The Community for Technology Leaders
2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2015)
Boston, MA, USA
June 7, 2015 to June 12, 2015
ISSN: 2160-7516
ISBN: 978-1-4673-6758-5
TABLE OF CONTENTS

Self-tuned deep super resolution (Abstract)

Zhangyang Wang , Beckman Institute, University of Illinois at Urbana-Champaign, 61801, USA
Yingzhen Yang , Beckman Institute, University of Illinois at Urbana-Champaign, 61801, USA
Zhaowen Wang , Adobe Systems Inc, San Jose, CA 95110, USA
Shiyu Chang , Beckman Institute, University of Illinois at Urbana-Champaign, 61801, USA
Wei Han , Beckman Institute, University of Illinois at Urbana-Champaign, 61801, USA
Jianchao Yang , Snapchat Inc, Venice, CA 90291, USA
Thomas Huang , Beckman Institute, University of Illinois at Urbana-Champaign, 61801, USA
pp. 1-8

Channel-Max, Channel-Drop and Stochastic Max-pooling (Abstract)

Yuchi Huang , NEC Labs, Beijing, China
Xiuyu Sun , NEC Labs, Beijing, China
Ming Lu , Tsinghua University, Beijing, China
Ming Xu , NEC Labs, Beijing, China
pp. 9-17

Convolutional recurrent neural networks: Learning spatial dependencies for image representation (Abstract)

Zhen Zuo , Nanyang Technological University, Singapore
Bing Shuai , Nanyang Technological University, Singapore
Gang Wang , Nanyang Technological University, Singapore
Xiao Liu , Nanyang Technological University, Singapore
Xingxing Wang , Nanyang Technological University, Singapore
Bing Wang , Nanyang Technological University, Singapore
Yushi Chen , Harbin Institute of Technology, China
pp. 18-26

Deep learning of binary hash codes for fast image retrieval (Abstract)

Kevin Lin , Academia Sinica, Taiwan
Huei-Fang Yang , Academia Sinica, Taiwan
Jen-Hao Hsiao , Yahoo! Taiwan
Chu-Song Chen , Academia Sinica, Taiwan
pp. 27-35

From generic to specific deep representations for visual recognition (Abstract)

Hossein Azizpour , KTH (Royal Institute of Technology), 114 28 Stockholm, Sweden
Ali Sharif Razavian , KTH (Royal Institute of Technology), 114 28 Stockholm, Sweden
Josephine Sullivan , KTH (Royal Institute of Technology), 114 28 Stockholm, Sweden
Atsuto Maki , KTH (Royal Institute of Technology), 114 28 Stockholm, Sweden
Stefan Carlsson , KTH (Royal Institute of Technology), 114 28 Stockholm, Sweden
pp. 36-45

Subset feature learning for fine-grained category classification (Abstract)

ZongYuan Ge , Australian Centre for Robotic Vision, Brisbane, Australia
Christopher McCool , Queensland University of Technology (QUT), Brisbane, Australia
Conrad Sanderson , University of Queensland, Brisbane, Australia
Peter Corke , Australian Centre for Robotic Vision, Brisbane, Australia
pp. 46-52

Exploiting local features from deep networks for image retrieval (Abstract)

Joe Yue-Hei Ng , University of Maryland, College Park, 20742, United States
Fan Yang , University of Maryland, College Park, 20742, United States
Larry S. Davis , University of Maryland, College Park, 20742, United States
pp. 53-61

Object level deep feature pooling for compact image representation (Abstract)

Konda Reddy Mopuri , Video Analytics Lab, SERC, Indian Institute of Science, Bangalore, India
R. Venkatesh Babu , Video Analytics Lab, SERC, Indian Institute of Science, Bangalore, India
pp. 62-70

Multi-scale pyramid pooling for deep convolutional representation (Abstract)

Donggeun Yoo , KAIST, Daejeon, 305-701, Korea
Sunggyun Park , KAIST, Daejeon, 305-701, Korea
Joon-Young Lee , KAIST, Daejeon, 305-701, Korea
In So Kweon , KAIST, Daejeon, 305-701, Korea
pp. 71-80

Color constancy using CNNs (Abstract)

Simone Bianco , University of Milan-Bicocca, Italy
Claudio Cusano , University of Pavia, Italy
Raimondo Schettini , University of Milan-Bicocca, Italy
pp. 81-89

Learning to count with deep object features (Abstract)

Santi Segui , Dept. Matematica Aplicada i Analisis, Universitat de Barcelona, Spain
Oriol Pujol , Dept. Matematica Aplicada i Analisis, Universitat de Barcelona, Spain
Jordi Vitria , Dept. Matematica Aplicada i Analisis, Universitat de Barcelona, Spain
pp. 90-96

Walking and talking: A bilinear approach to multi-label action recognition (Abstract)

Sameh Khamis , University of Maryland, College Park, 20742, United States
Larry S. Davis , University of Maryland, College Park, 20742, United States
pp. 1-8

Discovering human interactions in videos with limited data labeling (Abstract)

Mehran Khodabandeh , Simon Fraser University, Burnaby, BC, Canada
Arash Vahdat , Simon Fraser University, Burnaby, BC, Canada
Guang-Tong Zhou , Simon Fraser University, Burnaby, BC, Canada
Hossein Hajimirsadeghi , Simon Fraser University, Burnaby, BC, Canada
Mehrsan Javan Roshtkhari , McGill University, Montreal, QC, Canada
Greg Mori , Simon Fraser University, Burnaby, BC, Canada
Stephen Se , MDA Corporation, Richmond, BC, Canada
pp. 9-18

MuseumVisitors: A dataset for pedestrian and group detection, gaze estimation and behavior understanding (Abstract)

Federico Bartoli , University of Florence, 50121 Firenze, Italy
Giuseppe Lisanti , University of Florence, 50121 Firenze, Italy
Lorenzo Seidenari , University of Florence, 50121 Firenze, Italy
Svebor Karaman , University of Florence, 50121 Firenze, Italy
Alberto Del Bimbo , University of Florence, 50121 Firenze, Italy
pp. 19-27

Subject centric group feature for person re-identification (Abstract)

Li Wei , Quantitative Imaging Laboratory, Department of Computer Science, University of Houston, TX 77204-3010, U.S.A.
Shishir K. Shah , Quantitative Imaging Laboratory, Department of Computer Science, University of Houston, TX 77204-3010, U.S.A.
pp. 28-35

The GRODE metrics: Exploring the performance of group detection approaches (Abstract)

Francesco Setti , ISTC - CNR, via alla Cascata 56/C, I-38121 Trento, Italy
Marco Cristani , University of Verona, Strada Le Grazie 2, I-37134, Italy
pp. 36-42

Learning to identify leaders in crowd (Abstract)

Francesco Solera , University of Modena and Reggio Emilia, 41121 MO, Italy
Simone Calderara , University of Modena and Reggio Emilia, 41121 MO, Italy
Rita Cucchiara , University of Modena and Reggio Emilia, 41121 MO, Italy
pp. 43-48

A comparison of crowd commotion measures from generative models (Abstract)

Sadegh Mohammadi , Pattern Analysis and Computer Vision Department (PAVIS), Istituto Italiano di Tecnologia, Genova, Italy
Hamed Kiani , Pattern Analysis and Computer Vision Department (PAVIS), Istituto Italiano di Tecnologia, Genova, Italy
Alessandro Perina , Pattern Analysis and Computer Vision Department (PAVIS), Istituto Italiano di Tecnologia, Genova, Italy
Vittorio Murino , Pattern Analysis and Computer Vision Department (PAVIS), Istituto Italiano di Tecnologia, Genova, Italy
pp. 49-55

Real-time anomaly detection and localization in crowded scenes (Abstract)

Mohammad Sabokrou , Malek Ashtar University of Technology, Tehran, Iran
Mahmood Fathy , Iran University of Science and Technology, Tehran, Iran
Mojtaba Hoseini , Malek Ashtar University of Technology, Tehran, Iran
Reinhard Klette , Auckland University of Technology, New Zealand
pp. 56-62

Dominant flow extraction and analysis in traffic surveillance videos (Abstract)

Srinivas S S Kruthiventi , Video Analytics Lab, SERC, Indian Institute of Science, Bangalore, India
R. Venkatesh Babu , Video Analytics Lab, SERC, Indian Institute of Science, Bangalore, India
pp. 63-71

3D human motion capture from monocular image sequences (Abstract)

Bastian Wandt , Leibniz University Hannover, Germany
Hanno Ackermann , Leibniz University Hannover, Germany
Bodo Rosenhahn , Leibniz University Hannover, Germany
pp. 1-8

Multinomial processing models in visual cognitive effort diagnostics (Abstract)

Joshua D. Elkins , IUPUI, 420 University Blvd., Indianapolis, IN 46202, United States
Gahangir Hossain , IUPUI, 420 University Blvd., Indianapolis, IN 46202, United States
pp. 9-15

Action classification in still images using human eye movements (Abstract)

Gary Ge , Ward Melville High School, East Setauket, NY 11733, USA
Kiwon Yun , Stony Brook University, NY 11794, USA
Dimitris Samaras , Stony Brook University, NY 11794, USA
Gregory J. Zelinsky , Stony Brook University, NY 11794, USA
pp. 16-23

Semantically-enriched 3D models for common-sense knowledge (Abstract)

Manolis Savva , Computer Science Department, Stanford University, California 94305, United States
Angel X. Chang , Computer Science Department, Stanford University, California 94305, United States
Pat Hanrahan , Computer Science Department, Stanford University, California 94305, United States
pp. 24-31

Comparison of infrared and visible imagery for object tracking: Toward trackers with superior IR performance (Abstract)

Erhan Gundogdu , Electro-Optics System Design Department, MGEO, ASELSAN Inc., Ankara, Turkey
Huseyin Ozkan , Electro-Optics System Design Department, MGEO, ASELSAN Inc., Ankara, Turkey
H. Seckin Demir , Electro-Optics System Design Department, MGEO, ASELSAN Inc., Ankara, Turkey
Hamza Ergezer , Electro-Optics System Design Department, MGEO, ASELSAN Inc., Ankara, Turkey
Erdem Akagunduz , Electro-Optics System Design Department, MGEO, ASELSAN Inc., Ankara, Turkey
S. Kubilay Pakin , Electro-Optics System Design Department, MGEO, ASELSAN Inc., Ankara, Turkey
pp. 1-9

VAIS: A dataset for recognizing maritime imagery in the visible and infrared spectrums (Abstract)

Mabel M. Zhang , University of Pennsylvania, Philadelphia, 19104, United States
Jean Choi , Gwangju Institute of Science and Technology, Buk-gu, South Korea
Kostas Daniilidis , University of Pennsylvania, Philadelphia, 19104, United States
Michael T. Wolf , Jet Propulsion Laboratory, California Institute of Technology, Pasadena, 91109, United States
Christopher Kanan , Jet Propulsion Laboratory, California Institute of Technology, Pasadena, 91109, United States
pp. 10-16

A comparison of stereo and multiview 3-D reconstruction using cross-sensor satellite imagery (Abstract)

Ozge C. Ozcanli , Vision Systems Inc., Providence, RI, United States
Yi Dong , Vision Systems Inc., Providence, RI, United States
Joseph L. Mundy , Vision Systems Inc., Providence, RI, United States
Helen Webb , BAE Systems, Burlington, MA, United States
Riad Hammoud , BAE Systems, Burlington, MA, United States
Victor Tom , BAE Systems, Burlington, MA, United States
pp. 17-25

Online multimodal video registration based on shape matching (Abstract)

Pierre-Luc St-Charles , LITIV lab., Dept. of Computer & Software Eng., Polytechnique Montréal, QC, Canada
Guillaume-Alexandre Bilodeau , LITIV lab., Dept. of Computer & Software Eng., Polytechnique Montréal, QC, Canada
Robert Bergevin , LVSN - REPARTI, Université Laval, Québec City, Canada
pp. 26-34

Automated feature weighting and random pixel sampling in k-means clustering for terahertz image segmentation (Abstract)

Mohamed Walid Ayech , Department of Computer Science, University of Sherbrooke, J1K 2R1, Québec, Canada
Djemel Ziou , Department of Computer Science, University of Sherbrooke, J1K 2R1, Québec, Canada
pp. 35-40

A model-based approach to finding tracks in SAR CCD images (Abstract)

Tu-Thach Quach , Sandia National Laboratories, Albuquerque, NM 87185-1163, United States
Rebecca Malinas , Sandia National Laboratories, Albuquerque, NM 87185-1163, United States
Mark W. Koch , Sandia National Laboratories, Albuquerque, NM 87185-1163, United States
pp. 41-47

Efficient person re-identification by hybrid spatiogram and covariance descriptor (Abstract)

Mingyong Zeng , College of Communications Engineering, PLA University of Science and Technology, Nanjing 210007, China
Zemin Wu , College of Communications Engineering, PLA University of Science and Technology, Nanjing 210007, China
Chang Tian , College of Communications Engineering, PLA University of Science and Technology, Nanjing 210007, China
Lei Zhang , College of Communications Engineering, PLA University of Science and Technology, Nanjing 210007, China
Lei Hu , College of Communications Engineering, PLA University of Science and Technology, Nanjing 210007, China
pp. 48-56

Articulated Gaussian kernel correlation for human pose estimation (Abstract)

Meng Ding , School of Electrical and Computer Engineering, Oklahoma State University, Stillwater, USA 74074
Guoliang Fan , School of Electrical and Computer Engineering, Oklahoma State University, Stillwater, USA 74074
pp. 57-64

Automation of dormant pruning in specialty crop production: An adaptive framework for automatic reconstruction and modeling of apple trees (Abstract)

Noha M. Elfiky , Purdue University School of Electrical and Computer Engineering, Electrical Engineering Building, 475 Northwestern Ave, West Lafayette, IN 47907, United States
Shayan A. Akbar , Purdue University School of Electrical and Computer Engineering, Electrical Engineering Building, 475 Northwestern Ave, West Lafayette, IN 47907, United States
Jianxin Sun , Purdue University School of Electrical and Computer Engineering, Electrical Engineering Building, 475 Northwestern Ave, West Lafayette, IN 47907, United States
Johnny Park , Purdue University School of Electrical and Computer Engineering, Electrical Engineering Building, 475 Northwestern Ave, West Lafayette, IN 47907, United States
Avinash Kak , Purdue University School of Electrical and Computer Engineering, Electrical Engineering Building, 475 Northwestern Ave, West Lafayette, IN 47907, United States
pp. 65-73

A cloud infrastructure for target detection and tracking using audio and video fusion (Abstract)

Kui Liu , Intelligent Fusion Technology, Germantown, MD 20876, United States
Bingwei Liu , Binghamton University, NY 13902, United States
Erik Blasch , Air Force Research Laboratory, Rome, NY, 13441, United States
Dan Shen , Intelligent Fusion Technology, Germantown, MD 20876, United States
Zhonghai Wang , Intelligent Fusion Technology, Germantown, MD 20876, United States
Haibin Ling , Temple University, Philadelphia, PA 19122, United States
Genshe Chen , Intelligent Fusion Technology, Germantown, MD 20876, United States
pp. 74-81

Make my day - high-fidelity color denoising with Near-Infrared (Abstract)

Hiroto Honda , Toshiba Corp., Kawasaki, Japan
Radu Timofte , Computer Vision Lab, ETH Zurich, Switzerland
Luc Van Gool , KU Leuven, Belgium
pp. 82-90

USDOT number localization and recognition from vehicle side-view NIR images (Abstract)

Orhan Bulan , Palo Alto Research Center (PARC), 800 Phillips Rd. Webster NY 14580, United States
Safwan Wshah , Palo Alto Research Center (PARC), 800 Phillips Rd. Webster NY 14580, United States
Ramesh Palghat , Palo Alto Research Center (PARC), 800 Phillips Rd. Webster NY 14580, United States
Vladimir Kozitsky , Palo Alto Research Center (PARC), 800 Phillips Rd. Webster NY 14580, United States
Aaron Burry , Palo Alto Research Center (PARC), 800 Phillips Rd. Webster NY 14580, United States
pp. 91-96

Robust object recognition in RGB-D egocentric videos based on Sparse Affine Hull Kernel (Abstract)

Shaohua Wan , Dept. of Electrical and Computer Engineering, The University of Texas at Austin, United States
J.K. Aggarwal , Dept. of Electrical and Computer Engineering, The University of Texas at Austin, United States
pp. 97-104

Improving superpixel boundaries using information beyond the visual spectrum (Abstract)

Keith Sullivan , Exelis, Inc., McLean, VA USA
Wallace Lawson , Naval Research Laboratory, Washington, DC USA
Donald Sofge , Naval Research Laboratory, Washington, DC USA
pp. 105-112

A simply integrated dual-sensor based non-intrusive iris image acquisition system (Abstract)

Jang-Hee Yoo , SW·Content Research Laboratory, ETRI, Daejeon, S. Korea
Byung Jun Kang , Technical Research Institute, Hyundai Mobis, Gyeonggi, S. Korea
pp. 113-117

Heterogeneous structure fusion for Target Recognition in infrared imagery (Abstract)

Guangfeng Lin , Department of Information Science, Xi'an University of Technology, Shaanxi, China
Guoliang Fan , School of Electrical and Computer Engineering, Oklahoma State University, Stillwater, USA
Liangjiang Yu , School of Electrical and Computer Engineering, Oklahoma State University, Stillwater, USA
Xiaobing Kang , Department of Information Science, Xi'an University of Technology, Shaanxi, China
Erhu Zhang , Department of Information Science, Xi'an University of Technology, Shaanxi, China
pp. 118-125

Non-rigid articulated point set registration with Local Structure Preservation (Abstract)

Song Ge , School of Electrical and Computer Engineering, Oklahoma State University, Stillwater, 74078, United States
Guoliang Fan , School of Electrical and Computer Engineering, Oklahoma State University, Stillwater, 74078, United States
pp. 126-133

Sonar automatic target recognition for underwater UXO remediation (Abstract)

Jason C. Isaacs , Naval Surface Warfare Center, Panama City, FL USA
pp. 134-140

NIR-VIS heterogeneous face recognition via cross-spectral joint dictionary learning and reconstruction (Abstract)

Felix Juefei-Xu , CyLab Biometrics Center, Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Dipan K. Pal , CyLab Biometrics Center, Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Marios Savvides , CyLab Biometrics Center, Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA
pp. 141-150

Road segmentation using multipass single-pol synthetic aperture radar imagery (Abstract)

Mark W. Koch , Sandia National Laboratories, Albuquerque, NM 87185-1163, United States
Mary M. Moya , Sandia National Laboratories, Albuquerque, NM 87185-1163, United States
Jim G. Chow , Sandia National Laboratories, Albuquerque, NM 87185-1163, United States
Jeremy Goold , Sandia National Laboratories, Albuquerque, NM 87185-1163, United States
Rebecca Malinas , Sandia National Laboratories, Albuquerque, NM 87185-1163, United States
pp. 151-160

From photography to microbiology: Eigenbiome models for skin appearance (Abstract)

Parneet Kaur , Rutgers University, New Brunswick, NJ 08901, United States
Kristin J. Dana , Rutgers University, New Brunswick, NJ 08901, United States
Gabriela Oana Cula , Johnson & Johnson, New Brunswick, New Jersey, United States
pp. 1-10

Fast registration of segmented images by normal sampling (Abstract)

Jan Kybic , Faculty of Electrical Engineering, Czech Technical University in Prague, 166 36 Praha 6, Czech Republic
pp. 11-19

Deep neural networks for anatomical brain segmentation (Abstract)

Alexandre de Brebisson , Department of Mathematics, Imperial College London, SW7 2AZ, UK
Giovanni Montana , Department of Biomedical Engineering, King's College London, St Thomas' Hospital, SE1 7EH, UK
pp. 20-28

TAEF: A cross-distance/environment face recognition method (Abstract)

Chun-Ting Huang , University of Southern California, Los Angeles, United States
Zhengning Wang , University of Electronic Science and Technology of China, China
C.-C. Jay Kuo , University of Southern California, Los Angeles, United States
pp. 1-8

Perspective distortion modeling, learning and compensation (Abstract)

Joachim Valente , Google, Mountain View, CA, United States
Stefano Soatto , UCLA Vision Lab, University of California, Los Angeles, United States
pp. 9-16

Locality-constrained discriminative learning and coding (Abstract)

Shuyang Wang , Department of Electrical & Computer Engineering, Northeastern University, Boston, MA, USA
Yun Fu , Department of Electrical & Computer Engineering, Northeastern University, Boston, MA, USA
pp. 17-24

A preliminary investigation on the sensitivity of COTS face recognition systems to forensic analyst-style face processing for occlusions (Abstract)

Felix Juefei-Xu , CyLab Biometrics Center, Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Dipan K. Pal , CyLab Biometrics Center, Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Karanhaar Singh , CyLab Biometrics Center, Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Marios Savvides , CyLab Biometrics Center, Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA
pp. 25-33

Exploratory analysis of an operational iris recognition dataset from a CBSA border-crossing application (Abstract)

Estefan Ortiz , Department of Computer Science & Engineering, University of Notre Dame, Indiana 46556, United States
Kevin W. Bowyer , Department of Computer Science & Engineering, University of Notre Dame, Indiana 46556, United States
pp. 34-41

Evaluation of combined visible/NIR camera for iris authentication on smartphones (Abstract)

Shejin Thavalengal , FotoNation Ltd, Galway, Ireland
Petronel Bigioi , FotoNation Ltd, Galway, Ireland
Peter Corcoran , National University of Ireland Galway, Ireland
pp. 42-49

A preliminary study on identifying sensors from iris images (Abstract)

Nathan Kalka , Noblis, Falls Church, Virginia, United States
Nick Bartlow , Noblis, Falls Church, Virginia, United States
Bojan Cukic , University of North Carolina, Charlotte, United States
Arun Ross , Michigan State University, East Lansing, 48824, United States
pp. 50-56

The emperor's new masks: On demographic differences and disguises (Abstract)

Katherine L. Gibson , CIS Department, University of Pennsylvania, United States
Jonathan M. Smith , CIS Department, University of Pennsylvania, United States
pp. 57-64

Latent max-margin metric learning for comparing video face tubes (Abstract)

Gaurav Sharma , MPI Informatics, Germany
Patrick Perez , Technicolor, Paris, France
pp. 65-74

Unsupervised learning of overcomplete face descriptors (Abstract)

Juha Ylioinas , Center for Machine Vision Research, University of Oulu, 90014, Finland
Juho Kannala , Center for Machine Vision Research, University of Oulu, 90014, Finland
Abdenour Hadid , Center for Machine Vision Research, University of Oulu, 90014, Finland
Matti Pietikainen , Center for Machine Vision Research, University of Oulu, 90014, Finland
pp. 75-83

Person identification from action styles (Abstract)

Igor Kviatkovsky , Technion, Haifa, Israel
Ilan Shimshoni , The University of Haifa, Haifa, Israel
Ehud Rivlin , Technion, Haifa, Israel
pp. 84-92

A facial features detector integrating holistic facial information and part-based model (Abstract)

Eslam Mostafa , CVIP Lab, University of Louisville, KY 40292, USA
Asem A. Ali , Electrical Engineering Department, Assiut University, 71515, Egypt
Ahmed Shalaby , Kentucky Imaging Technology (KIT), Louisville, 40245, USA
Aly Farag , CVIP Lab, University of Louisville, KY 40292, USA
pp. 93-99

Genetic algorithm attack on minutiae-based fingerprint authentication and protected template fingerprint systems (Abstract)

Andras Rozsa , University of Colorado, Colorado Springs, USA
Albert E. Glock , University of Colorado, Colorado Springs, USA
Terrance E. Boult , University of Colorado, Colorado Springs, USA
pp. 100-108

Electromyograph and keystroke dynamics for spoof-resistant biometric authentication (Abstract)

Shreyas Venugopalan , CyLab Biometrics Center, Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Felix Juefei-Xu , CyLab Biometrics Center, Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Benjamin Cowley , CyLab Biometrics Center, Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Marios Savvides , CyLab Biometrics Center, Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA
pp. 109-118

A multiple server scheme for fingerprint fuzzy vaults (Abstract)

Jesse Hartloff , University at Buffalo, SUNY, NY, USA
Matthew Morse , University at Buffalo, SUNY, NY, USA
Bingsheng Zhang , National and Kapodistrian University of Athens, Greece
Thomas Effland , University at Buffalo, SUNY, NY, USA
Jennifer Cordaro , University at Buffalo, SUNY, NY, USA
Jim Schuler , University at Buffalo, SUNY, NY, USA
Sergey Tulyakov , University at Buffalo, SUNY, NY, USA
Atri Rudra , University at Buffalo, SUNY, NY, USA
Venu Govindaraju , University at Buffalo, SUNY, NY, USA
pp. 119-127

Pore-based ridge reconstruction for fingerprint recognition (Abstract)

Mauricio Pamplona Segundo , Intelligent Vision Research Lab, Department of Computer Science, Federal University of Bahia, Brazil
Rubisley de Paula Lemes , Intelligent Vision Research Lab, Department of Computer Science, Federal University of Bahia, Brazil
pp. 128-133

ChaLearn Looking at People 2015 challenges: Action spotting and cultural event recognition (Abstract)

Xavier Baro , Universitat Oberta de Catalunya - CVC, Spain
Jordi Gonzalez , Computer Vision Center (UAB), Spain
Junior Fabian , Computer Vision Center (UAB), Spain
Miguel A. Bautista , Universitat de Barcelona, Spain
Marc Oliu , Universitat de Barcelona, Spain
Hugo Jair Escalante , INAOE, Mexico
Isabelle Guyon , Chalearn, Berkeley, California, USA
Sergio Escalera , Universitat de Barcelona - CVC, Spain
pp. 1-9

Exploring Fisher vector and deep networks for action spotting (Abstract)

Zhe Wang , Shenzhen key lab of Comp. Vis. & Pat. Rec., Shenzhen Institutes of Advanced Technology, CAS, China
Limin Wang , Shenzhen key lab of Comp. Vis. & Pat. Rec., Shenzhen Institutes of Advanced Technology, CAS, China
Wenbin Du , Shenzhen key lab of Comp. Vis. & Pat. Rec., Shenzhen Institutes of Advanced Technology, CAS, China
Yu Qiao , Shenzhen key lab of Comp. Vis. & Pat. Rec., Shenzhen Institutes of Advanced Technology, CAS, China
pp. 10-14

Applying action attribute class validation to improve human activity recognition (Abstract)

David Tahmoush , US Army Research Laboratory, 2800 Powder Mill Rd, Adelphi MD, United States
pp. 15-21

Keep it accurate and diverse: Enhancing action recognition performance by ensemble learning (Abstract)

Mohammad Ali Bagheri , Faculty of Computer Science, Dalhousie University, Halifax, Canada
Qigang Gao , Faculty of Computer Science, Dalhousie University, Halifax, Canada
Sergio Escalera , Computer Vision Center, UAB, Edificio O, Campus UAB, 08193, Bellaterra (Cerdanyola), Barcelona, Spain
Albert Clapes , Computer Vision Center, UAB, Edificio O, Campus UAB, 08193, Bellaterra (Cerdanyola), Barcelona, Spain
Kamal Nasrollahi , Visual Analysis of People (VAP) Laboratory, Rendsburggade 14, 9000 Aalborg, Denmark
Michael B. Holte , Visual Analysis of People (VAP) Laboratory, Rendsburggade 14, 9000 Aalborg, Denmark
Thomas B. Moeslund , Visual Analysis of People (VAP) Laboratory, Rendsburggade 14, 9000 Aalborg, Denmark
pp. 22-29

Object-Scene Convolutional Neural Networks for event recognition in images (Abstract)

Limin Wang , Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong
Zhe Wang , Shenzhen key lab of Comp. Vis. & Pat. Rec., Shenzhen Institutes of Advanced Technology, CAS, China
Wenbin Du , Shenzhen key lab of Comp. Vis. & Pat. Rec., Shenzhen Institutes of Advanced Technology, CAS, China
Yu Qiao , Shenzhen key lab of Comp. Vis. & Pat. Rec., Shenzhen Institutes of Advanced Technology, CAS, China
pp. 30-35

Cultural Event recognition with visual ConvNets and temporal models (Abstract)

Amaia Salvador , Universitat Politecnica de Catalunya (UPC), Barcelona, Catalonia/Spain
Daniel Manchon-Vizuete , Universitat Politecnica de Catalunya (UPC), Barcelona, Catalonia/Spain
Andrea Calafell , Universitat Politecnica de Catalunya (UPC), Barcelona, Catalonia/Spain
Xavier Giro-i-Nieto , Universitat Politecnica de Catalunya (UPC), Barcelona, Catalonia/Spain
Matthias Zeppelzauer , St. Poelten University of Applied Sciences, Austria
pp. 36-44

Cultural event recognition by subregion classification with convolutional neural network (Abstract)

Sungheon Park , Graduate School of CST, Seoul National University, Korea
Nojun Kwak , Graduate School of CST, Seoul National University, Korea
pp. 45-50

Recognizing cultural events in images: A study of image categorization models (Abstract)

Heeyoung Kwon , Stony Brook University, NY 11794-4400, United States
Kiwon Yun , Stony Brook University, NY 11794-4400, United States
Minh Hoai , Stony Brook University, NY 11794-4400, United States
Dimitris Samaras , Stony Brook University, NY 11794-4400, United States
pp. 51-57

Articulated pose estimation with tiny synthetic videos (Abstract)

Dennis Park , UC Irvine, CA 92697, United States
Deva Ramanan , UC Irvine, CA 92697, United States
pp. 58-66

A semantic occlusion model for human pose estimation from a single depth image (Abstract)

Umer Rafi , RWTH Aachen University, Germany
Juergen Gall , University of Bonn, Germany
Bastian Leibe , RWTH Aachen University, Germany
pp. 67-74

A new retexturing method for virtual fitting room using Kinect 2 camera (Abstract)

Andres Traumann , iCV Group, IMS Lab, Institute of Technology, University of Tartu, 50411, Estonia
Gholamreza Anbarjafari , iCV Group, IMS Lab, Institute of Technology, University of Tartu, 50411, Estonia
Sergio Escalera , Computer Vision Center, Universitat de Barcelona, Spain
pp. 75-79

Pain recognition using spatiotemporal oriented energy of facial muscles (Abstract)

Ramin Irani , Visual Analysis of People (VAP) Laboratory, Rendsburggade 14, 9000 Aalborg, Denmark
Kamal Nasrollahi , Visual Analysis of People (VAP) Laboratory, Rendsburggade 14, 9000 Aalborg, Denmark
Thomas B. Moeslund , Visual Analysis of People (VAP) Laboratory, Rendsburggade 14, 9000 Aalborg, Denmark
pp. 80-87

Spatiotemporal analysis of RGB-D-T facial images for multimodal pain level recognition (Abstract)

Ramin Irani , Visual Analysis of People (VAP) Laboratory, Rendsburggade 14, 9000 Aalborg, Denmark
Kamal Nasrollahi , Visual Analysis of People (VAP) Laboratory, Rendsburggade 14, 9000 Aalborg, Denmark
Marc O. Simon , Computer Vision Center, UAB, Edificio O, Campus UAB, 08193, Bellaterra (Cerdanyola), Barcelona, Spain
Ciprian A. Corneanu , Computer Vision Center, UAB, Edificio O, Campus UAB, 08193, Bellaterra (Cerdanyola), Barcelona, Spain
Sergio Escalera , Computer Vision Center, UAB, Edificio O, Campus UAB, 08193, Bellaterra (Cerdanyola), Barcelona, Spain
Chris Bahnsen , Visual Analysis of People (VAP) Laboratory, Rendsburggade 14, 9000 Aalborg, Denmark
Dennis H. Lundtoft , Visual Analysis of People (VAP) Laboratory, Rendsburggade 14, 9000 Aalborg, Denmark
Thomas B. Moeslund , Visual Analysis of People (VAP) Laboratory, Rendsburggade 14, 9000 Aalborg, Denmark
Tanja L. Pedersen , Dept. of Communication and Psychology, Fredrik Bajers Vej 7, 9220 Aalborg, Denmark
Maria-Louise Klitgaard , Dept. of Communication and Psychology, Fredrik Bajers Vej 7, 9220 Aalborg, Denmark
Laura Petrini , Dept. of Communication and Psychology, Fredrik Bajers Vej 7, 9220 Aalborg, Denmark
pp. 88-95

Hand gesture recognition with 3D convolutional neural networks (Abstract)

Pavlo Molchanov , NVIDIA, Santa Clara, California, USA
Shalini Gupta , NVIDIA, Santa Clara, California, USA
Kihwan Kim , NVIDIA, Santa Clara, California, USA
Jan Kautz , NVIDIA, Santa Clara, California, USA
pp. 1-7

Hierarchical particle filtering for 3D hand tracking (Abstract)

Alexandros Makris , Institute of Computer Science, FORTH, Greece
Nikolaos Kyriazis , Institute of Computer Science, FORTH, Greece
Antonis A. Argyros , Institute of Computer Science, FORTH, Greece
pp. 8-17

On-the-fly hand detection training with application in egocentric action recognition (Abstract)

Jayant Kumar , PARC, A Xerox Company, 800 Phillips Road, Webster, NY 14580, United States
Qun Li , PARC, A Xerox Company, 800 Phillips Road, Webster, NY 14580, United States
Survi Kyal , PARC, A Xerox Company, 800 Phillips Road, Webster, NY 14580, United States
Edgar A. Bernal , PARC, A Xerox Company, 800 Phillips Road, Webster, NY 14580, United States
Raja Bala , PARC, A Xerox Company, 800 Phillips Road, Webster, NY 14580, United States
pp. 18-27

ICPIK: Inverse Kinematics based articulated-ICP (Abstract)

Shachar Fleishman , Intel, Santa Clara, California, United States
Mark Kliger , Intel, Santa Clara, California, United States
Alon Lerner , Intel, Santa Clara, California, United States
Gershom Kutliroff , Intel, Santa Clara, California, United States
pp. 28-35

Mining discriminative states of hands and objects to recognize egocentric actions with a wearable RGBD camera (Abstract)

Shaohua Wan , Dept. of Electrical and Computer Engineering, The University of Texas at Austin, United States
J.K. Aggarwal , Dept. of Electrical and Computer Engineering, The University of Texas at Austin, United States
pp. 36-43

American Sign Language alphabet recognition using Microsoft Kinect (Abstract)

Cao Dong , Missouri University of Science and Technology, Rolla, 65409, United States
Ming C. Leu , Missouri University of Science and Technology, Rolla, 65409, United States
Zhaozheng Yin , Missouri University of Science and Technology, Rolla, 65409, United States
pp. 44-52

Towards robust cascaded regression for face alignment in the wild (Abstract)

Chengchao Qu , Vision and Fusion Laboratory (IES), Karlsruhe Institute of Technology (KIT), Germany
Hua Gao , Signal Processing Laboratory (LTS5), École Polytechnique Fédérale de Lausanne (EPFL), Switzerland
Eduardo Monari , Fraunhofer Institute of Optronics, System Technologies and Image Exploitation (Fraunhofer IOSB), Germany
Jurgen Beyerer , Fraunhofer Institute of Optronics, System Technologies and Image Exploitation (Fraunhofer IOSB), Germany
Jean-Philippe Thiran , Signal Processing Laboratory (LTS5), École Polytechnique Fédérale de Lausanne (EPFL), Switzerland
pp. 1-9

Multi-observation face recognition in videos based on label propagation (Abstract)

Bogdan Raducanu , Computer Vision Center, Edifici “O” - Campus UAB, 01893 Bellaterra (Barcelona), SPAIN
Alireza Bosaghzadeh , University of the Basque Country UPV/EHU, San Sebastian, Spain
Fadi Dornaika , University of the Basque Country UPV/EHU, San Sebastian, Spain
pp. 10-17

Exemplar Hidden Markov Models for classification of facial expressions in videos (Abstract)

Karan Sikka , Univ. of California San Diego, USA
Abhinav Dhall , Univ. of Canberra, Australian National University, Australia
Marian Bartlett , Univ. of California San Diego, USA
pp. 18-25

Using Hankel matrices for dynamics-based facial emotion recognition and pain detection (Abstract)

Liliana Lo Presti , DICGIM - University of Palermo, V.le delle Scienze, Ed. 6, 90128 (Italy)
Marco La Cascia , DICGIM - University of Palermo, V.le delle Scienze, Ed. 6, 90128 (Italy)
pp. 26-33

Age and gender classification using convolutional neural networks (Abstract)

Gil Levi , Department of Mathematics and Computer Science, The Open University of Israel, Israel
Tal Hassncer , Department of Mathematics and Computer Science, The Open University of Israel, Israel
pp. 34-42

FAME: Face Association through Model Evolution (Abstract)

Eren Golge , Bilkent University, Department of Computer Engineering, Ankara, Turkey, 06800
Pinar Duygulu , Bilkent University, Department of Computer Engineering, Ankara, Turkey, 06800
pp. 43-49

Head pose estimation in the wild using approximate view manifolds (Abstract)

Kalaivani Sundararajan , University of Florida, Gainesville, USA
Damon L. Woodard , University of Florida, Gainesville, USA
pp. 50-58

Mixture of parts revisited: Expressive part interactions for Pose Estimation (Abstract)

Anoop R Katti , IIT Madras, Chennai, India
Anurag Mittal , IIT Madras, Chennai, India
pp. 59-67

Towards privacy-preserving activity recognition using extremely low temporal and spatial resolution cameras (Abstract)

Ji Dai , Department of Electrical and Computer Engineering, Boston University, 8 Saint Mary's Street, MA, 02215, United States
Jonathan Wu , Department of Electrical and Computer Engineering, Boston University, 8 Saint Mary's Street, MA, 02215, United States
Behrouz Saghafi , Department of Electrical and Computer Engineering, Boston University, 8 Saint Mary's Street, MA, 02215, United States
Janusz Konrad , Department of Electrical and Computer Engineering, Boston University, 8 Saint Mary's Street, MA, 02215, United States
Prakash Ishwar , Department of Electrical and Computer Engineering, Boston University, 8 Saint Mary's Street, MA, 02215, United States
pp. 68-76

Sparse Coding Trees with application to emotion classification (Abstract)

Hsieh-Chung Chen , Harvard University, Cambridge, MA, United States
Marcus Z. Comiter , Harvard University, Cambridge, MA, United States
H. T. Kung , Harvard University, Cambridge, MA, United States
Bradley McDanel , Harvard University, Cambridge, MA, United States
pp. 77-86

3D object class detection in the wild (Abstract)

Bojan Pepik , Max Planck Institute for Informatics, 66123 Saarbrücken, Germany
Michael Stark , Max Planck Institute for Informatics, 66123 Saarbrücken, Germany
Peter Gehler , Max Planck Institute for Intelligent Systems, 70569 Stuttgart, Germany
Tobias Ritschel , Max Planck Institute for Informatics, 66123 Saarbrücken, Germany
Bernt Schiele , Max Planck Institute for Informatics, 66123 Saarbrücken, Germany
pp. 1-10

On-board real-time tracking of pedestrians on a UAV (Abstract)

Floris De Smedt , ESAT-PSI-VISICS, KU Leuven, Belgium
Dries Hulens , ESAT-PSI-VISICS, KU Leuven, Belgium
Toon Goedeme , ESAT-PSI-VISICS, KU Leuven, Belgium
pp. 1-8

Guidance: A visual sensing platform for robotic applications (Abstract)

Guyue Zhou , Dajiang Innovations Technology Co., Ltd., Shenzhen, China
Lu Fang , University of Science and Technology of China, China
Ketan Tang , Dajiang Innovations Technology Co., Ltd., Shenzhen, China
Honghui Zhang , Dajiang Innovations Technology Co., Ltd., Shenzhen, China
Kai Wang , Dajiang Innovations Technology Co., Ltd., Shenzhen, China
Kang Yang , Dajiang Innovations Technology Co., Ltd., Shenzhen, China
pp. 9-14

Off-the-shelf sensor integration for mono-SLAM on smart devices (Abstract)

Philipp Tiefenbacher , Technische Universität München, Germany
Timo Schulze , Technische Universität München, Germany
Gerhard Rigoll , Technische Universität München, Germany
pp. 15-20

Retrieving gray-level information from a Binary Sensor and its application to gesture detection (Abstract)

Orazio Gallo , NVIDIA, Santa Clara, California, United States
Iuri Frosio , NVIDIA, Santa Clara, California, United States
Leonardo Gasparini , Center for Materials & Microsystems, Fondazione Bruno Kessler, 38122 Trento, Italy
Kari Pulli , NVIDIA, Santa Clara, California, United States
Massimo Gottardi , Center for Materials & Microsystems, Fondazione Bruno Kessler, 38122 Trento, Italy
pp. 21-26

Recursive edge-aware filters for stereo matching (Abstract)

Cevahir Cigla , Aselsan Inc., Ankara/Turkey
pp. 27-34

A real-time high dynamic range HD video camera (Abstract)

Rajesh Narasimha , Samsung Research America, 1301 East Lookout Drive | Richardson, TX 75082, United States
Umit Batur , Perception and Analytics Lab, Texas Instruments Inc., United States
pp. 35-41

FPGA acceleration for feature based processing applications (Abstract)

Gooitzen van der Wal , SRI International, Princeton, NJ, United States
David Zhang , SRI International, Princeton, NJ, United States
Indu Kandaswamy , SRI International, Princeton, NJ, United States
James Marakowitz , SRI International, Princeton, NJ, United States
Kevin Kaighn , SRI International, Princeton, NJ, United States
Joe Zhang , SRI International, Princeton, NJ, United States
Sek Chai , SRI International, Princeton, NJ, United States
pp. 42-47

Locally non-rigid registration for mobile HDR photography (Abstract)

Orazio Gallo , NVIDIA, Santa Clara, California, United States
Alejandro Troccoli , NVIDIA, Santa Clara, California, United States
Jun Hu , NVIDIA, Santa Clara, California, United States
Kari Pulli , NVIDIA, Santa Clara, California, United States
Jan Kautz , NVIDIA, Santa Clara, California, United States
pp. 48-55

Real-time embedded age and gender classification in unconstrained video (Abstract)

Ramin Azarmehr , School of Electrical Engineering and Computer Science, University of Ottawa, ON K1N 6N5 Canada
Robert Laganiere , School of Electrical Engineering and Computer Science, University of Ottawa, ON K1N 6N5 Canada
Won-Sook Lee , School of Electrical Engineering and Computer Science, University of Ottawa, ON K1N 6N5 Canada
Christina Xu , CogniVue Corporation, Gatineau, QC, Canada
Daniel Laroche , CogniVue Corporation, Gatineau, QC, Canada
pp. 56-64

FPGA-based pedestrian detection under strong distortions (Abstract)

D. Tasson , eVS embedded Vision Systems srl, c/o Computer Science Park, Strada Le Grazie, 15 Verona, Italy
A. Montagnini , eVS embedded Vision Systems srl, c/o Computer Science Park, Strada Le Grazie, 15 Verona, Italy
R. Marzotto , eVS embedded Vision Systems srl, c/o Computer Science Park, Strada Le Grazie, 15 Verona, Italy
M. Farenzena , eVS embedded Vision Systems srl, c/o Computer Science Park, Strada Le Grazie, 15 Verona, Italy
M. Cristani , University of Verona, Strada Le Grazie, 15, Italy
pp. 65-70

SparkleVision: Seeing the world through random specular microfacets (Abstract)

Zhengdong Zhang , Massachusetts Institute of Technology, Cambridge, 02139, United States
Phillip Isola , Massachusetts Institute of Technology, Cambridge, 02139, United States
Edward H. Adelson , Massachusetts Institute of Technology, Cambridge, 02139, United States
pp. 1-9

Efficient 3D kernel estimation for non-uniform camera shake removal using perpendicular camera system (Abstract)

Tao Yue , Department of Automation, Tsinghua University, Beijing, China
Jinli Suo , Department of Automation, Tsinghua University, Beijing, China
Qionghai Dai , Department of Automation, Tsinghua University, Beijing, China
pp. 10-15

Reconstruction-free inference on compressive measurements (Abstract)

Suhas Lohit , School of Electrical, Computer, and Energy Engineering, Arizona State University, Tempe, United States
Kuldeep Kulkarni , School of Electrical, Computer, and Energy Engineering, Arizona State University, Tempe, United States
Pavan Turaga , School of Electrical, Computer, and Energy Engineering, Arizona State University, Tempe, United States
Jian Wang , Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, United States
Aswin C. Sankaranarayanan , Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, United States
pp. 16-24

Dense sampling of 3D color transfer functions using HDR photography (Abstract)

Marcel Heinz , Technische Universität Chemnitz, 09111, Germany
Guido Brunnett , Technische Universität Chemnitz, 09111, Germany
pp. 25-32

Fresnel lens imaging with post-capture image processing (Abstract)

Artem Nikonorov , Samara State Aerospace University, 34, Moskovskoye Shosse, Russia, 443086
Roman Skidanov , Samara State Aerospace University, 34, Moskovskoye Shosse, Russia, 443086
Vladimir Fursov , Samara State Aerospace University, 34, Moskovskoye Shosse, Russia, 443086
Maksim Petrov , Image Processing Systems Institute of RAS, 151, Molodogvardeyskaya str., Samara, Russia, 443001
Sergey Bibikov , Image Processing Systems Institute of RAS, 151, Molodogvardeyskaya str., Samara, Russia, 443001
Yuriy Yuzifovich , Image Processing Systems Institute of RAS, 151, Molodogvardeyskaya str., Samara, Russia, 443001
pp. 33-41

Video stitching with spatial-temporal content-preserving warping (Abstract)

Wei Jiang , Huawei Media Lab, Futurewei Technologies Inc., Santa Clara, CA 95050, United States
Jinwei Gu , Huawei Media Lab, Futurewei Technologies Inc., Santa Clara, CA 95050, United States
pp. 42-48

Video compressive sensing with on-chip programmable subsampling (Abstract)

Leonidas Spinoulas , Department of Electrical Engineering and Computer Science, Northwestern University, 2145 Sheridan Road, Evanston, IL 60208, USA
Kuan He , Department of Electrical Engineering and Computer Science, Northwestern University, 2145 Sheridan Road, Evanston, IL 60208, USA
Oliver Cossairt , Department of Electrical Engineering and Computer Science, Northwestern University, 2145 Sheridan Road, Evanston, IL 60208, USA
Aggelos Katsaggelos , Department of Electrical Engineering and Computer Science, Northwestern University, 2145 Sheridan Road, Evanston, IL 60208, USA
pp. 49-57

Fast single-frequency time-of-flight range imaging (Abstract)

Ryan Crabb , Dept. of Computer Engineering, University of California, Santa Cruz, United States
Roberto Manduchi , Dept. of Computer Engineering, University of California, Santa Cruz, United States
pp. 58-65

Semantic segmentation of urban scenes by learning local class interactions (Abstract)

Michele Volpi , University of Edinburgh, South Bridge, EH8 9YL, United Kingdom
Vittorio Ferrari , University of Edinburgh, South Bridge, EH8 9YL, United Kingdom
pp. 1-9

Active learning approach to detecting standing dead trees from ALS point clouds combined with aerial infrared imagery (Abstract)

Przemyslaw Polewski , Hochschule München, 80333, Germany
Wei Yao , Hochschule München, 80333, Germany
Marco Heurich , Bavarian Forest National Park, 94481 Grafenau, Germany
Peter Krzystek , Hochschule München, 80333, Germany
Uwe Stilla , Technische Universität München, 80333, Germany
pp. 10-18

Universality of wavelet-based non-homogeneous hidden Markov chain model features for hyperspectral signatures (Abstract)

Siwei Feng , University of Massachusetts, Amherst, 01003, United States
Marco F. Duarte , University of Massachusetts, Amherst, 01003, United States
Mario Parente , University of Massachusetts, Amherst, 01003, United States
pp. 19-27

A semi-supervised approach for ice-water classification using dual-polarization SAR satellite imagery (Abstract)

Fan Li , University of Waterloo, 200 University Ave W, ON N2L 3G1, Canada
David A. Clausi , University of Waterloo, 200 University Ave W, ON N2L 3G1, Canada
Lei Wang , University of Waterloo, 200 University Ave W, ON N2L 3G1, Canada
Linlin Xu , University of Waterloo, 200 University Ave W, ON N2L 3G1, Canada
pp. 28-35

Effective semantic pixel labelling with convolutional networks and Conditional Random Fields (Abstract)

Sakrapee Paisitkriangkrai , Australian Centre for Visual Technology (ACVT), The University of Adelaide, Australia
Jamie Sherrah , Defence Science and Technology Organisation (DSTO), Australia
Pranam Janney , Defence Science and Technology Organisation (DSTO), Australia
Anton Van-Den Hengel , Australian Centre for Visual Technology (ACVT), The University of Adelaide, Australia
pp. 36-43

Do deep features generalize from everyday objects to remote sensing and aerial scenes domains? (Abstract)

Otavio A. B. Penatti , Advanced Technologies Group, SAMSUNG Research Institute, Campinas, SP, 13097-160, Brazil
Keiller Nogueira , Department of Computer Science, Universidade Federal de Minas Gerais, Belo Horizonte, 31270-010, Brazil
Jefersson A. dos Santos , Department of Computer Science, Universidade Federal de Minas Gerais, Belo Horizonte, 31270-010, Brazil
pp. 44-51

Matching Persistent Scatterers to optical oblique images (Abstract)

Lukas Schack , Leibniz Universität Hannover, Institute of Photogrammetry and GeoInformation, Germany
Uwe Soergel , Technische Universität Darmstadt, Institute of Geodesy, Germany
pp. 52-60

Simultaneous registration and change detection in multitemporal, very high resolution remote sensing data (Abstract)

Maria Vakalopoulou , Remote Sensing Laboratory, National Technical University of Athens, Greece
Konstantinos Karatzalos , Remote Sensing Laboratory, National Technical University of Athens, Greece
Nikos Komodakis , Ecole des Ponts ParisTech, University Paris-Est, France
Nikos Paragios , Center for Visual Computing, Ecole Centrale de Paris, France
pp. 61-69

On the location dependence of convolutional neural network features (Abstract)

Scott Workman , Department of Computer Science, University of Kentucky, United States
Nathan Jacobs , Department of Computer Science, University of Kentucky, United States
pp. 70-78

Oil spill candidate detection from SAR imagery using a thresholding-guided stochastic fully-connected conditional random field model (Abstract)

Linlin Xu , Department of Systems Design Engineering, University of Waterloo, Canada
M. Javad Shafiee , Department of Systems Design Engineering, University of Waterloo, Canada
Alexander Wong , Department of Systems Design Engineering, University of Waterloo, Canada
Fan Li , Department of Systems Design Engineering, University of Waterloo, Canada
Lei Wang , Department of Systems Design Engineering, University of Waterloo, Canada
David Clausi , Department of Systems Design Engineering, University of Waterloo, Canada
pp. 79-86

Detection of incomplete enclosures of rectangular shape in remotely sensed images (Abstract)

Igor Zingman , Computer and Information Science, University of Konstanz, Germany
Dietmar Saupe , Computer and Information Science, University of Konstanz, Germany
Karsten Lambers , IADK, University of Bamberg, Germany
pp. 87-96

Geometric inpainting of 3D structures (Abstract)

Pratyush Sahay , Indian Institute of Technology Madras, Chennai, India
A.N. Rajagopalan , Indian Institute of Technology Madras, Chennai, India
pp. 1-7

Real-time non-rigid multi-frame depth video super-resolution (Abstract)

Kassem Al Ismaeil , Interdisciplinary Centre for Security, Reliability, and Trust, University of Luxembourg, Luxembourg
Djamila Aouada , Interdisciplinary Centre for Security, Reliability, and Trust, University of Luxembourg, Luxembourg
Thomas Solignac , Advanced Engineering Department, IEE S.A., Luxembourg
Bruno Mirbach , Advanced Engineering Department, IEE S.A., Luxembourg
Bjorn Ottersten , Interdisciplinary Centre for Security, Reliability, and Trust, University of Luxembourg, Luxembourg
pp. 8-16

Accurate localization by fusing images and GPS signals (Abstract)

Kumar Vishal , Centre for Visual Information Technology, IIIT Hyderabad, India
C. V. Jawahar , Centre for Visual Information Technology, IIIT Hyderabad, India
Visesh Chari , Centre for Visual Information Technology, IIIT Hyderabad, India
pp. 17-24

Exploiting global priors for RGB-D saliency detection (Abstract)

Jianqiang Ren , Zhejiang University, China, 310027
Xiaojin Gong , Zhejiang University, China, 310027
Lu Yu , Zhejiang University, China, 310027
Wenhui Zhou , Hangzhou Dianzi University, China
Michael Ying Yang , TU Dresden, 01069, Germany
pp. 25-32

Sparse re-id: Block sparsity for person re-identification (Abstract)

Srikrishna Karanam , Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY 12180, United States
Yang Li , Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY 12180, United States
Richard J. Radke , Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY 12180, United States
pp. 33-40

Seamless change detection and mosaicing for aerial imagery (Abstract)

Nimisha T.M , Indian Institute of Technology Madras, Chennai, India
A.N. Rajagopalan , Indian Institute of Technology Madras, Chennai, India
R. Aravind , Indian Institute of Technology Madras, Chennai, India
pp. 1-8

Absolute geo-localization thanks to Hidden Markov Model and exemplar-based metric learning (Abstract)

Cedric Le Barz , THALES Services - 91767 Palaiseau, France
Nicolas Thome , Sorbonne University, UPMC University, Paris 06, UMR 7606, LIP6 - 75005, France
Matthieu Cord , Sorbonne University, UPMC University, Paris 06, UMR 7606, LIP6 - 75005, France
Stephane Herbin , French Aerospace Lab, ONERA - 91123 Palaiseau, France
Martial Sanfourche , French Aerospace Lab, ONERA - 91123 Palaiseau, France
pp. 9-17

Sequence searching with deep-learnt depth for condition- and viewpoint-invariant route-based place recognition (Abstract)

Michael Milford , Queensland University of Technology Australia, Australian Centre for Robotic Vision, Australia
Stephanie Lowry , Queensland University of Technology Australia, Australian Centre for Robotic Vision, Australia
Niko Sunderhauf , Queensland University of Technology Australia, Australian Centre for Robotic Vision, Australia
Sareh Shirazi , Queensland University of Technology Australia, Australian Centre for Robotic Vision, Australia
Edward Pepperell , Queensland University of Technology Australia, Australian Centre for Robotic Vision, Australia
Ben Upcroft , Queensland University of Technology Australia, Australian Centre for Robotic Vision, Australia
Chunhua Shen , The University of Adelaide, Australian Centre for Robotic Vision, Australia
Guosheng Lin , The University of Adelaide, Australian Centre for Robotic Vision, Australia
Fayao Liu , The University of Adelaide, Australian Centre for Robotic Vision, Australia
Cesar Cadena , The University of Adelaide, Australian Centre for Robotic Vision, Australia
Ian Reid , The University of Adelaide, Australian Centre for Robotic Vision, Australia
pp. 18-25

Robust and fast detection of moving vehicles in aerial videos using sliding windows (Abstract)

Michael Teutsch , Fraunhofer IOSB, Karlsruhe, Germany
Wolfgang Kruger , Fraunhofer IOSB, Karlsruhe, Germany
pp. 26-34

Driver cell phone usage detection on Strategic Highway Research Program (SHRP2) face view videos (Abstract)

Keshav Seshadri , CyLab Biometrics Center and the Department of Electrical and Computer Engineering (ECE), Carnegie Mellon University, Pittsburgh, USA
Felix Juefei-Xu , CyLab Biometrics Center and the Department of Electrical and Computer Engineering (ECE), Carnegie Mellon University, Pittsburgh, USA
Dipan K. Pal , CyLab Biometrics Center and the Department of Electrical and Computer Engineering (ECE), Carnegie Mellon University, Pittsburgh, USA
Marios Savvides , CyLab Biometrics Center and the Department of Electrical and Computer Engineering (ECE), Carnegie Mellon University, Pittsburgh, USA
Craig P. Thor , Office of Safety Research and Development, Federal Highway Administration, U.S. Department of Transportation, Virginia, USA
pp. 35-43
90 ms
(Ver 3.3 (11022016))