The Community for Technology Leaders
2016 IEEE Winter Conference on Applications of Computer Vision (WACV) (2016)
Lake Placid, NY, USA
March 7, 2016 to March 10, 2016
ISBN: 978-1-5090-0640-3
TABLE OF CONTENTS

Optimal feature learning and discriminative framework for polarimetric thermal to visible face recognition (Abstract)

Benjamin S. Riggan , U.S. Army Research Laboratory, 2800 Powder Mill Rd., Adelphi, MD 20783
Nathaniel J. Short , U.S. Army Research Laboratory, 2800 Powder Mill Rd., Adelphi, MD 20783
Shuowen Hu , U.S. Army Research Laboratory, 2800 Powder Mill Rd., Adelphi, MD 20783
pp. 1-7

Discovery of facial motions using deep machine perception (Abstract)

Afsaneh Ghasemi , Speech, Audio, Image and Video Technology (SAIVT) Laboratory, Queensland University of Technology, Australia
Simon Denman , Speech, Audio, Image and Video Technology (SAIVT) Laboratory, Queensland University of Technology, Australia
Sridha Sridharan , Speech, Audio, Image and Video Technology (SAIVT) Laboratory, Queensland University of Technology, Australia
Clinton Fookes , Speech, Audio, Image and Video Technology (SAIVT) Laboratory, Queensland University of Technology, Australia
pp. 1-7

Customized expression recognition for performance-driven cutout character animation (Abstract)

Xiang Yu , NEC Laboratories America
Jianchao Yang , Snapchat
Linjie Luo , Snapchat
Wilmot Li , Adobe
Dimitris Metaxas , Rutgers University
pp. 1-9

Going deeper in facial expression recognition using deep neural networks (Abstract)

Ali Mollahosseini , Department of Electrical and Computer Engineering
David Chan , Department of Computer Science University of Denver, Denver, CO
Mohammad H. Mahoor , Department of Electrical and Computer Engineering
pp. 1-10

Discriminative FaceTopics for face recognition via latent Dirichlet allocation (Abstract)

Tejas Indulal Dhamecha , IIIT Delhi, India
Praneet Sharma , IIIT Delhi, India
Richa Singh , IIIT Delhi, India
Mayank Vatsa , IIIT Delhi, India
pp. 1-8

Can we still avoid automatic face detection? (Abstract)

Michael J. Wilber , Department of Computer Science, Cornell University
Vitaly Shmatikov , Department of Computer Science, Cornell University
Serge Belongie , Department of Computer Science, Cornell University
pp. 1-9

Correlation filter cascade for facial landmark localization (Abstract)

Hamed Kiani Galoogahi , Pattern Analysis and Computer Vision Department, Istituto Italiano di Tecnologia, Genova, Italy
Terence Sim , School of Computing, National University of Singapore, Singapore
pp. 1-8

Face recognition using deep multi-pose representations (Abstract)

Wael AbdAlmageed , Information Sciences Institute, University of Southern California, Marina Del Rey, CA
Yue Wu , Information Sciences Institute, University of Southern California, Marina Del Rey, CA
Stephen Rawls , Information Sciences Institute, University of Southern California, Marina Del Rey, CA
Shai Harel , The Open University, Raanana, Israel
Tal Hassner , Information Sciences Institute, University of Southern California, Marina Del Rey, CA
Iacopo Masi , Institute for Robotics and Intelligent Systems, University of Southern California, Los Angeles, California
Jongmoo Choi , Institute for Robotics and Intelligent Systems, University of Southern California, Los Angeles, California
Jatuporn Lekust , Institute for Robotics and Intelligent Systems, University of Southern California, Los Angeles, California
Jungyeon Kim , Institute for Robotics and Intelligent Systems, University of Southern California, Los Angeles, California
Prem Natarajan , Information Sciences Institute, University of Southern California, Marina Del Rey, CA
Ram Nevatia , Institute for Robotics and Intelligent Systems, University of Southern California, Los Angeles, California
Gerard Medioni , Institute for Robotics and Intelligent Systems, University of Southern California, Los Angeles, California
pp. 1-9

Effect of illicit drug abuse on face recognition (Abstract)

Daksha Yadav , West Virginia University
Naman Kohli , West Virginia University
Prateekshit Pandey , IIIT-Delhi
Richa Singh , IIIT-Delhi
Mayank Vatsa , IIIT-Delhi
Afzel Noore , West Virginia University
pp. 1-7

Unconstrained face verification using deep CNN features (Abstract)

Jun-Cheng Chen , University of Maryland, College Park, 2. Rutgers, The State University of New Jersey
Vishal M. Patel , University of Maryland, College Park, 2. Rutgers, The State University of New Jersey
Rama Chellappa , University of Maryland, College Park, 2. Rutgers, The State University of New Jersey
pp. 1-9

Frontal to profile face verification in the wild (Abstract)

Soumyadip Sengupta , Center for Automation Research, University of Maryland, College Park, MD 20740, USA
Jun-Cheng Chen , Center for Automation Research, University of Maryland, College Park, MD 20740, USA
Carlos Castillo , Center for Automation Research, University of Maryland, College Park, MD 20740, USA
Vishal M. Patel , Department of Electrical and Computer Engineering Rutgers, The State University of New Jersey, Piscataway, NJ 08854, USA
Rama Chellappa , Center for Automation Research, University of Maryland, College Park, MD 20740, USA
David W. Jacobs , Center for Automation Research, University of Maryland, College Park, MD 20740, USA
pp. 1-9

Capturing facial videos with Kinect 2.0: A multithreaded open source tool and database (Abstract)

Daniel Merget , Institute for Human-Machine Communication, TUM, Germany
Tobias Eckl , Institute for Human-Machine Communication, TUM, Germany
Martin Schwoerer , Institute for Human-Machine Communication, TUM, Germany
Philipp Tiefenbacher , Institute for Human-Machine Communication, TUM, Germany
Gerhard Rigoll , Institute for Human-Machine Communication, TUM, Germany
pp. 1-5

Naming TV characters by watching and analyzing dialogs (Abstract)

Monica-Laura Haurilet , Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany
Makarand Tapaswi , Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany
Ziad Al-Halah , Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany
Rainer Stiefelhagen , Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany
pp. 1-9

Object detection in 20 questions (Abstract)

Xi Stephen Chen , Department of Computer Science, University of Maryland, College Park, MD 20742
He He , Department of Computer Science, University of Maryland, College Park, MD 20742
Larry S. Davis , Department of Computer Science, University of Maryland, College Park, MD 20742
pp. 1-9

Pose tracking by efficiently exploiting global features (Abstract)

Ratnesh Kumar , Placemeter, NY
Dhruv Batra , Virginia Tech, VA
pp. 1-9

Exploring bounding box context for multi-object tracker fusion (Abstract)

Stefan Breuers , Visual Computing Institute, RWTH Aachen University
Shishan Yang , Data Fusion Group, Georg-August-Universität Göttingen
Markus Mathias , Visual Computing Institute, RWTH Aachen University
Bastian Leibe , Visual Computing Institute, RWTH Aachen University
pp. 1-8

OCPAD — Occluded checkerboard pattern detector (Abstract)

Peter Fuersattel , Friedrich-Alexander University of Erlangen-Nuremberg
Sergiu Dotenco , Friedrich-Alexander University of Erlangen-Nuremberg
Simon Placht , Metrilus GmbH
Michael Balda , Metrilus GmbH
Andreas Maier , Friedrich-Alexander University of Erlangen-Nuremberg
Christian Riess , Friedrich-Alexander University of Erlangen-Nuremberg
pp. 1-9

Leveraging single for multi-target tracking using a novel trajectory overlap affinity measure (Abstract)

Santiago Manen , Computer Vision Laboratory, ETH Zurich
Radu Timofte , Computer Vision Laboratory, ETH Zurich
Dengxin Dai , Computer Vision Laboratory, ETH Zurich
Luc Van Gool , Computer Vision Laboratory, ETH Zurich
pp. 1-9

Procrustean decomposition for orthogonal cascade detection (Abstract)

Kun Duan , GE Global Research
Wei Wang , GE Global Research
Ting Yu , Nest Labs, Alphabet Inc.
pp. 1-9

Online tracking using saliency (Abstract)

Mohammed A. Yousefhussien , Rochester Institute of Technology
N. Andrew Browning , Scientific Systems Company, Inc.
Christopher Kanan , Rochester Institute of Technology
pp. 1-10

Robust visual tracking using template anchors (Abstract)

Luka Cehovin , Faculty of Computer and Information Science, University of Ljubljana, Slovenia, Večna pot 113, Ljubljana, Slovenia
Ales Leonardis , Faculty of Computer and Information Science, University of Ljubljana, Slovenia, Večna pot 113, Ljubljana, Slovenia
Matej Kristan , Faculty of Computer and Information Science, University of Ljubljana, Slovenia, Večna pot 113, Ljubljana, Slovenia
pp. 1-8

A structured approach to predicting image enhancement parameters (Abstract)

Parag Shridhar Chandakkar , School of Computing, Informatics and Decision Systems Engineering, Arizona State University
Baoxin Li , School of Computing, Informatics and Decision Systems Engineering, Arizona State University
pp. 1-9

Active contours for selective object segmentation (Abstract)

Jozsef Moinar , Synthetic and Systems Biology Unit, Hungarian Academy of Sciences, BRC, Szeged, Hungary
Adam Istvan Szucs , Synthetic and Systems Biology Unit, Hungarian Academy of Sciences, BRC, Szeged, Hungary
Csaba Molnar , Synthetic and Systems Biology Unit, Hungarian Academy of Sciences, BRC, Szeged, Hungary
Peter Horvath , Synthetic and Systems Biology Unit, Hungarian Academy of Sciences, BRC, Szeged, Hungary, Institute for Molecular Medicine Finland (FIMM) University of Helsinki, Helsinki, Finland
pp. 1-9

A survey on moving object detection for wide area motion imagery (Abstract)

Lars Wilko Sommer , Vision and Fusion Lab, Karlsruhe Institute of Technology KIT, Adenauerring 4, 76131 Karlsruhe, Germany
Michael Teutsch , Fraunhofer IOSB, Fraunhoferstrasse 1, 76131 Karlsruhe, Germany
Tobias Schuchert , Fraunhofer IOSB, Fraunhoferstrasse 1, 76131 Karlsruhe, Germany
Jurgen Beyerer , Fraunhofer IOSB, Fraunhoferstrasse 1, 76131 Karlsruhe, Germany
pp. 1-9

Dynamic belief fusion for object detection (Abstract)

Hyungtae Lee , SEDD, U.S. Army Research Laboratory, Adelphi, MD, USA
Heesung Kwon , SEDD, U.S. Army Research Laboratory, Adelphi, MD, USA
Ryan M. Robinson , SEDD, U.S. Army Research Laboratory, Adelphi, MD, USA
William D. Nothwang , SEDD, U.S. Army Research Laboratory, Adelphi, MD, USA
Amar M. Marathe , HRED, U.S. Army Research Laboratory, Aberdeen, MD, USA
pp. 1-9

Text detection in stores using a repetition prior (Abstract)

Bo Xiong , University of Texas at Austin
Kristen Grauman , University of Texas at Austin
pp. 1-9

Cutting through the clutter: Task-relevant features for image matching (Abstract)

Rohit Girdhar , Robotics Institute, Carnegie Mellon University
David F. Fouhey , Robotics Institute, Carnegie Mellon University
Kris M. Kitani , Robotics Institute, Carnegie Mellon University
Abhinav Gupta , Robotics Institute, Carnegie Mellon University
Martial Hebert , Robotics Institute, Carnegie Mellon University
pp. 1-9

A multi-modal feature fusion framework for kinect-based facial expression recognition using Dual Kernel Discriminant Analysis (DKDA) (Abstract)

Sherin Aly , Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, Virginia, USA
A. Lynn Abbott , Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, Virginia, USA
Marwan Torki , Department of Computer Engineering, Faculty of Engineering, Alexandria University, Egypt
pp. 1-10

Learning patch-dependent kernel forest for person re-identification (Abstract)

Wei Wang , University of Tennessee, Knoxville
Ali Taalimi , University of Tennessee, Knoxville
Kun Duan , GE Research Center
Rui Guo , University of Tennessee, Knoxville
Hairong Qi , University of Tennessee, Knoxville
pp. 1-9

Hide and seek: Uncovering facial occlusion with variable-threshold robust PCA (Abstract)

Wee Kheng Leow , Dept. of Computer Science, National University of Singapore
Guodong Li , Dept. of Computer Science, National University of Singapore
Jian Lai , Dept. of Computer Science, National University of Singapore
Terence Sim , Dept. of Computer Science, National University of Singapore
Vaishali Sharma , Dept. of Computer Science, National University of Singapore
pp. 1-8

Score reliability based weighting technique for score-level fusion in multi-biometric systems (Abstract)

Waziha Kabir , Department of Electrical and Computer Engineering, Concordia University, Montreal, Quebec, Canada, H3G 1M8
M. Omair Ahmad , Department of Electrical and Computer Engineering, Concordia University, Montreal, Quebec, Canada, H3G 1M8
M. N. S. Swamy , Department of Electrical and Computer Engineering, Concordia University, Montreal, Quebec, Canada, H3G 1M8
pp. 1-7

HeHOP: Highly efficient head orientation and position estimation (Abstract)

Anke Schwarz , Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology
Zhuang Lin , Robert Bosch GmbH
Rainer Stiefelhagen , Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology
pp. 1-8

A revisit to human action recognition from depth sequences: Guided SVM-sampling for joint selection (Abstract)

Michel Antunes , Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg
Djamila Aouada , Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg
Bjorn Ottersten , Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg
pp. 1-8

Abstraction hierarchy and self annotation update for fine grained activity recognition (Abstract)

Song Cao , University of Southern California, Institute for Robotics and Intelligent Systems, Los Angeles, CA 90089, USA
Kan Chen , University of Southern California, Institute for Robotics and Intelligent Systems, Los Angeles, CA 90089, USA
Ram Nevatia , University of Southern California, Institute for Robotics and Intelligent Systems, Los Angeles, CA 90089, USA
pp. 1-9

Activity recognition and prediction with pose based discriminative patch model (Abstract)

Song Cao , University of Southern California, Institute for Robotics and Intelligent Systems, Los Angeles, CA 90089, USA
Kan Chen , University of Southern California, Institute for Robotics and Intelligent Systems, Los Angeles, CA 90089, USA
Ram Nevatia , University of Southern California, Institute for Robotics and Intelligent Systems, Los Angeles, CA 90089, USA
pp. 1-9

Deep tree-structured face: A unified representation for multi-task facial biometrics (Abstract)

Rui Guo , Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville
Liu Liu , Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville
Wei Wang , Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville
Ali Taalimi , Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville
Chi Zhang , Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville
Hairong Qi , Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville
pp. 1-8

Recognition of ongoing complex activities by sequence prediction over a hierarchical label space (Abstract)

Wenbin Li , Max Planck Institute for Informatics
Mario Fritz , Max Planck Institute for Informatics
pp. 1-9

Linear-time online action detection from 3D skeletal data using bags of gesturelets (Abstract)

Moustafa Meshry , Dept. of Computer and Systems Engineering, Alexandria University, Egypt
Mohamed E. Hussein , Dept. of Computer and Systems Engineering, Alexandria University, Egypt
Marwan Torki , Dept. of Computer and Systems Engineering, Alexandria University, Egypt
pp. 1-9

Efficient video-based retrieval of human motion with flexible alignment (Abstract)

Ankur Gupta , University of British Columbia
John He , University of British Columbia
Julieta Martinez , University of British Columbia
James J. Little , University of British Columbia
Robert J. Woodham , University of British Columbia
pp. 1-9

Combining multiple sources of knowledge in deep CNNs for action recognition (Abstract)

Eunbyung Park , University of North Carolina at Chapel Hill
Xufeng Han , University of North Carolina at Chapel Hill
Tamara L. Berg , University of North Carolina at Chapel Hill
Alexander C. Berg , University of North Carolina at Chapel Hill
pp. 1-8

Person re-identification using deformable patch metric learning (Abstract)

Slawomir Bak , Disney Research, Pittsburgh, PA, USA, 15213
Peter Carr , Disney Research, Pittsburgh, PA, USA, 15213
pp. 1-9

Support vector machines with time series distance kernels for action classification (Abstract)

Mohammad Ali Bagheri , Dalhousie University, University of Lar
Qigang Gao , Dalhousie University
Sergio Escalera , Universitat de Barcelona
pp. 1-7

Face fiducial detection by consensus of exemplars (Abstract)

B R Mallikarjun , KCIS, IIIT Hyderabad
Visesh Chari , KCIS, IIIT Hyderabad
C V Jawahar , KCIS, IIIT Hyderabad
Akshay Asthana , Seeing Machines, Inc
pp. 1-9

One-to-many face recognition with bilinear CNNs (Abstract)

Aruni Roy Chowdhury , University of Massachusetts, Amherst
Tsung-Yu Lin , University of Massachusetts, Amherst
Subhransu Maji , University of Massachusetts, Amherst
Erik Learned-Miller , University of Massachusetts, Amherst
pp. 1-9

Tooth guard: A vision system for detecting missing tooth in rope mine shovel (Abstract)

Ser Nam Lim , GE Global Research
Joao Soares , Yahoo, Inc.
Ning Zhou , GE Global Research
pp. 1-7

Multiscale fully convolutional network with application to industrial inspection (Abstract)

Xiao Bian , GE Global Research
Ser Nam Lim , GE Global Research
Ning Zhou , GE Global Research
pp. 1-8

Measuring and modeling apple trees using time-of-flight data for automation of dormant pruning applications (Abstract)

Somrita Chattopadhyay , School of Electrical and Computer Engineering, Purdue University
Shayan A. Akbar , School of Electrical and Computer Engineering, Purdue University
Noha M. Elfiky , School of Electrical and Computer Engineering, Purdue University
Henry Medeiros , Department of Electrical and Computer Engineering, Marquette University
Avinash Kak , School of Electrical and Computer Engineering, Purdue University
pp. 1-9

Texture classification for rail surface condition evaluation (Abstract)

Ke Ma , Stony Brook University
Tomas F. Yago Vicente , Stony Brook University
Dimitris Samaras , Stony Brook University
Michael Petrucci , KLD Labs, Inc.
Daniel L. Magnus , KLD Labs, Inc.
pp. 1-9

Visual recognition of paper analytical device images for detection of falsified pharmaceuticals (Abstract)

Sandipan Banerjee , Department of Computer Science and Engineering, University of Notre Dame
James Sweet , Department of Computer Science and Engineering, University of Notre Dame
Christopher Sweet , Department of Computer Science and Engineering, University of Notre Dame
Marya Lieberman , Department of Chemistry and Biochemistry, University of Notre Dame
pp. 1-9

Deep learning architectures for domain adaptation in HOV/HOT lane enforcement (Abstract)

Safwan Wshah , Palo Alto Research Center
Beilei Xu , Palo Alto Research Center
Orhan Bulan , Palo Alto Research Center
Jayant Kumar , Palo Alto Research Center
Peter Paul , Palo Alto Research Center
pp. 1-7

Learning deep-sea substrate types with visual topic models (Abstract)

Arnold Kalmbach , McGill University
Maia Hoeberechts , Ocean Networks Canada
Alexandra Branzan Albu , University of Victoria
Herve Glotin , LSIS AMU ENSAM CNRS Univ. Toulon
Sebastien Paris , LSIS AMU ENSAM CNRS Univ. Toulon
Yogesh Girdhar , Woods Hole Oceanographic Inst.
pp. 1-9

Detection of cracks in nuclear power plant using spatial-temporal grouping of local patches (Abstract)

Stephen J. Schmugge , Dept. of Computer Science, Univ. of North Carolina at Charlotte, Charlotte, NC 28223
Lance Rice , Dept. of Computer Science, Univ. of North Carolina at Charlotte, Charlotte, NC 28223
N. Rich Nguyen , Dept. of Computer Science, Univ. of North Carolina at Charlotte, Charlotte, NC 28223
John Lindberg , Electric Power Research Institute, Charlotte, NC 28262
Robert Grizzi , Electric Power Research Institute, Charlotte, NC 28262
Chris Joffe , Electric Power Research Institute, Charlotte, NC 28262
Min C. Shin , Dept. of Computer Science, Univ. of North Carolina at Charlotte, Charlotte, NC 28223
pp. 1-7

An elastic functional data analysis framework for preoperative evaluation of patients with Rheumatoid Arthritis (Abstract)

Chafik Samir , LIMOS CNRS UMR 6158, University of Clermont Auvergne, Clermont, France
Sebastian Kurtek , Department of Statistics, The Ohio State University, Columbus, OH, USA
Anuj Srivastava , Department of Statistics, Florida State University, Tallahassee, FL, USA
Noe Borges , Physical Activity and Health, University of Santa Catarina, Florianopolis, Brazil
pp. 1-8

A deep convolutional neural network trained on representative samples for circulating tumor cell detection (Abstract)

Yunxiang Mao , Missouri University of Science and Technology
Zhaozheng Yin , Missouri University of Science and Technology
Joseph Schober , Southern Illinois University Edwardsville
pp. 1-6

A new computer vision-based system to help clinicians objectively assess visual pursuit with the moving mirror stimulus for the diagnosis of minimally conscious state (Abstract)

Thomas Hoyoux , Laboratory for Signal and Image Exploitation, University of Liège, Liège, Belgium
Sarah Wannez , Coma Science Group, University of Liège, Liège, Belgium
Thomas Langohr , Laboratory for Signal and Image Exploitation, University of Liège, Liège, Belgium
Jerome Wertz , Phasya S.A., Liege, Belgium
Steven Laureys , Coma Science Group, University of Liège, Liège, Belgium
Jacques G. Verly , Laboratory for Signal and Image Exploitation, University of Liège, Liège, Belgium
pp. 1-8

Weighted atlas auto-context with application to multiple organ segmentation (Abstract)

Telmo Amaral , Open Lab, School of Computing Science, Newcastle University, Newcastle upon Tyne, UK
Ilias Kyriazakis , School of Agriculture, Food and Rural Development, Newcastle University, Newcastle upon Tyne, UK
Stephen J. McKenna , CVIP, Computing, School of Science and Engineering, University of Dundee, Dundee, UK
Thomas Plotz , Open Lab, School of Computing Science, Newcastle University, Newcastle upon Tyne, UK
pp. 1-9

Accurate 3D bone segmentation in challenging CT images: Bottom-up parsing and contextualized optimization (Abstract)

Le Lu Dijia Wu , National Institutes of Health
Nathan Lay , National Institutes of Health
David Liu , National Institutes of Health
Isabella Nogues , Google, Inc.
Ronald M. Summers , Siemens Healthcare
pp. 1-10

Real-time road traffic density estimation using block variance (Abstract)

Kratika Garg , Nanyang Technological University, Singapore
Siew-Kei Lam , Nanyang Technological University, Singapore
Thambipillai Srikanthan , Nanyang Technological University, Singapore
Vedika Agarwal , Birla Institute of Technology and Science, Pilani, India
pp. 1-9

Atomic scenes for scalable traffic scene recognition in monocular videos (Abstract)

Chao-Yeh Chen , University of Texas at Austin
Wongun Choi , NEC Labs America
Manmohan Chandraker , NEC Labs America
pp. 1-9

Eye-CU: Sleep pose classification for healthcare using multimodal multiview data (Abstract)

Carlos Torres , Univ. of California Santa Barbara
Victor Fragoso , West Virginia University
Scott D. Hammond , Univ. of California Santa Barbara
Jeffrey C. Fried , Santa Barbara Cottage Hospital
B.S. Manjunath , Univ. of California Santa Barbara
pp. 1-9

Fixation prediction with a combined model of bottom-up saliency and vanishing point (Abstract)

Mengyang Feng , Department of Electrical Engineering, Dalian University of Technology, China
Ali Borji , Center for Research in Computer Vision, University of Central Florida, Orlando, USA
Huchuan Lu , Department of Electrical Engineering, Dalian University of Technology, China
pp. 1-7

Is image super-resolution helpful for other vision tasks? (Abstract)

Dengxin Dai , Computer Vision Lab, ETH Zurich
Yujian Wang , Computer Vision Lab, ETH Zurich
Yuhua Chen , Computer Vision Lab, ETH Zurich
Luc Van Gool , Computer Vision Lab, ETH Zurich
pp. 1-9

Energy-efficient ConvNets through approximate computing (Abstract)

Bert Moons , ESAT-MICAS, Dept. of Electrical Engineering, KU Leuven
Bert De Brabandere , ESAT-VISICS, Dept. of Electrical Engineering, KU Leuven
Luc Van Gool , ESAT-VISICS, Dept. of Electrical Engineering, KU Leuven
Marian Verhelst , ESAT-MICAS, Dept. of Electrical Engineering, KU Leuven
pp. 1-8

Fine-grained sketch-based image retrieval: The role of part-aware attributes (Abstract)

Ke Li , Beijing University of Posts and Telecommunications
Kaiyue Pang , Beijing University of Posts and Telecommunications
Yi-Zhe Song , School of Electronic Engineering and Computer Science Queen Mary University of London
Timothy Hospedales , School of Electronic Engineering and Computer Science Queen Mary University of London
Honggang Zhang , Beijing University of Posts and Telecommunications
Yichuan Hu , Beijing University of Posts and Telecommunications
pp. 1-9

A crowdsourced approach to student engagement recognition in e-learning environments (Abstract)

Aditya Kamath , Georgia Institute of Technology
Aradhya Biswas , Georgia Institute of Technology
Vineeth Balasubramanian , Indian Institute of Technology Hyderabad
pp. 1-9

Color multi-fusion fisher vector feature for fine art painting categorization and influence analysis (Abstract)

Ajit Puthenputhussery , New Jersey Institute of Technology
Qingfeng Liu , New Jersey Institute of Technology
Chengjun Liu , New Jersey Institute of Technology
pp. 1-9

Constructing image mosaics using focus based depth analysis (Abstract)

Mohamed A. Helala , Faculty of Science, University of Ontario Institute of Technology, Oshawa, ON L1H 7K4 Canada
Faisal Z. Qureshi , Faculty of Science, University of Ontario Institute of Technology, Oshawa, ON L1H 7K4 Canada
pp. 1-9

Image set classification by symmetric positive semi-definite matrices (Abstract)

Masoud Faraki , Research School of Engineering, Australian National University, Australia, NICTA, Canberra Research Laboratory, Australia
Mehrtash T. Harandi , Research School of Engineering, Australian National University, Australia, NICTA, Canberra Research Laboratory, Australia
Fatih Porikli , Research School of Engineering, Australian National University, Australia, NICTA, Canberra Research Laboratory, Australia
pp. 1-8

Precise deterministic change detection for smooth surfaces (Abstract)

Simon Stent , University of Cambridge
Riccardo Gherardi , Toshiba Research Europe
Bjorn Stenger , Toshiba Research Europe
Roberto Cipolla , University of Cambridge
pp. 1-9

Unsupervised saliency estimation based on robust hypotheses (Abstract)

Fei Xu , Utah State University
Min Xian , Utah State University
H. D. Cheng , Utah State University
Jianrui Ding , Harbin Institute of Technology
Yingtao Zhang , Harbin Institute of Technology
pp. 1-6

On the importance of normalisation layers in deep learning with piecewise linear activation units (Abstract)

Zhibin Liao , ARC Centre of Excellence for Robotic Vision, University of Adelaide, Australia
Gustavo Carneiro , ARC Centre of Excellence for Robotic Vision, University of Adelaide, Australia
pp. 1-8

Deep learning the dynamic appearance and shape of facial action units (Abstract)

Shashank Jaiswal , The University of Nottingham
Michel Valstar , The University of Nottingham
pp. 1-8

IPDC: Iterative part-based dense correspondence between point clouds (Abstract)

Rongqi Qiu , University of Southern California
Ulrich Neumann , University of Southern California
pp. 1-9

Categorizing cubes: Revisiting pose normalization (Abstract)

Mohsen Hejrati , University of California, Irvine
Deva Ramanan , Carnegie Mellon University
pp. 1-9

Unsupervised categorical shape reconstruction through manifolds (Abstract)

Kent Fujiwara , NTT Communication Science Laboratories, NTT Corporation, Kanagawa, Japan
Minoru Mori , NTT Communication Science Laboratories, NTT Corporation, Kanagawa, Japan
Kunio Kashino , NTT Communication Science Laboratories, NTT Corporation, Kanagawa, Japan
pp. 1-8

Mobile phone and cloud — A dream team for 3D reconstruction (Abstract)

Alex Locher , CVL, ETH Zurich, Switzerland
Michael Perdoch , CVL, ETH Zurich, Switzerland
Hayko Riemenschneider , CVL, ETH Zurich, Switzerland
Luc Van Gool , CVL, ETH Zurich, Switzerland
pp. 1-8

Online inspection of 3D parts via a locally overlapping camera network (Abstract)

Tolga Birdal , Technical University of Munich
Emrah Bala , Gravi Ltd
Tolga Eren , Gravi Ltd
Slobodan Ilic , Siemens AG
pp. 1-10

Omnidirectional image capture on mobile devices for fast automatic generation of 2.5D indoor maps (Abstract)

Giovanni Pintore , CRS4, Pula (CA), Italy
Valeria Garro , ISTI-CNR, Pisa, Italy
Fabio Ganovelli , ISTI-CNR, Pisa, Italy
Enrico Gobbetti , CRS4, Pula (CA), Italy
Marco Agus , CRS4, Pula (CA), Italy
pp. 1-9

Where is that pixel in the oblique-view video? (Abstract)

Yin Li , Computer Science Department, National University of Singapore
Teck Khim Ng , Computer Science Department, National University of Singapore
pp. 1-8

Mono camera multi-view diminished reality (Abstract)

Philipp Tiefenbacher , Technische Universität München, Institute for Human-Machine Communication
Michael Sirch , Technische Universität München, Institute for Human-Machine Communication
Gerhard Rigoll , Technische Universität München, Institute for Human-Machine Communication
pp. 1-8

Mosaicing scenes with a quadcopter (Abstract)

Meghshyam G. Prasad , Dept. of Computer Science and Engineering, IIT Bombay
Sharat Chandran , Dept. of Computer Science and Engineering, IIT Bombay
Michael S. Brown , School of Computing, NUS
pp. 1-8

High accuracy model-based object pose estimation for autonomous recharging applications (Abstract)

Hanno Jaspers , Institute for Autonomous Systems Technology (TAS), University of the Bundeswehr Munich
Georg R. Mueller , Institute for Autonomous Systems Technology (TAS), University of the Bundeswehr Munich
Hans-Joachim Wuensche , Institute for Autonomous Systems Technology (TAS), University of the Bundeswehr Munich
pp. 1-7

CoRBS: Comprehensive RGB-D benchmark for SLAM using Kinect v2 (Abstract)

Oliver Wasenmuller , DFKI - German Research Center for Artificial Intelligence, Kaiserslautern, Germany
Marcel Meyer , DFKI - German Research Center for Artificial Intelligence, Kaiserslautern, Germany
Didier Stricker , DFKI - German Research Center for Artificial Intelligence, Kaiserslautern, Germany
pp. 1-7

Sky segmentation in the wild: An empirical study (Abstract)

Radu P. Mihail , Valdosta State University
Scott Workman , University of Kentucky
Zach Bessinger , University of Kentucky
Nathan Jacobs , University of Kentucky
pp. 1-6

Semantic segmentation of modular furniture (Abstract)

Tobias Pohlen , Visual Computing Institute, Computer Vision Group, RWTH Aachen University
Ishrat Badami , Visual Computing Institute, Computer Vision Group, RWTH Aachen University
Markus Mathias , Visual Computing Institute, Computer Vision Group, RWTH Aachen University
Bastian Leibe , Visual Computing Institute, Computer Vision Group, RWTH Aachen University
pp. 1-9

Simultaneous semantic segmentation of a set of partially labeled images (Abstract)

Qiongjie Tian , Computer Science and Engineering, Arizona State University
Baoxin Li , Computer Science and Engineering, Arizona State University
pp. 1-9

Direct 3D pose estimation of a planar target (Abstract)

Hung-Yu Tseng , National Taiwan University
Po-Chen Wu , National Taiwan University
Ming-Hsuan Yang , UC Merced
Shao-Yi Chien , National Taiwan University
pp. 1-9

Forget the checkerboard: Practical self-calibration using a planar scene (Abstract)

Daniel Herrera , University of Oulu, Finland
C. Juho Kannala , University of Oulu, Finland
Janne Heikkila , University of Oulu, Finland
pp. 1-9

6DOF point cloud alignment using geometric algebra-based adaptive filtering (Abstract)

Anas Al-Nuaimi , Technische Universität München
Eckehard Steinbach , Technische Universität München
Wilder B. Lopes , Universidade de São Paulo
Cassio G. Lopes , Universidade de São Paulo
pp. 1-9

Unifying diffuse and specular reflections for the photometric stereo problem (Abstract)

Roberto Mecca , Engineering Department, University of Cambridge (United Kingdom)
Yvain Queau , Université de Toulouse (France)
pp. 1-9

Underwater 3D capture using a low-cost commercial depth camera (Abstract)

Sundara Tejaswi Digumarti , Disney Research Zurich, ETH Zurich
Gaurav Chaurasia , Disney Research Zurich
Aparna Taneja , Disney Research Zurich
Roland Siegwart , ETH Zurich
Amber Thomas , Walt Disney World
Paul Beardsley , Disney Research Zurich
pp. 1-9

Resolution enhancement in single depth map and aligned image (Abstract)

Yingli Tian , The Graduate Center and City College The City University of New York
Yang Xian , The Graduate Center The City University of New York
pp. 1-9

Lifting GIS maps into strong geometric context for scene understanding (Abstract)

Raul Diaz , Computer Science Department, University of California, Irvine
Minhaeng Lee , Computer Science Department, University of California, Irvine
Jochen Schubert , Computer Science Department, University of California, Irvine
Charless C. Fowlkes , Computer Science Department, University of California, Irvine
pp. 1-9

Heat propagation contours for 3D non-rigid shape analysis (Abstract)

Xupeng Wang , School of Information and Software Engineering, University of Electronic Science and Technology of China
Ferdous Sohel , School of Engineering and Information Technology, Murdoch University
Mohammed Bennamoun , School of Computer Science and Software Engineering, The University of Western Australia
Hang Lei , School of Information and Software Engineering, University of Electronic Science and Technology of China
pp. 1-7

Dealing with small data and training blind spots in the Manhattan world (Abstract)

Wajahat Hussain , Aragón Institute of Engineering Research (I3A), Universidad de Zaragoza, Spain
Javier Civera , Aragón Institute of Engineering Research (I3A), Universidad de Zaragoza, Spain
Luis Montano , Aragón Institute of Engineering Research (I3A), Universidad de Zaragoza, Spain
Martial Hebert , Robotics Institute, Carnegie Mellon University, USA
pp. 1-9

Automatic 3D reconstruction of manifold meshes via delaunay triangulation and mesh sweeping (Abstract)

Andrea Romanoni , Politécnico di Milano, Italy
Amael Delaunoy , ETH Zürich, Switzerland
Marc Pollefeys , ETH Zürich, Switzerland
Matteo Matteucci , Politecnico di Milano, Italy
pp. 1-8

Half hypersphere confinement for piecewise linear regression (Abstract)

Eduardo Perez-Pellitero , TNT Lab, Leibniz Universität Hannover
Jordi Salvador , Technicolor R&I Hannover
Javier Ruiz-Hidalgo , Image Processing Group, Universitat Politècnica de Catalunya
Bodo Rosenhahn , TNT Lab, Leibniz Universität Hannover
pp. 1-9

3D shape retrieval using a single depth image from low-cost sensors (Abstract)

Jie Feng , Department of Computer Science, Columbia University
Yan Wang , Department of Electrical Engineering, Columbia University
Shih-Fu Chang , Department of Computer Science, Columbia University
pp. 1-9

Architectural decomposition for 3D landmark building understanding (Abstract)

Nikolay Kobyshev , CVL, ETH Zurich, Switzerland
Hayko Riemenschneider , CVL, ETH Zurich, Switzerland
Andras Bodis-Szomoru , CVL, ETH Zurich, Switzerland
Luc Van Gool , CVL, ETH Zurich, Switzerland
pp. 1-10

Voting-based 3D object cuboid detection robust to partial occlusion from RGB-D images (Abstract)

Sangdoo Yun , Department of ECE, ASRI, Seoul National University, Seoul, Korea
Hawook Jeong , Samsung Electronics Co., Ltd
Soo Wan Kim , Samsung Electronics Co., Ltd
Jin Young Choi , Department of ECE, ASRI, Seoul National University, Seoul, Korea
pp. 1-8

Joint object recognition and pose estimation using a nonlinear view-invariant latent generative model (Abstract)

Amr Bakry , Computer Science Department, Rutgers University
Tarek Elgaaly , Computer Science Department, Rutgers University
Mohamed Elhoseiny , Computer Science Department, Rutgers University
Ahmed Elgammal , Computer Science Department, Rutgers University
pp. 1-9

The generalized relative pose and scale problem: View-graph fusion via 2D-2D registration (Abstract)

Laurent Kneip , Australian National University
Chris Sweeney , University of California Santa Barbara
Richard Hartley , Australian National University
pp. 1-9

Efficient joint stereo estimation and land usage classification for multiview satellite data (Abstract)

Ke Wang , Department of Computer Science, The University of North Carolina at Chapel Hill
Craig Stutts , Applied Research Associates, Inc.
Enrique Dunn , Department of Computer Science, The University of North Carolina at Chapel Hill
Jan-Michael Frahm , Department of Computer Science, The University of North Carolina at Chapel Hill
pp. 1-9

Automatic detection and analysis of photovoltaic modules in aerial infrared imagery (Abstract)

Sergiu Dotenco , Department of Computer Science, Nuremberg Institute of Technology, Nuremberg, Germany
Manuel Dalsass , ZAE Bayern, Germany
Ludwig Winkler , Pattern Recognition Lab, Friedrich-Alexander University Erlangen-Nürnberg, Erlangen, Germany
Tobias Wurzner , Pattern Recognition Lab, Friedrich-Alexander University Erlangen-Nürnberg, Erlangen, Germany
Christoph Brabec , ZAE Bayern, Germany
Andreas Maier , Pattern Recognition Lab, Friedrich-Alexander University Erlangen-Nürnberg, Erlangen, Germany
Florian Gallwitz , Department of Computer Science, Nuremberg Institute of Technology, Nuremberg, Germany
pp. 1-9

Open source structure-from-motion for aerial video (Abstract)

Matthew J. Leotta , Kitware, Inc.
Eric Smith , Kitware, Inc.
Matthew Dawkins , Kitware, Inc.
Paul Tunison , Kitware, Inc.
pp. 1-9

Person-following UAVs (Abstract)

Francisca Vasconcelos , Torrey Pines High School
Nuno Vasconcelos , University of California San Diego
pp. 1-9

Detection of quadrilateral document regions from digital photographs (Abstract)

Jian Fan , HP Labs, Palo Alto, California, USA
pp. 1-9

An FPGA-accelerated partial duplicate image retrieval engine for a document search system (Abstract)

Hidetoshi Matsumura , Fujitsu Laboratories Ltd., 4-1-1 Kamikodanaka, Nakahara-ku, Kawasaki, Kanagawa, Japan
Masahiko Sugimura , Fujitsu Laboratories Ltd., 4-1-1 Kamikodanaka, Nakahara-ku, Kawasaki, Kanagawa, Japan
Hironobu Yamasaki , Fujitsu Laboratories Ltd., 4-1-1 Kamikodanaka, Nakahara-ku, Kawasaki, Kanagawa, Japan
Yasumoto Tomita , Fujitsu Laboratories Ltd., 4-1-1 Kamikodanaka, Nakahara-ku, Kawasaki, Kanagawa, Japan
Takayuki Baba , Fujitsu Laboratories Ltd., 4-1-1 Kamikodanaka, Nakahara-ku, Kawasaki, Kanagawa, Japan
Yasuhiro Watanabe , Fujitsu Laboratories Ltd., 4-1-1 Kamikodanaka, Nakahara-ku, Kawasaki, Kanagawa, Japan
pp. 1-7

A fast and robust text spotter (Abstract)

Siyang Qin , Computer Engineering Department, University of California, Santa Cruz
Roberto Manduchi , Computer Engineering Department, University of California, Santa Cruz
pp. 1-8

Persistent 3D stabilization for aerial imagery (Abstract)

Bor-Jeng Chen , University of Southern California
Gerard Medioni , University of Southern California
pp. 1-8

A two-stage detector for hand detection in ego-centric videos (Abstract)

Xiaolong Zhu , Tencent
Wei Liu , The University of Hong Kong
Xuhui Jia , The University of Hong Kong
Kwan-Yee K. Wong , The University of Hong Kong
pp. 1-8

A novel inheritable color space with application to kinship verification (Abstract)

Qingfeng Liu , New Jersey Institute of Technology
Ajit Puthenputhussery , New Jersey Institute of Technology
Chengjun Liu , New Jersey Institute of Technology
pp. 1-9

A real-time visual card reader for mobile devices (Abstract)

Lukas Stehr , Data and Web Science Group, University of Mannheim
Robert Meusel , Data and Web Science Group, University of Mannheim
Stephan Kopf , Department of Computer Science IV, University of Mannheim
pp. 1-7

Accurate and efficient pulse measurement from facial videos on smartphones (Abstract)

Chong Huang , University of California, Santa Barbara
Xin Yang , Huazhong University of Science and Technology
Kwang-Ting Tim Cheng , University of California, Santa Barbara
pp. 1-8

Discovering useful parts for pose estimation in sparsely annotated datasets (Abstract)

Mikhail Breslav , Department of Computer Science, Boston University
Tyson L. Hedrick , Department of Biology, University of North Carolina
Stan Sclaroff , Department of Computer Science, Boston University
Margrit Betke , Department of Computer Science, Boston University
pp. 1-9

Arrays of single pixel time-of-flight sensors for privacy preserving tracking and coarse pose estimation (Abstract)

Indrani Bhattacharya , Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute
Richard J. Radke , Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute
pp. 1-9

A driver fatigue detection method based on multi-sensor signals (Abstract)

Hao Yin , Xi'an Jiaotong University
Yuanqi Su , Xi'an Jiaotong University
Yuehu Liu , Xi'an Jiaotong University
Danchen Zhao , Xi'an Jiaotong University
pp. 1-7

Accurate eye center localization using Snakuscule (Abstract)

Sanyam Garg , Microsoft Research India
Abhinav Tripathi , Microsoft Research India
Edward Cutrell , Microsoft Research India
pp. 1-8

Furthering fingerprint-based authentication: Introducing the true-neighbor template (Abstract)

Fawaz E. Alsaadi , University of Colorado at Colorado Springs, Colorado Springs, Colorado, USA
Terrance E. Boult , University of Colorado at Colorado Springs, Colorado Springs, Colorado, USA
pp. 1-7

A practical approach to real-time neutral feature subtraction for facial expression recognition (Abstract)

Nick Haber , Stanford University, 450 Serra Mall, Stanford, CA 94305
Catalin Voss , Stanford University, 450 Serra Mall, Stanford, CA 94305
Azar Fazel , Stanford University, 450 Serra Mall, Stanford, CA 94305
Terry Winograd , Stanford University, 450 Serra Mall, Stanford, CA 94305
Dennis P. Wall , Stanford University, 450 Serra Mall, Stanford, CA 94305
pp. 1-9

Person re-identification using multiple first-person-views on wearable devices (Abstract)

Anirban Chakraborty , Nanyang Technological University, Singapore 639798
Bappaditya Mandal , Institute for Infocomm Research (IR), A∗STAR, Singapore 138632
Hamed Kiani Galoogahi , Istituto Italiano di Tecnologia (IIT), Genova, 16163, Italy
pp. 1-8

A coarse-to-fine deep learning for person re-identification (Abstract)

Alexandre Franco , Intelligent Vision Research Lab, Federal University of Bahia
Luciano Oliveira , Intelligent Vision Research Lab, Federal University of Bahia
pp. 1-7

Analyzing human appearance as a cue for dating images (Abstract)

Tawfiq Salem , Department of Computer Science, University of Kentucky
Scott Workman , Department of Computer Science, University of Kentucky
Menghua Zhai , Department of Computer Science, University of Kentucky
Nathan Jacobs , Department of Computer Science, University of Kentucky
pp. 1-8

Multimodal emotion recognition using deep learning architectures (Abstract)

Hiranmayi Ranganathan , Center for Cognitive Ubiquitous Computing (CUbiC) Arizona State University
Shayok Chakraborty , Center for Cognitive Ubiquitous Computing (CUbiC) Arizona State University
Sethuraman Panchanathan , Center for Cognitive Ubiquitous Computing (CUbiC) Arizona State University
pp. 1-9

Fine-tuning human pose estimations in videos (Abstract)

Digvijay Singh , KCIS, International Institute of Information Technology, Hyderabad, India
Vineeth Balasubramanian , Computer Science and Engineering Department, Indian Institute of Technology, Hyderabad, India
C. V. Jawahar , KCIS, International Institute of Information Technology, Hyderabad, India
pp. 1-9

An enhanced deep feature representation for person re-identification (Abstract)

Shangxuan Wu , Intelligence Science and System Lab, Sun Yat-sen University, China
Ying-Cong Chen , Intelligence Science and System Lab, Sun Yat-sen University, China
Xiang Li , Intelligence Science and System Lab, Sun Yat-sen University, China
An-Cong Wu , Intelligence Science and System Lab, Sun Yat-sen University, China
Jin-Jie You , Intelligence Science and System Lab, Sun Yat-sen University, China
Wei-Shi Zheng , Intelligence Science and System Lab, Sun Yat-sen University, China
pp. 1-8

Crowd density estimation based on rich features and random projection forest (Abstract)

Bolei Xu , The University of Nottingham Ningbo China
Guoping Qiu , The University of Nottingham Ningbo China
pp. 1-8

People detection in crowded scenes by context-driven label propagation (Abstract)

Jingjing Liu , Rutgers University
Quanfu Fan , IBM T. J. Watson Research Center
Sharath Pankanti , IBM T. J. Watson Research Center
Dimitris N. Metaxas , Rutgers University
pp. 1-9

Efficient unsupervised abnormal crowd activity detection based on a spatiotemporal saliency detector (Abstract)

Yilin Wang , Arizona State University, Tempe, Arizona
Qiang Zhang , Samsung, Pasadena, California
Baoxin Li , Arizona State University, Tempe, Arizona
pp. 1-9

Vision-based counting of pedestrians and cyclists (Abstract)

Mehmet Kemal Kocamaz , Robotics Institute, Carnegie Mellon University
Jian Gong , Robotics Institute, Carnegie Mellon University
Bernardo R. Pires , Robotics Institute, Carnegie Mellon University
pp. 1-8

Static action recognition by efficient greedy inference (Abstract)

Shaukat Abidi , Faculty of Engineering and IT, University of Technology Sydney
Massimo Piccardi , Faculty of Engineering and IT, University of Technology Sydney
Mary-Anne Williams , Faculty of Engineering and IT, University of Technology Sydney
pp. 1-8

An analysis of 1-to-first matching in iris recognition (Abstract)

Andrey Kuehlkamp , Department of Computer Science & Engineering, University of Notre Dame, Notre Dame, Indiana
Kevin W. Bowyer , Department of Computer Science & Engineering, University of Notre Dame, Notre Dame, Indiana
pp. 1-8

Self-taught object localization with deep networks (Abstract)

Loris Bazzani , Department of Computer Science, Dartmouth College
Alessandra Bergamo , Department of Computer Science, Dartmouth College
Dragomir Anguelov , Google Inc.
Lorenzo Torresani , Department of Computer Science, Dartmouth College
pp. 1-9

Learning a structured dictionary for video-based face recognition (Abstract)

Hongyu Xu , Department of Electrical and Computer Engineering and the Center for Automation Research, UMIACS, University of Maryland, College Park, MD, USA
Jingjing Zheng , Department of Electrical and Computer Engineering and the Center for Automation Research, UMIACS, University of Maryland, College Park, MD, USA
Azadeh Alavi , Department of Electrical and Computer Engineering and the Center for Automation Research, UMIACS, University of Maryland, College Park, MD, USA
Rama Chellappa , Department of Electrical and Computer Engineering and the Center for Automation Research, UMIACS, University of Maryland, College Park, MD, USA
pp. 1-9

Kernel auto-encoder for semi-supervised hashing (Abstract)

Behnam Gholami , Computer Science Department, Rutgers University
Abolfazl Hajisami , Department of Electrical and Computer Engineering, Rutgers University
pp. 1-8

Higher-order class-specific priors for semantic segmentation of 3D outdoor scenes (Abstract)

Bingxiao Tang , School of Electronic Science and Engineering, Nanjing University, Nanjing, China
Yu Zhou , School of Electronic Science and Engineering, Nanjing University, Nanjing, China
Yao Yu , School of Electronic Science and Engineering, Nanjing University, Nanjing, China
Sidan Du , School of Electronic Science and Engineering, Nanjing University, Nanjing, China
pp. 1-9

Multi-view dynamic texture learning (Abstract)

Thanh Minh Nguyen , Department of Electrical and Computer Engineering, University of Windsor 401 Sunset Avenue, Windsor, ON, N9B-3P4, Canada
Q. M. Jonathan Wu , Department of Electrical and Computer Engineering, University of Windsor 401 Sunset Avenue, Windsor, ON, N9B-3P4, Canada
pp. 1-9

Automatic and quantitative evaluation of attribute discovery methods (Abstract)

Liangchen Liu , The University of Queensland, School of ITEE, QLD 4072, Australia
Arnold Wiliem , The University of Queensland, School of ITEE, QLD 4072, Australia
Shaokang Chen , The University of Queensland, School of ITEE, QLD 4072, Australia
Brian C. Lovell , The University of Queensland, School of ITEE, QLD 4072, Australia
pp. 1-9

Deep recursive and hierarchical conditional random fields for human action recognition (Abstract)

Tianliang Liu , Nanjing University of Posts and Telecommunications
Xincheng Wang , Nanjing University of Posts and Telecommunications
Xiubin Dai , Nanjing University of Posts and Telecommunications
Jiebo Luo , University of Rochester
pp. 1-9

Think big, solve small: Scaling up robust PCA with coupled dictionaries (Abstract)

Jian Lai , Dept. of Computer Science, National University of Singapore
Wee Kheng Leow , Dept. of Computer Science, National University of Singapore
Terence Sim , Dept. of Computer Science, National University of Singapore
Vaishali Sharma , Dept. of Computer Science, National University of Singapore
pp. 1-8

Discriminative training of CRF models with probably submodular constraints (Abstract)

Wojciech Zaremba , Dept. of Computer Science, Courant Institute, New York University
Matthew B. Blaschko , Center for Processing Speech and Images, Dept. of Electrical Engineering, KU Leuven
pp. 1-7

Efficient transductive semantic segmentation (Abstract)

Jose M. Alvarez , NICTA∗/Data61, Canberra ACT 2601, Australia
Mathieu Salzmann , EPFL, Laussane, Switzerland
Nick Barnes , NICTA∗/Data61, Canberra ACT 2601, Australia
pp. 1-9

Unsupervised network pretraining via encoding human design (Abstract)

Ming-Yu Liu , Mitsubishi Electric Research Labs (MERL), Cambridge MA, USA
Arun Mallya , University of Illinois, Urbana-Champaign, IL, USA
Oncel Tuzel , Mitsubishi Electric Research Labs (MERL), Cambridge MA, USA
Xi Chen , University of Maryland, College Park, MD, USA
pp. 1-9

Coupled depth learning (Abstract)

Mohammad Haris Baig , Dartmouth College, Hanover, New Hampshire, USA
Lorenzo Torresani , Dartmouth College, Hanover, New Hampshire, USA
pp. 1-10

Fine-grained classification via mixture of deep convolutional neural networks (Abstract)

ZongYuan Ge , Australian Centre for Robotic Vision, Brisbane, Australia
Alex Bewley , Queensland University of Technology (QUT), Brisbane, Australia
Christopher McCool , Australian Centre for Robotic Vision, Brisbane, Australia
Peter Corke , Australian Centre for Robotic Vision, Brisbane, Australia
Ben Upcroft , Australian Centre for Robotic Vision, Brisbane, Australia
Conrad Sanderson , University of Queensland, Brisbane, Australia
pp. 1-6

An end-to-end generative framework for video segmentation and recognition (Abstract)

Hilde Kuehne , University of Bonn
Juergen Gall , University of Bonn
Thomas Serre , Brown University
pp. 1-8

A mid-level representation of visual structures for video compression (Abstract)

Georgios Georgiadis , Dolby Laboratories, 4000 West Alameda Ave., Burbank, CA 91505
Stefano Soatto , UCLA Vision Lab, University of California, Los Angeles, CA 90095
pp. 1-8

Video summarization for remote invigilation of online exams (Abstract)

Melissa Cote , University of Victoria, Victoria, BC, Canada
Frederic Jean , University of Victoria, Victoria, BC, Canada
Alexandra Branzan Albu , University of Victoria, Victoria, BC, Canada
David Capson , University of Victoria, Victoria, BC, Canada
pp. 1-9

Automatic video editing for sensor-rich videos (Abstract)

Wesley Taylor , Faculty of Science, University of Ontario Institute of Technology, Oshawa, ON L1H 7K4 Canada
Faisal Z. Qureshi , Faculty of Science, University of Ontario Institute of Technology, Oshawa, ON L1H 7K4 Canada
pp. 1-9

Tag-based video retrieval by embedding semantic content in a continuous word space (Abstract)

Arnav Agharwal , University of Southern California
Rama Kovvuri , University of Southern California
Ram Nevatia , University of Amsterdam
Cees G.M. Snoek , University of Amsterdam
pp. 1-8

Discovering picturesque highlights from egocentric vacation videos (Abstract)

Vinay Bettadapura , Georgia Institute of Technology
Daniel Castro , Georgia Institute of Technology
Irfan Essa , Georgia Institute of Technology
pp. 1-9

Compact CNN for indexing egocentric videos (Abstract)

Yair Poleg , The Hebrew University of Jerusalem, Jerusalem, Israel
Ariel Ephrat , The Hebrew University of Jerusalem, Jerusalem, Israel
Shmuel Peleg , The Hebrew University of Jerusalem, Jerusalem, Israel
Chetan Arora , IIIT Delhi, India
pp. 1-9

Transition Hough forest for trajectory-based action recognition (Abstract)

Guillermo Garcia-Hernando , Imperial College London
Hyung Jin Chang , Imperial College London
Ismael Serrano , University of Castilla-La Mancha
Oscar Deniz , University of Castilla-La Mancha
Tae-Kyun Kim , Imperial College London
pp. 1-8

Is alice chasing or being chased?: Determining subject and object of activities in videos (Abstract)

Teng Zhang , School of ITEE, The University of Queensland
Liangchen Liu , School of ITEE, The University of Queensland
Arnold Wiliem , School of ITEE, The University of Queensland
Brian Lovell , School of ITEE, The University of Queensland
pp. 1-7

High performance moves recognition and sequence segmentation based on key poses filtering (Abstract)

Claudio Marcio de Souza Vicente , Universidade Federal de Minas Gerais. UFMG, Brazil
Erickson R. Nascimento , Universidade Federal de Minas Gerais. UFMG, Brazil
Luiz Eduardo C. Emery , Universidade Federal de Minas Gerais. UFMG, Brazil
Cristiano Arruda G. Flor , Universidade Federal de Minas Gerais. UFMG, Brazil
Thales Vieira , Universidade Federal de Alagoas. UFAL, Brazil
Leonardo B. Oliveira , Universidade Federal de Minas Gerais. UFMG, Brazil
pp. 1-8

The geometry of a scene: On deep semantics for visual perception driven cognitive film, studies (Abstract)

Jakob Suchan , Human-Centred Cognitive Assistance Lab., University of Bremen, Germany
Mehul Bhatt , Human-Centred Cognitive Assistance Lab., University of Bremen, Germany
pp. 1-9

A fast method for estimating transient scene attributes (Abstract)

Ryan Baltenberger , Department of Computer Science, University of Kentucky
Menghua Zhai , Department of Computer Science, University of Kentucky
Connor Greenwell , Department of Computer Science, University of Kentucky
Scott Workman , Department of Computer Science, University of Kentucky
Nathan Jacobs , Department of Computer Science, University of Kentucky
pp. 1-8

MIDI-assisted egocentric optical music recognition (Abstract)

Liang Chen , Indiana University, Bloomington, IN
Kun Duan , GE Global Research, Niskayuna, NY
pp. 1-9

The ULg multimodality drowsiness database (called DROZY) and examples of use (Abstract)

Quentin Massoz , Laboratory for Signal and Image Exploitation, University of Liège, Liège, Belgium
Thomas Langohr , Laboratory for Signal and Image Exploitation, University of Liège, Liège, Belgium
Clementine Francois , Laboratory for Signal and Image Exploitation, University of Liège, Liège, Belgium
Jacques G. Verly , Laboratory for Signal and Image Exploitation, University of Liège, Liège, Belgium
pp. 1-7

Task-driven progressive part localization for fine-grained recognition (Abstract)

Chen Huang , University of Missouri
Zhihai He , University of Missouri
pp. 1-9

Generating reliable video annotations by exploiting the crowd (Abstract)

Roberto Di Salvo , Pattern Recognition and Computer Vision (PeRCeiVe) Lab, Department of Electrical, Electronics and Computer Engineering (DIEEI), University of Catania, Italy
Concetto Spampinato , Pattern Recognition and Computer Vision (PeRCeiVe) Lab, Department of Electrical, Electronics and Computer Engineering (DIEEI), University of Catania, Italy
Daniela Giordano , Pattern Recognition and Computer Vision (PeRCeiVe) Lab, Department of Electrical, Electronics and Computer Engineering (DIEEI), University of Catania, Italy
pp. 1-8

Extended coherent point drift algorithm with correspondence priors and optimal subsampling (Abstract)

Vladislav Golyanik , German Research Center for Artificial Intelligence, Trippstadter Str. 122, 67663 Kaiserslautern, Germany
Bertram Taetz , German Research Center for Artificial Intelligence, Trippstadter Str. 122, 67663 Kaiserslautern, Germany
Gerd Reis , German Research Center for Artificial Intelligence, Trippstadter Str. 122, 67663 Kaiserslautern, Germany
Didier Stricker , German Research Center for Artificial Intelligence, Trippstadter Str. 122, 67663 Kaiserslautern, Germany
pp. 1-9

Occlusion-aware video registration for highly non-rigid objects (Abstract)

Bertram Taetz , German Research Center for Artificial Intelligence, Kaiserslautern, Germany
Gabriele Bleser , German Research Center for Artificial Intelligence, Kaiserslautern, Germany
Vladislav Golyanik , German Research Center for Artificial Intelligence, Kaiserslautern, Germany
Didier Stricke , German Research Center for Artificial Intelligence, Kaiserslautern, Germany
pp. 1-9

Optimal radiometric calibration for camera-display communication (Abstract)

Eric Wengrowski , Department of Electrical and Computer Engineering and WINLAB, Rutgers University
Wenjia Yuan , Department of Electrical and Computer Engineering and WINLAB, Rutgers University
Kristin J. Dana , Department of Electrical and Computer Engineering and WINLAB, Rutgers University
Ashwin Ashok , Department of Electrical and Computer Engineering, Carnegie Mellon University
Marco Gruteser , Department of Electrical and Computer Engineering and WINLAB, Rutgers University
Narayan Mandayam , Department of Electrical and Computer Engineering and WINLAB, Rutgers University
pp. 1-10

Decomposing time series with application to temporal segmentation (Abstract)

Jiaping Zhao , University of Southern California
Laurent Itti , University of Southern California
pp. 1-9

LATCH: Learned arrangements of three patch codes (Abstract)

Gil Levi , The Open University of Israel
Tal Hassner , The Open University of Israel, USC / Information Sciences Institute
pp. 1-9

Texture instance similarity via dense correspondences (Abstract)

Tal Hassner , The open University of Israel
Gilad Saban , The open University of Israel
Lior Wolf , Tel-Aviv University
pp. 1-9

Mode-shape interpretation: Re-thinking modal space for recovering deformable shapes (Abstract)

Antonio Agudo , Institut de Robòtica i Informàtica Industrial (CSIC-UPC), Barcelona, Spain
J. M. M. Montiel , Instituto de Investigación en Ingeniería de Aragon (I3A), Universidad de Zaragoza, Spain
Begona Calvo , Instituto de Investigación en Ingeniería de Aragon (I3A), Universidad de Zaragoza, Spain
Francesc Moreno-Noguer , Institut de Robòtica i Informàtica Industrial (CSIC-UPC), Barcelona, Spain
pp. 1-8

Line segment matching: A benchmark (Abstract)

Kai Li , School of Remote Sensing and Information Engineering, Wuhan University, P.R. China
Jian Yao , School of Remote Sensing and Information Engineering, Wuhan University, P.R. China
Mengsheng Lu , School of Remote Sensing and Information Engineering, Wuhan University, P.R. China
Yuan Heng , School of Remote Sensing and Information Engineering, Wuhan University, P.R. China
Teng Wu , School of Remote Sensing and Information Engineering, Wuhan University, P.R. China
Yinxuan Li , School of Remote Sensing and Information Engineering, Wuhan University, P.R. China
pp. 1-9

Binary patterns for shape description in RGB-D object registration (Abstract)

Cristina Romero-Gonzalez , Computer Systems Department, University of Castilla-La Mancha, Spain
Jesus Martinez-Gomez , Computer Systems Department, University of Castilla-La Mancha, Spain
Ismael Garcia-Varea , Computer Systems Department, University of Castilla-La Mancha, Spain
Luis Rodriguez-Ruiz , Computer Systems Department, University of Castilla-La Mancha, Spain
pp. 1-9

Joint geometric graph embedding for partial shape matching in images (Abstract)

Anirban Mukhopadhyay , Zuse Institute Berlin, Berlin, Germany
Arun C S Kumar , Department of Computer Science, The University of Georgia, Athens, Georgia, 30602-7404, USA
Suchendra M. Bhandarkar , Department of Computer Science, The University of Georgia, Athens, Georgia, 30602-7404, USA
pp. 1-9

Graph matching with low-rank regularization (Abstract)

Tianshu Yu , University of Calgary
Ruisheng Wang , University of Calgary
pp. 1-9

Adapting attributes by selecting features similar across domains (Abstract)

Siqi Liu , University of Pittsburgh
Adriana Kovashka , University of Pittsburgh
pp. 1-8

Predicting wide receiver trajectories in American football (Abstract)

Namhoon Lee , The Robotics Institute, Carnegie Mellon University
Kris M. Kitani , The Robotics Institute, Carnegie Mellon University
pp. 1-9

Human and sheep facial landmarks localisation by triplet interpolated features (Abstract)

Heng Yang , University of Cambridge
Renqiao Zhang , University of Cambridge
Peter Robinson , University of Cambridge
pp. 1-8

Joint point and line segment matching on wide-baseline stereo images (Abstract)

Kai Li , School of Remote Sensing and Information Engineering, Wuhan University, P.R. China
Jian Yao , School of Remote Sensing and Information Engineering, Wuhan University, P.R. China
Menghan Xia , School of Remote Sensing and Information Engineering, Wuhan University, P.R. China
Li Li , School of Remote Sensing and Information Engineering, Wuhan University, P.R. China
pp. 1-9

A two-sample test for statistical comparisons of shape populations (Abstract)

Wade Henning , The Meaning of Shape Company, Tallahassee, FL
Anuj Srivastava , Florida State University Tallahassee, FL
pp. 1-9
97 ms
(Ver 3.3 (11022016))