pfister , Harvard SEAS, USA
Christian Theobalt , MPI for Informatics, Germany
pp. 2188-2196

Person re-identification by Local Maximal Occurrence representation and metric learning (Abstract)

Shengcai Liao , Center for Biometrics and Security Research, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 95 Zhongguancun East Road, Beijing 100190, China
Yang Hu , Center for Biometrics and Security Research, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 95 Zhongguancun East Road, Beijing 100190, China
Xiangyu Zhu , Center for Biometrics and Security Research, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 95 Zhongguancun East Road, Beijing 100190, China
Stan Z. Li , Center for Biometrics and Security Research, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 95 Zhongguancun East Road, Beijing 100190, China
pp. 2197-2206

Joint patch and multi-label learning for facial action unit detection (Abstract)

Kaili Zhao , School of Comm. and Info. Engineering, Beijing University of Posts and Telecom., China
Wen-Sheng Chu , Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Fernando De la Torre , Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Jeffrey F. Cohn , Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Honggang Zhang , School of Comm. and Info. Engineering, Beijing University of Posts and Telecom., China
pp. 2207-2216

Real-time visual analysis of microvascular blood flow for critical care (Abstract)

Chao Liu , Carnegie Mellon University, The Robotics Institute, USA
Hernando Gomez , University of Pittsburgh, School of Medicine, USA
Srinivasa Narasimhan , Carnegie Mellon University, The Robotics Institute, USA
Artur Dubrawski , Carnegie Mellon University, The Robotics Institute, USA
Michael R. Pinsky , University of Pittsburgh, School of Medicine, USA
Brian Zuckerbraun , University of Pittsburgh, School of Medicine, USA
pp. 2217-2225

JOTS: Joint Online Tracking and Segmentation (Abstract)

Longyin Wen , NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, CHN
Dawei Du , SCCE, University of Chinese Academy of Sciences, Beijing, CHN
Zhen Lei , NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, CHN
Stan Z. Li , NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, CHN
Ming-Hsuan Yang , School of Engineering, University of California at Merced, USA
pp. 2226-2234

Gaze-enabled egocentric video summarization via constrained submodular maximization (Abstract)

Jia Xu , University of Wisconsin-Madison, USA
Lopamudra Mukherjee , University of Wisconsin-Whitewater, USA
Yin Li , Georgia Institute of Technology, USA
Jamieson Warner , University of Wisconsin-Madison, USA
James M. Rehg , Georgia Institute of Technology, USA
Vikas Singh , University of Wisconsin-Madison, USA
pp. 2235-2244

Sparse depth super resolution (Abstract)

Jiajun Lu , University of Illinois at Urbana Champaign, USA
David Forsyth , University of Illinois at Urbana Champaign, USA
pp. 2245-2253

Efficient illuminant estimation for color constancy using grey pixels (Abstract)

Kai-Fu Yang , University of Electronic Science and Technology of China, Chengdu, China
Shao-Bing Gao , University of Electronic Science and Technology of China, Chengdu, China
Yong-Jie Li , University of Electronic Science and Technology of China, Chengdu, China
pp. 2254-2263

Can humans fly? Action understanding with multiple classes of actors (Abstract)

Chenliang Xu , Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, USA
Shao-Hang Hsieh , Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, USA
Caiming Xiong , Statistics, University of California, Los Angeles, USA
Jason J. Corso , Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, USA
pp. 2264-2273

Reweighted laplace prior based hyperspectral compressive sensing for unknown sparsity (Abstract)

Yanning Zhang , School of Computer Science, Northwestern Polytechnical University, Xi'an, 710072, China
Chunna Tian , School of Electronic Engineering, Xidian University, Xi'an, 710071, China
Fei Li , School of Computer Science, Northwestern Polytechnical University, Xi'an, 710072, China
pp. 2274-2281

Class consistent multi-modal fusion with binary features (Abstract)

Ashish Shrivastava , University of Maryland, College Park, USA
Mohammad Rastegari , University of Maryland, College Park, USA
Sumit Shekhar , University of Maryland, College Park, USA
Rama Chellappa , University of Maryland, College Park, USA
Larry S. Davis , University of Maryland, College Park, USA
pp. 2282-2291

R6P - Rolling shutter absolute pose problem (Abstract)

Cenek Albl , Czech Technical University in Prague, Faculty of Electrical engineering, 166 27 Praha 6, Technicka 2, Czech Republic
Zuzana Kukelova , Microsoft Research Ltd, 21 Station Road, Cambridge CB1 2FB, UK
Tomas Pajdla , Czech Technical University in Prague, Faculty of Electrical engineering, 166 27 Praha 6, Technicka 2, Czech Republic
pp. 2292-2300

Embedded phase shifting: Robust phase shifting with embedded signals (Abstract)

Daniel Moreno , Brown University, Providence, RI, USA
Kilho Son , Brown University, Providence, RI, USA
Gabriel Taubin , Brown University, Providence, RI, USA
pp. 2301-2309

Shape and light directions from shading and polarization (Abstract)

Trung Thanh Ngo , Faculty of Information Science and Electrical Engineering, Kyushu University, Japan
Hajime Nagahara , Faculty of Information Science and Electrical Engineering, Kyushu University, Japan
Rin-ichiro Taniguchi , Faculty of Information Science and Electrical Engineering, Kyushu University, Japan
pp. 2310-2318

3D deep shape descriptor (Abstract)

Yi Fang , Department of Electrical and Computer Engineering, New York University Abu Dhabi, UAE
Jin Xie , Department of Electrical and Computer Engineering, New York University Abu Dhabi, UAE
Guoxian Dai , Department of Electrical and Computer Engineering, New York University Abu Dhabi, UAE
Meng Wang , Department of Electrical and Computer Engineering, New York University Abu Dhabi, UAE
Fan Zhu , Department of Electrical and Computer Engineering, New York University Abu Dhabi, UAE
Tiantian Xu , Polytechnic School of Engineering, New York University, USA
Edward Wong , Polytechnic School of Engineering, New York University, USA
pp. 2319-2328

Cross-age face verification by coordinating with cross-face age verification (Abstract)

Liang Du , Department of Computer and Information Sciences, Temple University, Philadelphia, USA
Haibin Ling , Department of Computer and Information Sciences, Temple University, Philadelphia, USA
pp. 2329-2338

Beyond Mahalanobis metric: Cayley-Klein metric learning (Abstract)

Yanhong Bi , Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
Bin Fan , Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
Fuchao Wu , Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
pp. 2339-2347

From dictionary of visual words to subspaces: Locality-constrained affine subspace coding (Abstract)

Peihua Li , School of Information and Communication Engineering, Dalian University of Technology, China
Xiaoxiao Lu , School of Information and Communication Engineering, Dalian University of Technology, China
Qilong Wang , School of Information and Communication Engineering, Dalian University of Technology, China
pp. 2348-2357

FPA-CS: Focal plane array-based compressive imaging in short-wave infrared (Abstract)

Huaijin Chen , ECE Department, Rice University, Houston, TX, USA
M. Salman Asif , ECE Department, Rice University, Houston, TX, USA
Aswin C. Sankaranarayanan , ECE Department, Carnegie Mellon University, Pittsburgh, PA, USA
Ashok Veeraraghavan , ECE Department, Rice University, Houston, TX, USA
pp. 2358-2366

BOLD - Binary online learned descriptor for efficient image matching (Abstract)

Vassileios Balntas , University of Surrey, UK
Lilian Tang , University of Surrey, UK
Krystian Mikolajczyk , University of Surrey, UK
pp. 2367-2375

Defocus deblurring and superresolution for time-of-flight depth cameras (Abstract)

Lei Xiao , University of British Columbia, Canada
Felix Heide , University of British Columbia, Canada
Matthew O'Toole , University of Toronto, Canada
Andreas Kolb , University of Siegen, Germany
Matthias B. Hullin , University of Bonn, Germany
Kyros Kutulakos , University of Toronto, Canada
Wolfgang Heidrich , KAUST, Saudi Arabia
pp. 2376-2384

Burst deblurring: Removing camera shake through fourier burst accumulation (Abstract)

Mauricio Delbracio , ECE, Duke University, USA
Guilermo Sapiro , ECE, Duke University, USA
pp. 2385-2393

SOM: Semantic obviousness metric for image quality assessment (Abstract)

Peng Zhang , Department of Electronic Engineering and Information Science, University of Science and Technology of China, China
Wengang Zhou , Department of Electronic Engineering and Information Science, University of Science and Technology of China, China
Lei Wu , Department of Electronic Engineering and Information Science, University of Science and Technology of China, China
Houqiang Li , Department of Electronic Engineering and Information Science, University of Science and Technology of China, China
pp. 2394-2402

DeepID-Net: Deformable deep convolutional neural networks for object detection (Abstract)

Wanli Ouyang , The Chinese University of Hong Kong, China
Xiaogang Wang , The Chinese University of Hong Kong, China
Xingyu Zeng , The Chinese University of Hong Kong, China
Shi Qiu , The Chinese University of Hong Kong, China
Ping Luo , The Chinese University of Hong Kong, China
Yonglong Tian , The Chinese University of Hong Kong, China
Hongsheng Li , The Chinese University of Hong Kong, China
Shuo Yang , The Chinese University of Hong Kong, China
Zhe Wang , The Chinese University of Hong Kong, China
Chen-Change Loy , The Chinese University of Hong Kong, China
Xiaoou Tang , The Chinese University of Hong Kong, China
pp. 2403-2412

Efficient globally optimal consensus maximisation with tree search (Abstract)

Tat-Jun Chin , School of Computer Science, The University of Adelaide, Australia
Pulak Purkait , School of Computer Science, The University of Adelaide, Australia
Anders Eriksson , School of Electrical Engineering and Computer Science, Queensland University of Technology, Australia
David Suter , School of Computer Science, The University of Adelaide, Australia
pp. 2413-2421

Mind's eye: A recurrent visual representation for image caption generation (Abstract)

Xinlei Chen , Carnegie Mellon University, USA
C. Lawrence Zitnick , Microsoft Research, Redmond, USA
pp. 2422-2431

Hierarchical sparse coding with geometric prior for visual geo-location (Abstract)

Raghuraman Gopalan , AT&T Labs-Research, Dept. of Video and Multimedia Technologies Research, Middletown NJ 07748 USA
pp. 2432-2439

P3.5P: Pose estimation with unknown focal length (Abstract)

Changchang Wu , Google Inc., USA
pp. 2440-2448

Joint vanishing point extraction and tracking (Abstract)

Till Kroeger , Computer Vision Laboratory, D-ITET, ETH Zurich, Switzerland
Dengxin Dai , Computer Vision Laboratory, D-ITET, ETH Zurich, Switzerland
Luc Van Gool , Computer Vision Laboratory, D-ITET, ETH Zurich, Switzerland
pp. 2449-2457

Learning a non-linear knowledge transfer model for cross-view action recognition (Abstract)

Hossein Rahmani , Computer Science and Software Engineering, The University of Western Australia, Australia
Ajmal Mian , Computer Science and Software Engineering, The University of Western Australia, Australia
pp. 2458-2466

Random tree walk toward instantaneous 3D human pose estimation (Abstract)

Ho Yub Jung , Div. of Comp. & Elect. Sys. Eng., Hankuk U. of Foreign Studies, Yongin, Korea, 449-791
Soochahn Lee , Dept. of Elect. Eng., Soonchunghyang U., Asan-si, Korea, 336-745
Yong Seok Heo , Dept. of Elect. & Comp. Eng., Ajou University, Suwon, Korea, 336-745
Il Dong Yun , Div. of Comp. & Elect. Sys. Eng., Hankuk U. of Foreign Studies, Yongin, Korea, 449-791
pp. 2467-2474

Deep hashing for compact binary codes learning (Abstract)

Venice Erin Liong , Advanced Digital Sciences Center, Singapore
Jiwen Lu , Advanced Digital Sciences Center, Singapore
Gang Wang , Advanced Digital Sciences Center, Singapore
Pierre Moulin , Advanced Digital Sciences Center, Singapore
Jie Zhou , Department of Automation, Tsinghua University, Beijing, China
pp. 2475-2483

Completing 3D object shape from one depth image (Abstract)

Jason Rock , University of Illinois at Urbana-Champaign, USA
Tanmay Gupta , University of Illinois at Urbana-Champaign, USA
Justin Thorsen , University of Illinois at Urbana-Champaign, USA
JunYoung Gwak , University of Illinois at Urbana-Champaign, USA
Daeyun Shin , University of Illinois at Urbana-Champaign, USA
Derek Hoiem , University of Illinois at Urbana-Champaign, USA
pp. 2484-2493

Encoding based saliency detection for videos and images (Abstract)

Thomas Mauthner , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Horst Possegger , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Georg Waltner , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Horst Bischof , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
pp. 2494-2502

Online sketching hashing (Abstract)

Cong Leng , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China
Jiaxiang Wu , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China
Jian Cheng , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China
Xiao Bai , School of Computer Science and Engineering, Beihang University, China
Hanqing Lu , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China
pp. 2503-2511

Enriching object detection with 2D-3D registration and continuous viewpoint estimation (Abstract)

Christopher Bongsoo Choy , Stanford University, USA
Michael Stark , Max Planck Institute for Informatics, Germany
Sam Corbett-Davies , Stanford University, USA
Silvio Savarese , Stanford University, USA
pp. 2512-2520

Representing 3D texture on mesh manifolds for retrieval and recognition applications (Abstract)

Naoufel Werghi , Khalifa University of Science, Technology & Research, Sharjah, UAE
Claudio Tortorici , Khalifa University of Science, Technology & Research, Sharjah, UAE
Stefano Berretti , University of Florence, Italy
Alberto Del Bimbo , University of Florence, Italy
pp. 2521-2530

Saliency propagation from simple to difficult (Abstract)

Chen Gong , Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, China
Dacheng Tao , The Centre for Quantum Computation & Intelligent Systems, University of Technology, Sydney, Australia
Wei Liu , IBM T. J. Watson Research Center, USA
S.J. Maybank , Birkbeck College, London, UK
Meng Fang , The Centre for Quantum Computation & Intelligent Systems, University of Technology, Sydney, Australia
Keren Fu , Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, China
Jie Yang , Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, China
pp. 2531-2539

Learning an efficient model of hand shape variation from depth images (Abstract)

Sameh Khamis , University of Maryland, USA
Jonathan Taylor , Microsoft Research, USA
Jamie Shotton , Microsoft Research, USA
Cem Keskin , Microsoft Research, USA
Shahram Izadi , Microsoft Research, USA
Andrew Fitzgibbon , Microsoft Research, USA
pp. 2540-2548

On the minimal problems of low-rank matrix factorization (Abstract)

Fangyuan Jiang , Centre for Mathematical Sciences, Lund University, Sweden
Magnus Oskarsson , Centre for Mathematical Sciences, Lund University, Sweden
Kalle Astrom , Centre for Mathematical Sciences, Lund University, Sweden
pp. 2549-2557

Symmetry-based text line detection in natural scenes (Abstract)

Zheng Zhang , School of Electronic Information and Communications, Huazhong University of Science and Technology, China
Wei Shen , Key Lab of Specialty Fiber Optics and Optical Access Networks, Shanghai University, China
Cong Yao , School of Electronic Information and Communications, Huazhong University of Science and Technology, China
Xiang Bai , School of Electronic Information and Communications, Huazhong University of Science and Technology, China
pp. 2558-2567

DevNet: A Deep Event Network for multimedia event detection and evidence recounting (Abstract)

Chuang Gan , Institute for Interdisciplinary Information Sciences, Tsinghua University, China
Naiyan Wang , Hong Kong University of Science and Technology, China
Yi Yang , Centre for Quantum Computation and Intelligent Systems, University of Technology, Sydney, Australia
Dit-Yan Yeung , Hong Kong University of Science and Technology, China
Alexander G. Hauptmann , School of Computer Science, Carnegie Mellon University, USA
pp. 2568-2577

Learning to detect Motion Boundaries (Abstract)

Philippe Weinzaepfel , Inria, France
Jerome Revaud , Inria, France
Zaid Harchaoui , Inria, France
Cordelia Schmid , Inria, France
pp. 2578-2586

Improving object proposals with multi-thresholding straddling expansion (Abstract)

Xiaozhi Chen , Department of Electronic Engineering, Tsinghua University, China
Huimin Ma , Department of Electronic Engineering, Tsinghua University, China
Xiang Wang , Department of Electronic Engineering, Tsinghua University, China
Zhichen Zhao , Department of Electronic Engineering, Tsinghua University, China
pp. 2587-2595

Visual recognition by counting instances: A multi-instance cardinality potential kernel (Abstract)

Hossein Hajimirsadeghi , School of Computing Science, Simon Fraser University, Canada
Wang Yan , School of Computing Science, Simon Fraser University, Canada
Arash Vahdat , School of Computing Science, Simon Fraser University, Canada
Greg Mori , School of Computing Science, Simon Fraser University, Canada
pp. 2596-2605

Unconstrained 3D face reconstruction (Abstract)

Joseph Roth , Department of Computer Science and Engineering, Michigan State University, USA
Yiying Tong , Department of Computer Science and Engineering, Michigan State University, USA
Xiaoming Liu , Department of Computer Science and Engineering, Michigan State University, USA
pp. 2606-2615

Becoming the expert - interactive multi-class machine teaching (Abstract)

Edward Johns , University College London, UK
Oisin Mac Aodha , University College London, UK
Gabriel J. Brostow , University College London, UK
pp. 2616-2624

Long-term recurrent convolutional networks for visual recognition and description (Abstract)

Jeff Donahue , UC Berkeley, USA
Lisa Anne Hendricks , UC Berkeley, USA
Sergio Guadarrama , UC Berkeley, USA
Marcus Rohrbach , UC Berkeley, USA
Subhashini Venugopalan , UT Austin, TX, USA
Trevor Darrell , UC Berkeley, USA
Kate Saenko , UMass Lowell, MA, USA
pp. 2625-2634

Zero-shot object recognition by semantic manifold distance (Abstract)

Zhenyong Fu , Queen Mary, University of London, E1 4NS, UK
Tao A Xiang , Queen Mary, University of London, E1 4NS, UK
Elyor Kodirov , Queen Mary, University of London, E1 4NS, UK
Shaogang Gong , Queen Mary, University of London, E1 4NS, UK
pp. 2635-2644

Hyper-class augmented and regularized deep learning for fine-grained image classification (Abstract)

Saining Xie , University of California, San Diego, USA
Tianbao Yang , Department of Computer Science, University of Iowa, USA
Xiaoyu Wang , Snapchat Research, USA
Yuanqing Lin , NEC Laboratories America, Inc., USA
pp. 2645-2654

Direct structure estimation for 3D reconstruction (Abstract)

Nianjuan Jiang , Advanced Digital Sciences Center, Singapore
Wen-Yan Lin , Advanced Digital Sciences Center, Singapore
Minh N. Do , University of Illinois at Urbana-Champaign, USA
Jiangbo Lu , Advanced Digital Sciences Center, Singapore
pp. 2655-2663

Global supervised descent method (Abstract)

Xuehan Xiong , Carnegie Mellon University, Pittsburgh PA, USA
Fernando De la Torre , Carnegie Mellon University, Pittsburgh PA, USA
pp. 2664-2673

Robust camera location estimation by convex programming (Abstract)

Onur Ozyesil , Program in Applied and Computational Mathematics, Princeton University, NJ 08544-1000, USA
Amit Singer , Program in Applied and Computational Mathematics, Princeton University, NJ 08544-1000, USA
pp. 2674-2683

Practical robust two-view translation estimation (Abstract)

Johan Fredriksson , Centre for Mathematical Sciences, Lund University, Sweden
Viktor Larsson , Centre for Mathematical Sciences, Lund University, Sweden
Carl Olsson , Centre for Mathematical Sciences, Lund University, Sweden
pp. 2684-2690

Learning from massive noisy labeled data for image classification (Abstract)

Tong Xiao , The Chinese University of Hong Kong, China
Tian Xia , Baidu Research, USA
Yi Yang , Baidu Research, USA
Chang Huang , Baidu Research, USA
Xiaogang Wang , The Chinese University of Hong Kong, China
pp. 2691-2699

KL divergence based agglomerative clustering for automated Vitiligo grading (Abstract)

Mithun Das Gupta , IBM Research Labs, Bangalore India
Srinidhi Srinivasa , Ricoh Innovations Pvt. Ltd., Bangalore, India
J. Madhukara , St. John's Hospital, Bangalore, India
Meryl Antony , St. John's Hospital, Bangalore, India
pp. 2700-2709

Robust saliency detection via regularized random walks ranking (Abstract)

Changyang Li , The University of Sydney, Australia
Yuchen Yuan , The University of Sydney, Australia
Weidong Cai , The University of Sydney, Australia
Yong Xia , Northwestern Polytechnical University, USA
David Dagan Feng , The University of Sydney, Australia
pp. 2710-2717

Weakly supervised semantic segmentation for social images (Abstract)

Wei Zhang , Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, China
Sheng Zeng , Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, China
Dequan Wang , Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, China
Xiangyang Xue , Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, China
pp. 2718-2726

Image specificity (Abstract)

Mainak Jas , Aalto University, Finland
Devi Parikh , Virginia Tech, USA
pp. 2727-2736

Web-scale training for face identification (Abstract)

Yaniv Taigman , Facebook AI Research, Menlo Park, CA 94025, USA
Ming Yang , Facebook AI Research, Menlo Park, CA 94025, USA
Marc'Aurelio Ranzato , Facebook AI Research, Menlo Park, CA 94025, USA
Lior Wolf , Tel Aviv University, Israel
pp. 2746-2754

Dynamically encoded actions based on spacetime saliency (Abstract)

Christoph Feichtenhofer , Institute of Electrical Measurement and Measurement Signal Processing, TU Graz, Austria
Axel Pinz , Institute of Electrical Measurement and Measurement Signal Processing, TU Graz, Austria
Richard P. Wildes , Department of Electrical Engineering and Computer Science, York University, Toronto, Canada
pp. 2755-2764

Three viewpoints toward exemplar SVM (Abstract)

Takumi Kobayashi , National Institute of Advanced Industrial Science and Technology, Umezono 1-1-1, Tsukuba, Japan
pp. 2765-2773

Visual recognition by learning from web data: A weakly supervised domain generalization approach (Abstract)

Li Niu , School of Computer Engineering, Nanyang Technology University (NTU), Singapore
Wen Li , School of Computer Engineering, Nanyang Technology University (NTU), Singapore
Dong Xu , School of Computer Engineering, Nanyang Technology University (NTU), Singapore
pp. 2774-2783

Clustering of static-adaptive correspondences for deformable object tracking (Abstract)

Georg Nebehay , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Roman Pflugfelder , Digital Safety and Security Department, Austrian Institute of Technology, Austria
pp. 2784-2791

Geo-semantic segmentation (Abstract)

Shervin Ardeshir , Center for Research in Computer Vision, University of Central Florida, USA
Kofi Malcolm Collins-Sibley , Northeastern University, USA
Mubarak Shah , Center for Research in Computer Vision, University of Central Florida, USA
pp. 2792-2799

Towards unified depth and semantic prediction from a single image (Abstract)

Peng Wang , University of California, Los Angeles, USA
Xiaohui Shen , Adobe Research, USA
Zhe Lin , Adobe Research, USA
Scott Cohen , Adobe Research, USA
Brian Price , Adobe Research, USA
Alan Yuille , University of California, Los Angeles, USA
pp. 2800-2809

Towards force sensing from vision: Observing hand-object interactions to infer manipulation forces (Abstract)

Tu-Hoa Pham , CNRS-AIST Joint Robotics Laboratory, Japan
Abderrahmane Kheddar , CNRS-AIST Joint Robotics Laboratory, Japan
Ammar Qammaz , Institute of Computer Science, FORTH, Greece
Antonis A. Argyros , Institute of Computer Science, FORTH, Greece
pp. 2810-2819

A MRF shape prior for facade parsing with occlusions (Abstract)

Mateusz Kozinski , Université Paris-Est, LIGM (UMR CNRS 8049), ENPC, F-77455 Marne-la-Vallée, France
Raghudeep Gadde , Université Paris-Est, LIGM (UMR CNRS 8049), ENPC, F-77455 Marne-la-Vallée, France
Sergey Zagoruyko , Université Paris-Est, LIGM (UMR CNRS 8049), ENPC, F-77455 Marne-la-Vallée, France
Guillaume Obozinski , Université Paris-Est, LIGM (UMR CNRS 8049), ENPC, F-77455 Marne-la-Vallée, France
Renaud Marlet , Université Paris-Est, LIGM (UMR CNRS 8049), ENPC, F-77455 Marne-la-Vallée, France
pp. 2820-2828

Probability occupancy maps for occluded depth images (Abstract)

Timur Bagautdinov , École Polytechnique Fédérale de Lausanne (EPFL), Switzerland
Francois Fleuret , IDIAP Research Institute, Switzerland
Pascal Fua , École Polytechnique Fédérale de Lausanne (EPFL), Switzerland
pp. 2829-2837

Segment based 3D object shape priors (Abstract)

Rabeeh Karimi Mahabadi , Department of Computer Science, ETH Zürich, Switzerland
Christian Hane , Department of Computer Science, ETH Zürich, Switzerland
Marc Pollefeys , Department of Computer Science, ETH Zürich, Switzerland
pp. 2838-2846

Shape-from-Template in Flatland (Abstract)

Mathias Gallardo , ALCoV-ISIT, UMR6284 CNRS / Université d'Auvergne, Clermont-Ferrand, France
Daniel Pizarro , ALCoV-ISIT, UMR6284 CNRS / Université d'Auvergne, Clermont-Ferrand, France
Adrien Bartoli , ALCoV-ISIT, UMR6284 CNRS / Université d'Auvergne, Clermont-Ferrand, France
Toby Collins , ALCoV-ISIT, UMR6284 CNRS / Université d'Auvergne, Clermont-Ferrand, France
pp. 2847-2854

Understanding tools: Task-oriented object modeling, learning and recognition (Abstract)

Yixin Zhu , Center for Vision, Cognition, Learning, and Art, University of California, Los Angeles, 90095, USA
Yibiao Zhao , Center for Vision, Cognition, Learning, and Art, University of California, Los Angeles, 90095, USA
Song-Chun Zhu , Center for Vision, Cognition, Learning, and Art, University of California, Los Angeles, 90095, USA
pp. 2855-2864

Deep roto-translation scattering for object classification (Abstract)

Edouard Oyallon , Département Informatique, Ecole Normale Supérieure, 45 rue d'Ulm, 75005 Paris, France
Stephane Mallat , Département Informatique, Ecole Normale Supérieure, 45 rue d'Ulm, 75005 Paris, France
pp. 2865-2873

Non-rigid registration of images with geometric and photometric deformation by using local affine Fourier-moment matching (Abstract)

Hong-Ren Su , Institute of Information Systems and Applications, National Tsing Hua University, Hsinchu, Taiwan
Shang-Hong Lai , Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan
pp. 2874-2882

Detector discovery in the wild: Joint multiple instance and representation learning (Abstract)

Judy Hoffman , UC Berkeley, USA
Deepak Pathak , UC Berkeley, USA
Trevor Darrell , UC Berkeley, USA
Kate Saenko , UMass Lowell, USA
pp. 2883-2891

Deeply learned face representations are sparse, selective, and robust (Abstract)

Yi Sun , Department of Information Engineering, The Chinese University of Hong Kong, China
Xiaogang Wang , Department of Electronic Engineering, The Chinese University of Hong Kong, China
Xiaoou Tang , Department of Information Engineering, The Chinese University of Hong Kong, China
pp. 2892-2900

Unsupervised visual alignment with similarity graphs (Abstract)

Fatemeh Shokrollahi Yancheshmeh , Department of Signal Processing, Tampere University of Technology, Finland
Ke Chen , Department of Signal Processing, Tampere University of Technology, Finland
Joni-Kristian Kamarainen , Department of Signal Processing, Tampere University of Technology, Finland
pp. 2901-2908

Video anomaly detection and localization using hierarchical feature representation and Gaussian process regression (Abstract)

Kai-Wen Cheng , Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, R.O.C.
Yie-Tarng Chen , Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, R.O.C.
Wen-Hsien Fang , Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, R.O.C.
pp. 2909-2917

Inferring 3D layout of building facades from a single image (Abstract)

Jiyan Pan , Google Inc., USA
Martial Hebert , Carnegie Mellon University, USA
Takeo Kanade , Carnegie Mellon University, USA
pp. 2918-2926

Evaluation of output embeddings for fine-grained image classification (Abstract)

Zeynep Akata , Computer Vision and Multimodal Computing, Max Planck Institute for Informatics, Saarbrucken, Germany
Scott Reed , Computer Science and Engineering Division, University of Michigan, Ann Arbor, USA
Daniel Walter , Computer Science and Engineering Division, University of Michigan, Ann Arbor, USA
Honglak Lee , Computer Science and Engineering Division, University of Michigan, Ann Arbor, USA
Bernt Schiele , Computer Vision and Multimodal Computing, Max Planck Institute for Informatics, Saarbrucken, Germany
pp. 2927-2936

Virtual view networks for object reconstruction (Abstract)

Joao Carreira , University of California, Berkeley, 94720, USA
Abhishek Kar , University of California, Berkeley, 94720, USA
Shubham Tulsiani , University of California, Berkeley, 94720, USA
Jitendra Malik , University of California, Berkeley, 94720, USA
pp. 2937-2946

Real-time coarse-to-fine topologically preserving segmentation (Abstract)

Jian Yao , University of Toronto, Canada
Marko Boben , University of Ljubljana, Slovenia
Sanja Fidler , University of Toronto, Canada
Raquel Urtasun , University of Toronto, Canada
pp. 2947-2955

Supervised mid-level features for word image representation (Abstract)

Albert Gordo , Computer Vision Group, Xerox Research Centre Europe, France
pp. 2956-2964

Learning lightness from human judgement on relative reflectance (Abstract)

Takuya Narihira , UC Berkeley, USA
Michael Maire , TTI Chicago, USA
Stella X. Yu , UC Berkeley, USA
pp. 2965-2973

Scene classification with semantic Fisher vectors (Abstract)

Mandar Dixit , University of California, San Diego, USA
Si Chen , University of California, San Diego, USA
Dashan Gao , Qualcomm Inc., San Diego, USA
Nikhil Rasiwasia , SnapDeal.com, India
Nuno Vasconcelos , University of California, San Diego, USA
pp. 2974-2983

Co-saliency detection via looking deep and wide (Abstract)

Dingwen Zhang , Northwestern Polytechnical University, China
Junwei Han , Microsoft Research, China
pp. 2994-3002

Adopting an unconstrained ray model in light-field cameras for 3D shape reconstruction (Abstract)

Filippo Bergamasco , Dipartimento di Scienze Ambientali, Informatica e Statistica, Università Ca' Foscari Venezia, Venice Italy
Andrea Albarelli , Dipartimento di Scienze Ambientali, Informatica e Statistica, Università Ca' Foscari Venezia, Venice Italy
Luca Cosmo , Dipartimento di Scienze Ambientali, Informatica e Statistica, Università Ca' Foscari Venezia, Venice Italy
Andrea Torsello , Dipartimento di Scienze Ambientali, Informatica e Statistica, Università Ca' Foscari Venezia, Venice Italy
Emanuele Rodola , Department of Computer Science, Technische Universität München, Garching, Germany
Daniel Cremers , Department of Computer Science, Technische Universität München, Garching, Germany
pp. 3003-3012

Towards 3D object detection with bimodal deep Boltzmann machines over RGBD imagery (Abstract)

Wei Liu , Dep. of Cognitive Science, School of Info. Science and Eng., Xiamen University, China
Rongrong Ji , Dep. of Cognitive Science, School of Info. Science and Eng., Xiamen University, China
Shaozi Li , Dep. of Cognitive Science, School of Info. Science and Eng., Xiamen University, China
pp. 3013-3021

An active search strategy for efficient object class detection (Abstract)

Abel Gonzalez-Garcia , University of Edinburgh, UK
Alexander Vezhnevets , University of Edinburgh, UK
Vittorio Ferrari , University of Edinburgh, UK
pp. 3022-3031

Geodesic exponential kernels: When curvature and linearity conflict (Abstract)

Aasa Feragen , DIKU, University of Copenhagen, Denmark
Francois Lauze , DIKU, University of Copenhagen, Denmark
Soren Hauberg , DTU Compute, Denmark
pp. 3032-3042

Transformation-Invariant Convolutional Jungles (Abstract)

Dmitry Laptev , ETH Zurich, Switzerland
Joachim M. Buhmann , ETH Zurich, Switzerland
pp. 3043-3051

Exemplar SVMs as visual feature encoders (Abstract)

Joaquin Zepeda , Technicolor, France
Patrick Perez , Technicolor, France
pp. 3052-3060

Object scene flow for autonomous vehicles (Abstract)

Moritz Menze , Leibniz Universität Hannover, Germany
Andreas Geiger , MPI Tübingen, Germany
pp. 3061-3070

Reflectance hashing for material recognition (Abstract)

Hang Zhang , Department of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ 08854, USA
Kristin Dana , Department of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ 08854, USA
Ko Nishino , Department of Computer Science, Drexel University, Philadelphia, PA 19104, USA
pp. 3071-3080

Joint photo stream and blog post summarization and exploration (Abstract)

Gunhee Kim , Seoul National University, Korea
Seungwhan Moon , Carnegie Mellon University, USA
Leonid Sigal , Disney Research Pittsburgh, USA
pp. 3081-3089

Video summarization by learning submodular mixtures of objectives (Abstract)

Michael Gygli , Computer Vision Lab, ETH Zurich, Switzerland
Helmut Grabner , Computer Vision Lab, ETH Zurich, Switzerland
Luc Van Gool , Computer Vision Lab, ETH Zurich, Switzerland
pp. 3090-3098

Building proteins in a day: Efficient 3D molecular reconstruction (Abstract)

Marcus A. Brubaker , University of Toronto, Canada
Ali Punjani , University of Toronto, Canada
David J. Fleet , University of Toronto, Canada
pp. 3099-3108

Learning descriptors for object recognition and 3D pose estimation (Abstract)

Paul Wohlhart , Institute for Computer Vision and Graphics, Graz University of Technology, Austria
Vincent Lepetit , Institute for Computer Vision and Graphics, Graz University of Technology, Austria
pp. 3109-3118

Image partitioning into convex polygons (Abstract)

Liuyun Duan , INRIA Sophia Antipolis, France
Florent Lafarge , INRIA Sophia Antipolis, France
pp. 3119-3127

Deep visual-semantic alignments for generating image descriptions (Abstract)

Andrej Karpathy , Department of Computer Science, Stanford University, USA
Li Fei-Fei , Department of Computer Science, Stanford University, USA
pp. 3128-3137

Unsupervised learning of complex articulated kinematic structures combining motion and skeleton information (Abstract)

Hyung Jin Chang , Department of Electrical and Electronic Engineering, Imperial College London, United Kingdom
Yiannis Demiris , Department of Electrical and Electronic Engineering, Imperial College London, United Kingdom
pp. 3138-3146

Elastic functional coding of human actions: From vector-fields to latent variables (Abstract)

Rushil Anirudh , School of Electrical, Computer, and Energy Engineering, Arizona State University, Tempe, USA
Pavan Turaga , School of Arts, Media and Engineering, Arizona State University, Tempe, USA
Jingyong Su , Department of Mathematics & Statistics, Texas Tech University, Lubbock, USA
Anuj Srivastava , Department of Statistics, Florida State University, Tallahassee, USA
pp. 3147-3155

Show and tell: A neural image caption generator (Abstract)

Oriol Vinyals , Google, USA
Alexander Toshev , Google, USA
Samy Bengio , Google, USA
Dumitru Erhan , Google, USA
pp. 3156-3164

Descriptor free visual indoor localization with line segments (Abstract)

Branislav Micusik , AIT Austrian Institute of Technology, Austria
Horst Wildenauer , Zeno Track GmbH, Austria
pp. 3165-3173

Fixation bank: Learning to reweight fixation candidates (Abstract)

Jiaping Zhao , University of Southern California, USA
Christian Siagian , University of Southern California, USA
Laurent Itti , University of Southern California, USA
pp. 3174-3182

Deep networks for saliency detection via local estimation and global search (Abstract)

Lijun Wang , Dalian University of Technology, China
Huchuan Lu , Dalian University of Technology, China
Xiang Ruan , OMRON Corporation, Japan
Ming-Hsuan Yang , University of California at Merced, USA
pp. 3183-3192

Reflection removal using ghosting cues (Abstract)

YiChang Shih , MIT CSAIL, USA
Dilip Krishnan , Google Research, USA
Fredo Durand , MIT CSAIL, USA
William T. Freeman , MIT CSAIL, USA
pp. 3193-3201

A dataset for Movie Description (Abstract)

Anna Rohrbach , Max Planck Institute for Informatics, Saarbrücken, Germany
Marcus Rohrbach , UC Berkeley EECS and ICSI, CA, United States
Niket Tandon , Max Planck Institute for Informatics, Saarbrücken, Germany
Bernt Schiele , Max Planck Institute for Informatics, Saarbrücken, Germany
pp. 3202-3212

Fast and robust hand tracking using detection-guided optimization (Abstract)

Srinath Sridhar , Max Planck Institute for Informatics, Germany
Franziska Mueller , Max Planck Institute for Informatics, Germany
Antti Oulasvirta , Aalto University, Finland
Christian Theobalt , Max Planck Institute for Informatics, Germany
pp. 3213-3221

Efficient SDP inference for fully-connected CRFs based on low-rank decomposition (Abstract)

Peng Wang , University of Adelaide, Australia
Chunhua Shen , University of Adelaide, Australia
Anton van den Hengel , University of Adelaide, Australia
pp. 3222-3231

Discriminative learning of iteration-wise priors for blind deconvolution (Abstract)

Wangmeng Zuo , School of Computer Science and Technology, Harbin Institute of Technology, China
Dongwei Ren , School of Computer Science and Technology, Harbin Institute of Technology, China
Shuhang Gu , Dept. of Computing, The Hong Kong Polytechnic University, China
Liang Lin , Sun Yat-Sen University, Guangzhou, China
Lei Zhang , Dept. of Computing, The Hong Kong Polytechnic University, China
pp. 3232-3240

Eye tracking assisted extraction of attentionally important objects from videos (Abstract)

S. Karthikeyan , Department of Electrical and Computer Engineering, University of California Santa Barbara, USA
Thuyen Ngo , Department of Electrical and Computer Engineering, University of California Santa Barbara, USA
Miguel Eckstein , Department of Psychological and Brain Sciences, University of California Santa Barbara, USA
B.S. Manjunath , Department of Electrical and Computer Engineering, University of California Santa Barbara, USA
pp. 3241-3250

Multi-view feature engineering and learning (Abstract)

Jingming Dong , UCLA Vision Lab, University of California, Los Angeles, 90095, USA
Nikolaos Karianakis , UCLA Vision Lab, University of California, Los Angeles, 90095, USA
Damek Davis , UCLA Vision Lab, University of California, Los Angeles, 90095, USA
Joshua Hernandez , UCLA Vision Lab, University of California, Los Angeles, 90095, USA
Jonathan Balzer , UCLA Vision Lab, University of California, Los Angeles, 90095, USA
Stefano Soatto , UCLA Vision Lab, University of California, Los Angeles, 90095, USA
pp. 3251-3260

Self Scaled Regularized Robust Regression (Abstract)

Yin Wang , Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
Caglayan Dicle , Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
Mario Sznaier , Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
Octavia Camps , Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
pp. 3261-3269

Simultaneous feature learning and hash coding with deep neural networks (Abstract)

Hanjiang Lai , Department of Electronic and Computer Engineering, National University of Singapore, Singapore
Yan Pan , School of Software, Sun Yan-Sen University, China
Ye Liu , School of Information Science and Technology, Sun Yan-Sen University, China
Shuicheng Yan , Department of Electronic and Computer Engineering, National University of Singapore, Singapore
pp. 3270-3278

MatchNet: Unifying feature and metric learning for patch-based matching (Abstract)

Xufeng Han , University of North Carolina at Chapel Hill, USA
Thomas Leung , Google Research, USA
Yangqing Jia , Google Research, USA
Rahul Sukthankar , Google Research, USA
Alexander C. Berg , University of North Carolina at Chapel Hill, USA
pp. 3279-3286

Reconstructing the world* in six days (Abstract)

Jared Heinly , Department of Computer Science, The University of North Carolina at Chapel Hill, USA
Johannes L. Schonberger , Department of Computer Science, The University of North Carolina at Chapel Hill, USA
Enrique Dunn , Department of Computer Science, The University of North Carolina at Chapel Hill, USA
Jan-Michael Frahm , Department of Computer Science, The University of North Carolina at Chapel Hill, USA
pp. 3287-3295

Exact bias correction and covariance estimation for stereo vision (Abstract)

Charles Freundlich , Duke University, USA
Michael Zavlanos , Duke University, USA
Philippos Mordohai , Stevens Institute of Technology, USA
pp. 3296-3304

Computing similarity transformations from only image correspondences (Abstract)

Chris Sweeney , University of California Santa Barbara, USA
Laurent Kneip , Research School of Engineering, Australian National University, Australia
Tobias Hollerer , University of California Santa Barbara, USA
Matthew Turk , University of California Santa Barbara, USA
pp. 3305-3313

Image segmentation in Twenty Questions (Abstract)

Christian Rupprecht , Technische Universität München, Munich, Germany
Loic Peter , Technische Universität München, Munich, Germany
Nassir Navab , Technische Universität München, Munich, Germany
pp. 3314-3322

Interaction part mining: A mid-level approach for fine-grained action recognition (Abstract)

Yang Zhou , University of Texas at San Antonio, US
Bingbing Ni , Advanced Digital Sciences Center, Singapore
Richang Hong , HeFei University of Technology, China
Meng Wang , HeFei University of Technology, China
Qi Tian , University of Texas at San Antonio, US
pp. 3323-3331

Sparse projections for high-dimensional binary codes (Abstract)

Yan Xia , University of Science and Technology of China, China
Kaiming He , Microsoft Research, USA
Pushmeet Kohli , Microsoft Research, USA
Jian Sun , Microsoft Research, USA
pp. 3332-3339

Hierarchically-constrained optical flow (Abstract)

Ryan Kennedy , Department of Computer and Information Science, University of Pennsylvania, USA
Camillo J. Taylor , Department of Computer and Information Science, University of Pennsylvania, USA
pp. 3340-3348

The k-support norm and convex envelopes of cardinality and rank (Abstract)

Anders Eriksson , School of Electrical Engineering and Computer Science, Queensland University of Technology, Australia
Trung Thanh Pham , School of Computer Science, The University of Adelaide, Australia
Tat-Jun Chin , School of Computer Science, The University of Adelaide, Australia
Ian Reid , School of Computer Science, The University of Adelaide, Australia
pp. 3349-3357

Matching bags of regions in RGBD images (Abstract)

Hao Jiang , Boston College, USA
pp. 3358-3366

Recurrent convolutional neural network for object recognition (Abstract)

Ming Liang , State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology (TNList), Tsinghua University, Beijing 100084, China
Xiaolin Hu , State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology (TNList), Tsinghua University, Beijing 100084, China
pp. 3367-3375

Feedforward semantic segmentation with zoom-out features (Abstract)

Mohammadreza Mostajabi , Toyota Technological Institute at Chicago, USA
Payman Yadollahpour , Toyota Technological Institute at Chicago, USA
Gregory Shakhnarovich , Toyota Technological Institute at Chicago, USA
pp. 3376-3385

The aperture problem for refractive motion (Abstract)

Tianfan Xue , MIT Computer Science and Artificial Intelligence Laboratory, USA
Hossein Mobahi , MIT Computer Science and Artificial Intelligence Laboratory, USA
Fredo Durand , MIT Computer Science and Artificial Intelligence Laboratory, USA
William T. Freeman , MIT Computer Science and Artificial Intelligence Laboratory, USA
pp. 3386-3394

Saliency-aware geodesic video object segmentation (Abstract)

Wenguan Wang , Beijing Lab of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, China
Jianbing Shen , Beijing Lab of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, China
Fatih Porikli , Research School of Engineering, Australian National University, Australia
pp. 3395-3402

DEEP-CARVING: Discovering visual attributes by carving deep neural nets (Abstract)

Sukrit Shankar , Machine Intelligence Lab (MIL), Cambridge University, USA
Vikas K. Garg , Computer Science & Artificial Intelligence Lab (CSAIL), MIT, USA
Roberto Cipolla , Machine Intelligence Lab (MIL), Cambridge University, USA
pp. 3403-3412

Rent3D: Floor-plan priors for monocular layout estimation (Abstract)

Chenxi Liu , State Key Lab. on Intelligent Technology and Systems, Tsinghua Nat. Lab. for Inf. Science and Tech. (TNList), Department of Automation, Tsinghua University, China
Alexander G. Schwing , Department of Computer Science, University of Toronto, Canada
Kaustav Kundu , Department of Computer Science, University of Toronto, Canada
Raquel Urtasun , Department of Computer Science, University of Toronto, Canada
Sanja Fidler , Department of Computer Science, University of Toronto, Canada
pp. 3413-3421

Learning a sequential search for landmarks (Abstract)

Saurabh Singh , University of Illinois, Urbana-Champaign, USA
Derek Hoiem , University of Illinois, Urbana-Champaign, USA
David Forsyth , University of Illinois, Urbana-Champaign, USA
pp. 3422-3430

Fully convolutional networks for semantic segmentation (Abstract)

Jonathan Long , UC Berkeley, USA
Evan Shelhamer , UC Berkeley, USA
Trevor Darrell , UC Berkeley, USA
pp. 3431-3440

Deep correlation for matching images and text (Abstract)

Fei Yan , Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, United Kingdom, GU2 7XH
Krystian Mikolajczyk , Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, United Kingdom, GU2 7XH
pp. 3441-3450

Multi-objective convolutional learning for face labeling (Abstract)

Sifei Liu , UC Merced, USA
Jimei Yang , UC Merced, USA
Chang Huang , Baidu Research, USA
Ming-Hsuan Yang , UC Merced, USA
pp. 3451-3459

Deep multiple instance learning for image classification and auto-annotation (Abstract)

Jiajun Wu , Massachusetts Institute of Technology, USA
Yinan Yu , Institute of Deep Learning, Baidu, USA
Chang Huang , Institute of Deep Learning, Baidu, USA
Kai Yu , Institute of Deep Learning, Baidu, USA
pp. 3460-3469

Multi-instance object segmentation with occlusion handling (Abstract)

Yi-Ting Chen , University of California at Merced, USA
Xiaokai Liu , University of California at Merced, USA
Ming-Hsuan Yang , University of California at Merced, USA
pp. 3470-3478

Material recognition in the wild with the Materials in Context Database (Abstract)

Sean Bell , Department of Computer Science, Cornell University, USA
Paul Upchurch , Department of Computer Science, Cornell University, USA
Noah Snavely , Department of Computer Science, Cornell University, USA
Kavita Bala , Department of Computer Science, Cornell University, USA
pp. 3479-3487

Understanding pedestrian behaviors from stationary crowd groups (Abstract)

Shuai Yi , Department of Electronic Engineering, The Chinese University of Hong Kong, China
Hongsheng Li , Department of Electronic Engineering, The Chinese University of Hong Kong, China
Xiaogang Wang , Department of Electronic Engineering, The Chinese University of Hong Kong, China
pp. 3488-3496

Depth from focus with your mobile phone (Abstract)

Supasorn Suwajanakorn , University of Washington, USA
Carlos Hernandez , Google Inc., USA
Steven M. Seitz , University of Washington, USA
pp. 3497-3506

Metric imitation by manifold transfer for efficient vision applications (Abstract)

Dengxin Dai , Computer Vision Lab, ETH Zurich, Switzerland
Till Kroeger , Computer Vision Lab, ETH Zurich, Switzerland
Radu Timofte , Computer Vision Lab, ETH Zurich, Switzerland
Luc Van Gool , Computer Vision Lab, ETH Zurich, Switzerland
pp. 3527-3536

The stitched puppet: A graphical model of 3D human shape and pose (Abstract)

Silvia Zuffi , Max Planck Institute for Intelligent Systems, Tübingen, Germany
Michael J. Black , Max Planck Institute for Intelligent Systems, Tübingen, Germany
pp. 3537-3546

Scene labeling with LSTM recurrent neural networks (Abstract)

Wonmin Byeon , University of Kaiserslautern, Germany
Thomas M. Breuel , University of Kaiserslautern, Germany
Federico Raue , University of Kaiserslautern, Germany
Marcus Liwicki , University of Kaiserslautern, Germany
pp. 3547-3555

FAemb: A function approximation-based embedding method for image retrieval (Abstract)

Thanh-Toan Do , Singapore University of Technology and Design, Singapore
Quang D. Tran , Singapore University of Technology and Design, Singapore
Ngai-Man Cheung , Singapore University of Technology and Design, Singapore
pp. 3556-3564

Automatically discovering local visual material attributes (Abstract)

Gabriel Schwartz , Department of Computer Science, Drexel University, USA
Ko Nishino , Department of Computer Science, Drexel University, USA
pp. 3565-3573

Depth image enhancement using local tangent plane approximations (Abstract)

Kiyoshi Matsuo , Hokuyo Automatic Co., LTD., Korea
Yoshimitsu Aoki , Keio University, Korea
pp. 3574-3583

Video co-summarization: Video summarization by visual co-occurrence (Abstract)

Wen-Sheng Chu , Robotics Institute, Carnegie Mellon University, USA
Yale Song , Yahoo Labs, New York, USA
Alejandro Jaimes , Yahoo Labs, New York, USA
pp. 3584-3592

Watch and learn: Semi-supervised learning of object detectors from videos (Abstract)

Ishan Misra , Robotics Institute, Carnegie Mellon University, USA
Abhinav Shrivastava , Robotics Institute, Carnegie Mellon University, USA
Martial Hebert , Robotics Institute, Carnegie Mellon University, USA
pp. 3593-3602

Generalized Tensor Total Variation minimization for visual data recovery? (Abstract)

Xiaojie Guo , State Key Laboratory of Information Security, IIE, CAS, Beijing, 100093, China
Yi Ma , School of Information Science and Technology, Shanghai Tech University, 200031, China
pp. 3603-3611

Active learning for structured probabilistic models with histogram approximation (Abstract)

Qing Sun , Virginia Tech, USA
Ankit Laddha , CMU, USA
Dhruv Batra , Virginia Tech, USA
pp. 3612-3621

Image parsing with a wide range of classes and scene-level context (Abstract)

Marian George , Department of Computer Science, ETH Zurich, Switzerland
pp. 3622-3630

Bayesian sparse representation for hyperspectral image super resolution (Abstract)

Naveed Akhtar , The University of Western Australia, 35 Stirling Highway, Crawley, 6009, Australia
Faisal Shafait , The University of Western Australia, 35 Stirling Highway, Crawley, 6009, Australia
Ajmal Mian , The University of Western Australia, 35 Stirling Highway, Crawley, 6009, Australia
pp. 3631-3640

Semantic object segmentation via detection in weakly labeled video (Abstract)

Yu Zhang , State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, China
Xiaowu Chen , State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, China
Jia Li , State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, China
Chen Wang , State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, China
Changqun Xia , State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, China
pp. 3641-3649

Learning with dataset bias in latent subcategory models (Abstract)

Dimitris Stamos , Department of Computer Science, University College London, UK
Samuele Martelli , Pattern Analysis & Computer Vision, Istituto Italiano di Tecnologia, Italy
Moin Nabi , Pattern Analysis & Computer Vision, Istituto Italiano di Tecnologia, Italy
Andrew McDonald , Department of Computer Science, University College London, UK
Vittorio Murino , Pattern Analysis & Computer Vision, Istituto Italiano di Tecnologia, Italy
Massimiliano Pontil , Department of Computer Science, University College London, UK
pp. 3650-3658

Project-Out Cascaded Regression with an application to face alignment (Abstract)

Georgios Tzimiropoulos , School of Computer Science, University of Nottingham, U.K.
pp. 3659-3667

Image retrieval using scene graphs (Abstract)

Justin Johnson , Stanford University, USA
Ranjay Krishna , Stanford University, USA
Michael Stark , Max Planck Institute for Informatics, USA
Li-Jia Li , Yahoo Labs, USA
David A. Shamma , Yahoo Labs, USA
Michael S. Bernstein , Stanford University, USA
Li Fei-Fei , Stanford University, USA
pp. 3668-3678

Unifying holistic and Parts-Based Deformable Model fitting (Abstract)

Joan Alabort-i-Medina , Department of Computing, Imperial College London, United Kingdom
Stefanos Zafeiriou , Department of Computing, Imperial College London, United Kingdom
pp. 3679-3688

Small instance detection by integer programming on object density maps (Abstract)

Zheng Ma , Department of Computer Science, City University of Hong Kong, China
Lei Yu , Department of Computer Science, City University of Hong Kong, China
Antoni B. Chan , Department of Computer Science, City University of Hong Kong, China
pp. 3689-3697

Multi-task deep visual-semantic embedding for video thumbnail selection (Abstract)

Wu Liu , Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
Tao Mei , Microsoft Research, Beijing 100080, China
Yongdong Zhang , Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
Cherry Che , Microsoft Research, Beijing 100080, China
Jiebo Luo , University of Rochester, NY 14627, USA
pp. 3707-3715

Fine-grained visual categorization via multi-stage metric learning (Abstract)

Qi Qian , Department of Computer Science and Engineering, Michigan State University, East Lansing, 48824, USA
Rong Jin , Department of Computer Science and Engineering, Michigan State University, East Lansing, 48824, USA
Shenghuo Zhu , Alibaba Group, Seattle, WA, 98101, USA
Yuanqing Lin , NEC Laboratories America, Cupertino, CA, 95014, USA
pp. 3716-3724

Saturation-preserving specular reflection separation (Abstract)

Yuanliu Liu , Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, China
Zejian Yuan , Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, China
Nanning Zheng , Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, China
Yang Wu , Center for Frontier Science and Technology, Nara Institute of Science and Technology, Japan
pp. 3725-3733

Joint SFM and detection cues for monocular 3D localization in road scenes (Abstract)

Shiyu Song , NEC Labs America, Cupertino, CA, United States
Manmohan Chandraker , NEC Labs America, Cupertino, CA, United States
pp. 3734-3742

Fisher vectors meet Neural Networks: A hybrid classification architecture (Abstract)

Florent Perronnin , Computer Vision Group, Xerox Research Centre Europe, France
Diane Larlus , Computer Vision Group, Xerox Research Centre Europe, France
pp. 3743-3752

UniHIST: A unified framework for image restoration with marginal histogram constraints (Abstract)

Xing Mei , Computer Science Department, University at Albany, SUNY, 12222, United States
Weiming Dong , NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China
Bao-Gang Hu , NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China
Siwei Lyu , Computer Science Department, University at Albany, SUNY, 12222, United States
pp. 3753-3761

Human action segmentation with hierarchical supervoxel consistency (Abstract)

Jiasen Lu , Computer Science and Engineering, SUNY at Buffalo, United States
Ran Xu , Computer Science and Engineering, SUNY at Buffalo, United States
Jason J. Corso , Electrical Engineering and Computer Science, University of Michigan, United States
pp. 3762-3771

Robust Manhattan Frame estimation from a single RGB-D image (Abstract)

Bernard Ghanem , King Abdullah University of Science and Technology (KAUST), Saudi Arabia
Ali Thabet , King Abdullah University of Science and Technology (KAUST), Saudi Arabia
Juan Carlos Niebles , Universidad del Norte, Colombia
Fabian Caba Heilbron , King Abdullah University of Science and Technology (KAUST), Saudi Arabia
pp. 3772-3780

Learning to segment under various forms of weak supervision (Abstract)

Jia Xu , University of Wisconsin-Madison, United States
Alexander G. Schwing , University of Toronto, Canada
Raquel Urtasun , University of Toronto, Canada
pp. 3781-3790

Fast and accurate image upscaling with super-resolution forests (Abstract)

Samuel Schulter , Graz University of Technology, Institute for Computer Graphics and Vision, Austria
Christian Leistner , Microsoft Photogrammetry, Austria
Horst Bischof , Graz University of Technology, Institute for Computer Graphics and Vision, Austria
pp. 3791-3799

Light field from micro-baseline image pair (Abstract)

Zhoutong Zhang , Beijing Key Laboratory of Multi-dimension & Multi-scale Computational Photography (MMCP), Tsinghua University, 100084 China
Yebin Liu , Beijing Key Laboratory of Multi-dimension & Multi-scale Computational Photography (MMCP), Tsinghua University, 100084 China
Qionghai Dai , Beijing Key Laboratory of Multi-dimension & Multi-scale Computational Photography (MMCP), Tsinghua University, 100084 China
pp. 3800-3809

Efficient ConvNet-based marker-less motion capture in general scenes with a low number of cameras (Abstract)

A. Elhayek , MPI Informatics, 66123 Saarbrücken, Germany
E. de Aguiar , MPI Informatics, 66123 Saarbrücken, Germany
A. Jain , New York University, United States
J. Tompson , New York University, United States
L. Pishchulin , MPI Informatics, 66123 Saarbrücken, Germany
M. Andriluka , Stanford University, California 94305, United States
C. Bregler , New York University, United States
B. Schiele , MPI Informatics, 66123 Saarbrücken, Germany
C. Theobalt , MPI Informatics, 66123 Saarbrücken, Germany
pp. 3810-3818

Learning scene-specific pedestrian detectors without real data (Abstract)

Hironori Hattori , Sony Corporation, Tokyo, Japan
Vishnu Naresh Boddeti , The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, United States
Kris Kitani , The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, United States
Takeo Kanade , The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, United States
pp. 3819-3827

Deep filter banks for texture recognition and segmentation (Abstract)

Mircea Cimpoi , University of Oxford, United Kingdom
Subhransu Maji , University of Massachusetts, Amherst, United States
Andrea Vedaldi , University of Oxford, United Kingdom
pp. 3828-3836

Multiple random walkers and their application to image cosegmentation (Abstract)

Chulwoo Lee , School of Electrical Engineering, Korea University, South Korea
Won-Dong Jang , School of Electrical Engineering, Korea University, South Korea
Jae-Young Sim , School of ECE, UNIST, South Korea
Chang-Su Kim , School of Electrical Engineering, Korea University, South Korea
pp. 3837-3845

Beyond the shortest path: Unsupervised domain adaptation by Sampling Subspaces along the Spline Flow (Abstract)

Rui Caseiro , Institute of Systems and Robotics - University of Coimbra, Portugal
Joao F. Henriques , Institute of Systems and Robotics - University of Coimbra, Portugal
Pedro Martins , Institute of Systems and Robotics - University of Coimbra, Portugal
Jorge Batista , Institute of Systems and Robotics - University of Coimbra, Portugal
pp. 3846-3854

Spherical embedding of inlier silhouette dissimilarities (Abstract)

Etai Littwin , Tel-Aviv University, Israel
Hadar Averbuch-Elor , Tel-Aviv University, Israel
Daniel Cohen-Or , Tel-Aviv University, Israel
pp. 3855-3863

Semantics-preserving hashing for cross-view retrieval (Abstract)

Zijia Lin , Department of Computer Science and Technology, Tsinghua University, Beijing, China
Guiguang Ding , School of Software, Tsinghua University, Beijing, China
Mingqing Hu , Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
Jianmin Wang , School of Software, Tsinghua University, Beijing, China
pp. 3864-3872

Object proposal by multi-branch hierarchical segmentation (Abstract)

Chaoyang Wang , Shanghai Jiao Tong University, China
Long Zhao , Tongji University, China
Shuang Liang , Tongji University, China
Liqing Zhang , Shanghai Jiao Tong University, China
Jinyuan Jia , Tongji University, China
Yichen Wei , Microsoft Research, Beijing 100080, China
pp. 3873-3881

Ambient occlusion via compressive visibility estimation (Abstract)

Wei Yang , University of Delaware, Newark, 19716, United States
Yu Ji , University of Delaware, Newark, 19716, United States
Haiting Lin , University of Delaware, Newark, 19716, United States
Yang Yang , University of Delaware, Newark, 19716, United States
Sing Bing Kang , Microsoft Research, Beijing 100080, China
Jingyi Yu , University of Delaware, Newark, 19716, United States
pp. 3882-3889

Shape-tailored local descriptors and their application to segmentation and tracking (Abstract)

Naeemullah Khan , King Abdullah University of Science & Technology (KAUST), Saudi Arabia
Marei Algarni , King Abdullah University of Science & Technology (KAUST), Saudi Arabia
Anthony Yezzi , School of Electrical & Computer Engineering, Georgia Institute of Technology, USA
Ganesh Sundaramoorthi , King Abdullah University of Science & Technology (KAUST), Saudi Arabia
pp. 3890-3899

Scalable object detection by filter compression with regularized sparse coding (Abstract)

Ting-Hsuan Chao , National Taiwan University, Taipei, Taiwan
Yen-Liang Lin , National Taiwan University, Taipei, Taiwan
Yin-Hsi Kuo , National Taiwan University, Taipei, Taiwan
Winston H. Hsu , National Taiwan University, Taipei, Taiwan
pp. 3900-3907

An improved deep learning architecture for person re-identification (Abstract)

Ejaz Ahmed , University of Maryland, 3364 A.V. Williams, College Park, 20740, United States
Michael Jones , Mitsubishi Electric Research Labs, 201 Broadway, Cambridge, MA 02139, United States
Tim K. Marks , Mitsubishi Electric Research Labs, 201 Broadway, Cambridge, MA 02139, United States
pp. 3908-3916

Understanding classifier errors by examining influential neighbors (Abstract)

Mayank Kabra , Janelia Research Campus of the Howard Hughes Medical Institute, Ashburn, VA, 20147, USA
Alice Robie , Janelia Research Campus of the Howard Hughes Medical Institute, Ashburn, VA, 20147, USA
Kristin Branson , Janelia Research Campus of the Howard Hughes Medical Institute, Ashburn, VA, 20147, USA
pp. 3917-3925

Riemannian coding and dictionary learning: Kernels to the rescue (Abstract)

Mehrtash Harandi , Australian National University & NICTA*, Canberra, Australia
Mathieu Salzmann , Australian National University & NICTA*, Canberra, Australia
pp. 3926-3935

Scalable structure from motion for densely sampled videos (Abstract)

B. Resch , Disney Research Zurich, 48 8006, Switzerland
H. P. A. Lensch , Tübingen University, 72074, Germany
O. Wang , Disney Research Zurich, 48 8006, Switzerland
M. Pollefeys , ETH Zurich, 8092, Switzerland
A. Sorkine-Hornung , Disney Research Zurich, 48 8006, Switzerland
pp. 3936-3944

Parsing occluded people by flexible compositions (Abstract)

Xianjie Chen , University of California, Los Angeles, 90095, United States
Alan Yuille , University of California, Los Angeles, 90095, United States
pp. 3945-3954

Joint calibration of Ensemble of Exemplar SVMs (Abstract)

Davide Modolo , University of Edinburgh, EH8 9YL, United Kingdom
Alexander Vezhnevets , University of Edinburgh, EH8 9YL, United Kingdom
Olga Russakovsky , Stanford University, California 94305, United States
Vittorio Ferrari , University of Edinburgh, EH8 9YL, United Kingdom
pp. 3955-3963

Holistic 3D scene understanding from a single geo-tagged image (Abstract)

Shenlong Wang , Department of Computer Science, University of Toronto, ON M5S, Canada
Sanja Fidler , Department of Computer Science, University of Toronto, ON M5S, Canada
Raquel Urtasun , Department of Computer Science, University of Toronto, ON M5S, Canada
pp. 3964-3972

A large-scale car dataset for fine-grained categorization and verification (Abstract)

Linjie Yang , Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong
Ping Luo , Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong
Chen Change Loy , Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong
Xiaoou Tang , Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong
pp. 3973-3981

DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection (Abstract)

Wei Shen , Key Lab of Specialty Fiber Optics and Optical Access Networks, Shanghai University, China
Xinggang Wang , School of Electronic Information and Communications, Huazhong University of Science and Technology, Hongshan, Wuhan, Hubei, China
Yan Wang , Rapid-Rich Object Search Lab, Nanyang Technological University, Singapore 639798
Xiang Bai , School of Electronic Information and Communications, Huazhong University of Science and Technology, Hongshan, Wuhan, Hubei, China
Zhijiang Zhang , Key Lab of Specialty Fiber Optics and Optical Access Networks, Shanghai University, China
pp. 3982-3991

Convolutional feature masking for joint object and stuff segmentation (Abstract)

Jifeng Dai , Microsoft Research, Beijing 100080, China
Kaiming He , Microsoft Research, Beijing 100080, China
Jian Sun , Microsoft Research, Beijing 100080, China
pp. 3992-4000

A fixed viewpoint approach for dense reconstruction of transparent objects (Abstract)

Kai Han , The University of Hong Kong, Hong Kong
Kwan-Yee K. Wong , The University of Hong Kong, Hong Kong
Miaomiao Liu , NICTA, Canberra ACT 0200, Australia
pp. 4001-4008

Low-level vision by consensus in a spatial hierarchy of regions (Abstract)

Ayan Chakrabarti , TTI-Chicago, IL 60637, United States
Ying Xiong , Harvard University, Cambridge, MA 02138, United States
Steven J. Gortler , Harvard University, Cambridge, MA 02138, United States
Todd Zickler , Harvard University, Cambridge, MA 02138, United States
pp. 4009-4017