Proceedings

2017 IEEE Winter Conference on Applications of Computer Vision

WACV 2017

Proceedings

2017 IEEE Winter Conference on Applications of Computer Vision

24–31 March 2017

Santa Rosa, California

Los Alamitos, California

Washington • Tokyo

Copyright © 2017 by The Institute of Electrical and Electronics Engineers, Inc.

All rights reserved.

Copyright and Reprint Permissions: Abstracting is permitted with credit to the source. Libraries may photocopy beyond the limits of US copyright law, for private use of patrons, those articles in this volume that carry a code at the bottom of the first page, provided that the per-copy fee indicated in the code is paid through the Copyright Clearance Center, 222 Rosewood Drive, Danvers, MA 01923. Other copying, reprint, or republication requests should be addressed to: IEEE Copyrights Manager, IEEE Service Center, 445 Hoes Lane, P.O. Box 133, Piscataway, NJ 08855-1331. The papers in this book comprise the proceedings of the meeting mentioned on the cover and title page. They reflect the authors’ opinions and, in the interests of timely dissemination, are published as presented and without change. Their inclusion in this publication does not necessarily constitute endorsement by the editors, the IEEE Computer Society, or the Institute of Electrical and Electronics Engineers, Inc.

IEEE Computer Society Order Number E6090

BMS Part Number CFP17082-ART ISBN 978-1-5090-4822-9

Additional copies may be ordered from:

IEEE Computer Society IEEE Service Center IEEE Computer Society Customer Service Center 445 Hoes Lane Asia/Pacific Office

10662 Los Vaqueros Circle P.O. Box 1331 Watanabe Bldg., 1-4-2 P.O. Box 3014 Piscataway, NJ 08855-1331 Minami-Aoyama

Los Alamitos, CA 90720-1314 Tel: + 1 732 981 0060 Minato-ku, Tokyo 107-0062 Tel: + 1 800 272 6657 Fax: + 1 732 981 9667 JAPAN Fax: + 1 714 821 4641 http://shop.ieee.org/store/ Tel: + 81 3 3408 3118

http://computer.org/cspress csbooks@computer.org

customer-service@ieee.org Fax: + 81 3 3408 3553 tokyo.ofc@computer.org

Individual paper REPRINTS may be ordered at: <reprints@computer.org>

Editorial production by Lisa O’Conner Cover art production by Mark Bartosik

IEEE Computer Society

Conference Publishing Services (CPS) http://www.computer.org/cps

2017 IEEE Winter Conferenceon Applications of Computer

Vision

WACV 2017Table of Contents

Message from the General and Program Chairs.......................................................................................................xvi

Organizing Committee and Area Chairs ...................................................................................................................xvii

Sponsors.....................................................................................................................................................................xviii

Segmentation, TrackingDeep Salient Object Detection by Integrating Multi-level Cues .......................................................................................1

Jing Zhang, Yuchao Dai, and Fatih Porikli

Multi-planar Fitting in an Indoor ManhattanWorld ..........................................................................................................11Seongdo Kim and Roberto Manduchi

Universal Skin Detection Without Color Information ......................................................................................................20Abhijit Sarkar, A. Lynn Abbott, and Zachary Doerzaph

Recurrent Fully Convolutional Networks for Video Segmentation .................................................................................29Sepehr Valipour, Mennatullah Siam, Martin Jagersand, and Nilanjan Ray

Learning Spatial Transforms for Refining Object Segment Proposals ..........................................................................37Haoyang Zhang, Xuming He, and Fatih Porikli

Repeated Pattern Detection Using CNN Activations .....................................................................................................47Louis Lettry, Michal Perdoch, Kenneth Vanhoey, and Luc Van Gool

Deep Context Modeling for Semantic Segmentation ....................................................................................................56Kien Nguyen, Clinton Fookes, and Sridha Sridharan

3D Semantic Segmentation of Modular Furniture Using rjMCMC .................................................................................64Ishrat Badami, Manu Tom, Markus Mathias, and Bastian Leibe

PASCAL Boundaries: A Semantic Boundary Dataset with a Deep Semantic BoundaryDetector .........................................................................................................................................................................73

Vittal Premachandran, Boyan Bonev, Xiaochen Lian, and Alan Yuille

Can Affordances Guide Object Decomposition into Semantically Meaningful Parts? ...................................................82Safoura Rezapour Lakani, Antonio J. Rodríguez-Sánchez, and Justus Piater

Solving Occlusion Problem in Pedestrian Detection by Constructing Discriminative PartLayers ............................................................................................................................................................................91

Cong Cao, Yu Wang, Jien Kato, Guanwen Zhang, and Kenji Mase

v

Unifying Registration Based Tracking: A Case Study with Structural Similarity ..........................................................100Abhineet Singh, Mennatullah Siam, and Martin Jagersand

Action RecognitionDeep Moving Poselets for Video Based Action Recognition .......................................................................................111

Effrosyni Mavroudi, Lingling Tao, and René Vidal

First-Person Action Decomposition and Zero-Shot Learning ......................................................................................121Yun C. Zhang, Yin Li, and James M. Rehg

Higher-Order Pooling of CNN Features via Kernel Linearization for Action Recognition ............................................130Anoop Cherian, Piotr Koniusz, and Stephen Gould

Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely LowResolutions ..................................................................................................................................................................139

Jiawei Chen, Jonathan Wu, Janusz Konrad, and Prakash Ishwar

On Geometric Features for Skeleton-Based Action Recognition Using Multilayer LSTMNetworks ......................................................................................................................................................................148

Songyang Zhang, Xiaoming Liu, and Jun Xiao

Real-Time Online Action Detection Forests Using Spatio-Temporal Contexts ...........................................................158Seungryul Baek, Kwang In Kim, and Tae-Kyun Kim

Ordered Pooling of Optical Flow Sequences for Action Recognition ..........................................................................168Jue Wang, Anoop Cherian, and Fatih Porikli

Two Stream LSTM: A Deep Fusion Framework for Human Action Recognition .........................................................177Harshala Gammulle, Simon Denman, Sridha Sridharan, and Clinton Fookes

Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking ..................................................187Wenhui Li, Yongkang Wong, An-An Liu, Yang Li, Yu-Ting Su, and Mohan Kankanhalli

Efficient Action Detection in Untrimmed Videos via Multi-task Learning .....................................................................197Yi Zhu and Shawn Newsam

Learning Discriminative Features via Label Consistent Neural Network .....................................................................207Zhuolin Jiang, Yaming Wang, Larry Davis, Walter Andrews, and Viktor Rozgic

Recognition of Group Activities in Videos Based on Single-and Two-Person Descriptors .........................................217Stéphane Lathuilière, Georgios Evangelidis, and Radu Horaud

Comp Photo, 3D Modeling, Remote Sensing, GestureQuantitative Analysis of Automatic Image Cropping Algorithms: A Datasetand Comparative Study ...............................................................................................................................................226

Yi-Ling Chen, Tzu-Wei Huang, Kai-Han Chang, Yu-Chen Tsai, Hwann-Tzong Chen,and Bing-Yu Chen

Joint Regression and Ranking for Image Enhancement .............................................................................................235Parag Shridhar Chandakkar and Baoxin Li

Material Classification under Natural Illumination Using Reflectance Maps ...............................................................244Stamatios Georgoulis, Vincent Vanweddingen, Marc Proesmans, and Luc Van Gool

vi

Dense Batch Non-Rigid Structure from Motion in a Second .......................................................................................254Vladislav Golyanik and Didier Stricker

Global Model with Local Interpretation for Dynamic Shape Reconstruction ...............................................................264Antonio Agudo and Francesc Moreno-Noguer

Occlusions are Fleeting - Texture is Forever: Moving Past Brightness Constancy .....................................................273Christopher Ham, Surya Singh, and Simon Lucey

Accurate 3D Reconstruction of Dynamic Scenes from Monocular Image Sequenceswith Severe Occlusions ...............................................................................................................................................282

Vladislav Golyanik, Torben Fetzer, and Didier Stricker

Patchwork Stereo: Scalable, Structure-Aware 3D Reconstruction in Man-MadeEnvironments ...............................................................................................................................................................292

Amine Bourki, Martin de La Gorce, Renaud Marlet, and Nikos Komodakis

Calibration Technique for Underwater Active Oneshot Scanning System with StaticPattern Projector and Multiple Cameras ......................................................................................................................302

Hiroshi Kawasaki, Hideaki Nakai, Hirohisa Baba, Ryusuke Sagawa, and Ryo Furukawa

Fast Deep Vehicle Detection in Aerial Images ............................................................................................................311Lars Wilko Sommer, Tobias Schuchert, and Jürgen Beyerer

Beyond Spatial Auto-Regressive Models: Predicting Housing Prices with SatelliteImagery ........................................................................................................................................................................320

Archith J. Bency, Swati Rallapalli, Raghu K. Ganti, Mudhakar Srivatsa, and B. S. Manjunath

Robust Hand Gestural Interaction for Smartphone Based AR/VR Applications ..........................................................330Shreyash Mohatta, Ramakrishna Perla, Gaurav Gupta, Ehtesham Hassan,and Ramya Hebbalaguppe

Spatial-Temporal Motion Field Analysis for Pixelwise Crack Detection on ConcreteSurfaces ......................................................................................................................................................................336

Subhajit Chaudhury, Gaku Nakano, Jun Takada, and Akihiko Iketani

Scene Understanding, Motion Processing2-Line Exhaustive Searching for Real-Time Vanishing Point Estimation in ManhattanWorld ...........................................................................................................................................................................345

Xiaohu Lu, Jian Yaoy, Haoang Li, and Yahui Liu

Pano2CAD: Room Layout from a Single Panorama Image ........................................................................................354Jiu Xu, Björn Stenger, Tommi Kerola, and Tony Tung

A Multi-view RGB-D Approach for Human Pose Estimation in Operating Rooms ......................................................363Abdolrahim Kadkhodamohammadi, Afshin Gangi, Michel de Mathelin, and Nicolas Padoy

Real Estate Image Classification .................................................................................................................................373Jawadul H. Bappy, Joseph R. Barr, Narayanan Srinivasan, and Amit K. Roy-Chowdhury

Learn How to Choose: Independent Detectors Versus Composite Visual Phrases ....................................................382Guy Rosenthal, Ariel Shamir, and Leonid Sigal

vii

Temporal Robust Features for Violence Detection .....................................................................................................391Daniel Moreira, Sandra Avila, Mauricio Perez, Daniel Moraes, Vanessa Testoni,Eduardo Valle, Siome Goldenstein, and Anderson Rocha

SAMP: Shape and Motion Priors for 4D Vehicle Reconstruction ................................................................................400Francis Engelmann, Jörg Stückler, and Bastian Leibe

Predicting the Perceptual Demands of Urban Driving with Video Regression ............................................................409Luke Palmer, Alina Bialkowski, Gabriel J. Brostow, Jonas Ambeck-Madsen, and Nilli Lavie

Optimal Threshold and LoG Based Feature Identification and Tracking of Bat FlappingFlight ............................................................................................................................................................................418

Yousi Lin, Yang Xu, Hui Chen, Matthew J. Bender, A. Lynn Abbott, and Rolf Müller

Fast Semi Dense Epipolar Flow Estimation ................................................................................................................427Matthieu Garrigues and Antoine Manzanera

Global Consistency Priors for Joint Part-Based Object Tracking and ImageSegmentation ..............................................................................................................................................................436

Oliver Müller and Bodo Rosenhahn

Joint Epipolar Tracking (JET): Simultaneous Optimization of Epipolar Geometryand Feature Correspondences ....................................................................................................................................445

Henry Bradler, Matthias Ochs, Nolang Fanani, and Rudolf Mester

Computing Egomotion with Local Loop Closures for Egocentric Videos ....................................................................454Suvam Patra, Himanshu Aggarwal, Himani Arora, Subhashis Banerjee, and Chetan Arora

Statistical Methods, Object RecognitionCyclical Learning Rates for Training Neural Networks ................................................................................................464

Leslie N. Smith

Guaranteed Parameter Estimation for Discrete Energy Minimization .........................................................................473Mengtian Li and Daniel Huber

Solving Robust Regularization Problems Using Iteratively Re-weighted Least Squares ............................................483Khurrum Aftab Kiani and Tom Drummond

Detecting Social Insects in Videos Using Spatiotemporal Regularization ...................................................................493N. Rich Nguyen and Min C. Shin

From Affine Rank Minimization Solution to Sparse Modeling .....................................................................................501Iman Abbasnejad, Sridha Sridharan, Simon Denman, Clinton Fookes, and Simon Lucey

Learning Attributes from Human Gaze ........................................................................................................................510Nils Murrugarra-Llerena and Adriana Kovashka

Multi-task Curriculum Transfer Deep Learning of Clothing Attributes .........................................................................520Qi Dong, Shaogang Gong, and Xiatian Zhu

Deep Learning Logo Detection with Data Expansion by Synthesising Context ..........................................................530Hang Su, Xiatian Zhu, and Shaogang Gong

Boosted Convolutional Neural Networks (BCNN) for Pedestrian Detection ................................................................540Chi-Hao Wu, Weihao Gan, De Lan, and C.-C. Jay Kuo

viii

Improved Deep Learning of Object Category Using Pose Information .......................................................................550Jiaping Zhao and Laurent Itti

Learning to Recognize Objects by Retaining Other Factors of Variation ....................................................................560Jiaping Zhao, Chin-Kai Chang, and Laurent Itti

Artistic Movement Recognition by Boosted Fusion of Color Structure and TopographicDescription ...................................................................................................................................................................569

Corneliu Florea, Cosmin Ţoca, and Fabian Gieseke

Security, Vision for Aerial, MultimediaPlug-and-Play CNN for Crowd Motion Analysis: An Application to Abnormal EventDetection .....................................................................................................................................................................578

Mahdyar Ravanbakhsh, Moin Nabi, Hossein Mousavi, Enver Sangineto, and Nicu Sebe

Deep Heterogeneous Feature Fusion for Template-Based Face Recognition ...........................................................586Navaneeth Bodla, Jingxiao Zheng, Hongyu Xu, Jun-Cheng Chen, Carlos Castillo,and Rama Chellappa

Integrated Global-Local Metric Learning for Person Re-identification .........................................................................596Jing Zhang and Xu Zhao

Multi-shot Person Re-Identification Using Part Appearance Mixture ..........................................................................605Furqan M. Khan and François Brèmond

Active Online Anomaly Detection Using Dirichlet Process Mixture Model and GaussianProcess Classification .................................................................................................................................................615

Jagannadan Varadarajan, Ramanathan Subramanian, Narendra Ahuja, Pierre Moulin,and Jean-Marc Odobez

Flowdometry: An Optical Flow and Deep Learning Based Approach to Visual Odometry ..........................................624Peter Muller and Andreas Savakis

PCA Based Computation of Illumination-Invariant Space for Road Detection ............................................................632Taeyoung Kim, Yu-Wing Tai, and Sung-Eui Yoon

Road Detection Using Convolutional Neural Networks ...............................................................................................641Aparajit Narayan, Elio Tuci, Frédéric Labrosse, and Muhanad H. Mohammed Alkilabi

Providing Video Annotations in Multimedia Containers for Visualization and Research .............................................650Julius Schöning, Patrick Faion, Gunther Heidemann, and Ulf Krumnack

Detecting Sexually Provocative Images ......................................................................................................................660Debashis Ganguly, Mohammad H. Mofrad, and Adriana Kovashka

Complex Event Recognition from Images with Few Training Examples .....................................................................669Unaiza Ahsan, Chen Sun, James Hays, and Irfan Essa

High-Level Concepts for Affective Understanding of Images ......................................................................................679Afsheen Rafaqat Ali, Usman Shahid, Mohsen Ali, and Jeffrey Ho

ix

Vision SystemsAssessment of Peanut Pod Maturity ...........................................................................................................................688

Ekta Bindlish, A. Lynn Abbott, and Maria Balota

X-Ray Scattering Image Classification Using Deep Learning .....................................................................................697Boyu Wang, Kevin Yager, Dantong Yu, and Minh Hoai

A Deep Learning Frame-Work for Recognizing Developmental Disorders .................................................................705Pushkar Shukla, Tanu Gupta, Aradhya Saini, Priyanka Singh, and Raman Balasubramanian

When Was That Made? ...............................................................................................................................................715Sirion Vittayakorn, Alexander C. Berg, and Tamara L. Berg

Telecom Inventory Management via Object Recognition and Localisation on GoogleStreet View Images .....................................................................................................................................................725

Ramya Hebbalaguppe, Gaurav Garg, Ehtesham Hassan, Hiranmay Ghosh,and Ankit Verma

Deep Object Ranking for Template Matching ..............................................................................................................734Jean-Philippe Mercier, Ludovic Trottier, Philippe Giguère, and Brahim Chaib-draa

A Deep Learning Paradigm for Detection of Harmful Algal Blooms ............................................................................743Arun CS Kumar and Suchendra M. Bhandarkar

Crime Mapping from Satellite Imagery via Deep Learning ..........................................................................................752Alameen Najjar, Shun'Ichi Kaneko, and Yoshikazu Miyanaga

Robust Road Marking Detection and Recognition Using Density-Based Groupingand Machine Learning Techniques .............................................................................................................................760

Oleksandr Bailo, Seokju Lee, Francois Rameau, Jae Shin Yoon, and In So Kweon

Beacon-Guided Structure from Motion for Smartphone-Based Navigation .................................................................769Tatsuya Ishihara, Jayakorn Vongkulbhisal, Kris M. Kitani, and Chieko Asakawa

Hardware-Centric Vision Processing for Mobile IoT Environment ExploitingApproximate Graph Cut in Resistor Grid .....................................................................................................................778

Yeongjae Choi, Jun-Seok Park, and Lee-Sup Kim

Exploring Local Context for Multi-target Tracking inWide Area Aerial Surveillance ....................................................787Bor-Jeng Chen and Gérard Medioni

Medical, Vision for Graphics and Robotics, Open Source APIMelanoma Detection Based on Mahalanobis Distance Learning and Constrained GraphRegularized Nonnegative Matrix Factorization ............................................................................................................797

Yanyang Gu, Jun Zhou, and Bin Qian

Size and Texture-Based Classification of Lung Tumors with 3D CNNs ......................................................................806Zhihao Luo, Marcus A. Brubaker, and Michael Brudno

3D-Brain Segmentation Using Deep Neural Network and Gaussian Mixture Model ...................................................815Duy M. H. Nguyen, Huy T. Vu, Huy Q. Ung, and Binh T. Nguyen

x

Ultrasound Tracking Using ProbeSight: Camera Pose Estimation Relative to ExternalAnatomy by Inverse Rendering of a Prior High-Resolution 3D Surface Map ..............................................................825

Jihang Wang, Chengqian Che, John Galeotti, Samantha Horvath, Vijay Gorantla,and George Stetten

Center-Focusing Multi-task CNN with Injected Features for Classification of GliomaNuclear Images ...........................................................................................................................................................834

Veda Murthy, Le Hou, Dimitris Samaras, Tahsin M. Kurc, and Joel H. Saltz

Densification of Semi-Dense Reconstructions for Novel View Generation of LiveScenes .........................................................................................................................................................................842

Domagoj Baričević, Tobias Höllerer, and Matthew Turk

Texture Attribute Synthesis and Transfer Using Feed-Forward CNNs .......................................................................852Thomas Irmer, Tobias Glasmachers, and Subhransu Maji

A Statistical Approach to Continuous Self-Calibrating Eye Gaze Trackingfor Head-Mounted Virtual Reality Systems ..................................................................................................................862

Subarna Tripathi and Brian Guenter

Sparse Dictionary Learning for Identifying Grasp Locations .......................................................................................871Ludovic Trottier, Philippe Giguère, and Brahim Chaib-draa

T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-Less Objects ..........................................................880Tomáš Hodaň, Pavel Haluza, Štěpán Obdržálek, Jiří Matas, Manolis Lourakis,and Xenophon Zabulis

Gaussian Mixture Models for Temporal Depth Fusion ................................................................................................889Cevahir Cigla, Roland Brockers, and Larry Matthies

An Open-Source Platform for Underwater Image and Video Analytics .......................................................................898Matthew Dawkins, Linus Sherrill, Keith Fieldhouse, Anthony Hoogs, Benjamin Richards,David Zhang, Lakshman Prasad, Kresimir Williams, Nathan Lauffenburger,and Gaoang Wang

Object Recognition 2, Large Scale SystemsDescribing Unseen Classes by Exemplars: Zero-Shot Learning Using Grouped SimileEnsemble .....................................................................................................................................................................907

Yang Long and Ling Shao

Deep Multi-modal Vehicle Detection in Aerial ISR Imagery ........................................................................................916Wesam Sakla, Goran Konjevod, and T. Nathan Mundhenk

Subcategory-Aware Convolutional Neural Networks for Object Proposals and Detection ..........................................924Yu Xiang, Wongun Choi, Yuanqing Lin, and Silvio Savarese

StuffNet: Using ‘Stuff’ to Improve Object Detection .....................................................................................................934Samarth Brahmbhatt, Henrik I. Christensen, and James Hays

Towards Fine-Grained Open Zero-Shot Learning: Inferring Unseen Visual Featuresfrom Attributes .............................................................................................................................................................944

Yang Long, Li Liu, and Ling Shao

xi

Fused DNN: A Deep Neural Network Fusion Approach to Fast and Robust PedestrianDetection .....................................................................................................................................................................953

Xianzhi Du, Mostafa El-Khamy, Jungwon Lee, and Larry Davis

Fast Pedestrian Detection via Random Projection Features with Shape Prior ...........................................................962Yun Zhao, Zejian Yuan, Dapeng Chen, Jie Lyu, and Tie Liu

Enriched Deep Recurrent Visual Attention Model for Multiple Object Recognition .....................................................971Artsiom Ablavatski, Shijian Lu, and Jianfei Cai

Box Refinement: Object Proposal Enhancement and Pruning ....................................................................................979Siyang Li, Heming Zhang, Junting Zhang, Yuzhuo Ren, and C.-C. Jay Kuo

Semantic Text Summarization of Long Videos ............................................................................................................989Shagan Sah, Sourabh Kulhare, Allison Gray, Subhashini Venugopalan,Emily Prud'Hommeaux, and Raymond Ptucha

Unsupervised Joint Mining of Deep Features and Image Labels for Large-ScaleRadiology Image Categorization and Scene Recognition ...........................................................................................998

Xiaosong Wang, Le Lu, Hoo-Chang Shin, Lauren Kim, Mohammadhadi Bagheri,Isabella Nogues, Jianhua Yao, and Ronald M. Summers

Industrial Inspection, VR and AR, Stereo, EvaluationProbabilistic Surface Inference for Industrial Inspection Planning ............................................................................1008

Mahsa Mohammadikaji, Stephan Bergmann, Stephan Irgenfried, Jürgen Beyerer,Carsten Dachsbacher, and Heinz Wörn

Spatio-Temporal Anomaly Detection for Industrial Robots through Predictionin Unsupervised Feature Space ................................................................................................................................1017

Asim Munawar, Phongtharin Vinayavekhin, and Giovanni De Magistris

Automatic Defect Recognition in X-Ray Testing Using Computer Vision ..................................................................1026Domingo Mery and Carlos Arteta

X-Ray PoseNet: 6 DoF Pose Estimation for Mobile X-Ray Devices .........................................................................1036Mai Bui, Shadi Albarqouni, Michael Schrapp, Nassir Navab, and Slobodan Ilic

Crack Segmentation by Leveraging Multiple Frames of Varying Illumination ...........................................................1045Stephen J. Schmugge, Lance Rice, John Lindberg, Robert Grizziy, Chris Joffey,and Min C. Shin

GPU-Accelerated Real-Time Stixel Computation ......................................................................................................1054Daniel Hernandez-Juarez, Antonio Espinosa, Juan C. Moure, David Vázquez,and Antonio M. López

Model-Driven Simulations for Computer Vision .........................................................................................................1063Vsr Veeravasarapu, Constantin Rothkopf, and Ramesh Visvanathan

Automatic Calibration of a Multiple-Projector Spherical Fish Tank VR Display .........................................................1072Qian Zhou, Gregor Miller, Kai Wu, Daniela Correa, and Sidney Fels

Transfer Learning and Deep Feature Extraction for Planktonic Image Data Sets ....................................................1082Eric C. Orenstein and Oscar Beijbom

xii

Fast and Robust Eyelid Outline and Aperture Detection in Real-World Scenarios ...................................................1089Wolfgang Fuhl, Thiago Santini, and Enkelejda Kasneci

On Crater Verification Using Mislocalized Crater Regions ........................................................................................1098Ebrahim Emami, George Bebis, Ara Nefian, and Terry Fong

Face Processing, Biometrics, Image Compression, HCIRobust 3D Patch-Based Face Hallucination .............................................................................................................1105

Chengchao Qu, Christian Herrmann, Eduardo Monari, Tobias Schuchert,and Jürgen Beyerer

Dictionary Alignment for Low-Resolution and Heterogeneous Face Recognition .....................................................1115Sivaram Prasad Mudunuri and Soma Biswas

Pose-Robust Face Verification by Exploiting Competing Tasks ...............................................................................1124Boyu Lu, Jingxiao Zheng, Jun-Cheng Chen, and Rama Chellappa

Deep Feature Consistent Variational Autoencoder ...................................................................................................1133Xianxu Hou, Linlin Shen, Ke Sun, and Guoping Qiu

Egocentric Height Estimation ....................................................................................................................................1142Jessica Finocchiaro, Aisha Urooj Khan, and Ali Borji

Gender-from-Iris or Gender-from-Mascara? ..............................................................................................................1151Andrey Kuehlkamp, Benedict Becker, and Kevin Bowyer

ContlensNet: Robust Iris Contact Lens Detection Using Deep Convolutional NeuralNetworks ....................................................................................................................................................................1160

R. Raghavendra, Kiran B. Raja, and Christoph Busch

Breathing Rate Monitoring during Sleep from a Depth Camera under Real-LifeConditions ..................................................................................................................................................................1168

Manuel Martinez and Rainer Stiefelhagen

Writer Identification in Noisy Handwritten Documents ..............................................................................................1177Karl Ni, Patrick Callier, and Bradley Hatch

Image Set Classification Using Sparse Bayesian Regression ..................................................................................1187Mohammed E. Fathy and Rama Chellappa

Bandwidth Limited Object Recognition in High Resolution Imagery .........................................................................1197Laura Lopez-Fuentes, Andrew D. Bagdanov, Joost van de Weijer, and Harald Skinnemoen

Personalized Image Aesthetic Quality Assessment by Joint Regression and Ranking ............................................1206Kayoung Park, Seunghoon Hong, Mooyeol Baek, and Bohyung Han

Human Motion, Image Indexing, Vision SystemsDeep Spatio-Temporal Features for Multimodal Emotion Recognition .....................................................................1215

Dung Nguyen, Kien Nguyen, Sridha Sridharan, Afsane Ghasemi, David Dean,and Clinton Fookes

Human Pose Estimation Using Deep Structure Guided Learning .............................................................................1224Baole Ai, Yu Zhou, Yao Yu, and Sidan Du

xiii

Switching Linear Inverse-Regression Model for Tracking Head Pose ......................................................................1232Vincent Drouard, Silèye Ba, and Radu Horaud

Deep Image Set Hashing ..........................................................................................................................................1241Jie Feng, Svebor Karaman, and Shih-Fu Chang

Learning Effective Binary Descriptors via Cross Entropy ..........................................................................................1251Liu Liu and Hairong Qi

Convolutional Sparse and Low-Rank Coding-Based Rain Streak Removal .............................................................1259He Zhang and Vishal M. Patel

Fast, Accurate, Small-Scale 3D Scene Capture Using a Low-Cost Depth Sensor ...................................................1268Nicole Carey, Justin Werfel, and Radhika Nagpal

Who Moved My Cheese? Automatic Annotation of Rodent Behaviors with ConvolutionalNeural Networks ........................................................................................................................................................1277

Zhongzheng Ren, Adriana Noronha Annie, Vogel Ciernia, and Yong Jae Lee

Temporally Coded Illumination for Rolling Shutter Motion De-blurring .....................................................................1287Scott McCloskey and Sharath Venkatesha

Text-Edge-Box: An Object Proposal Approach for Scene Texts Localization ...........................................................1296Dinh Nguyen, Lu Shijian, Nizar Ouarti, and Mounir Mokhtari

Distance Penalization and Fusion for Person Re-identification .................................................................................1306Behzad Mirmahboub, Mohamed Lamine Mekhalfi, and Vittorio Murino

Author Index ............................................................................................................................................................1315

xiv

Message from the General and Program Chairs

Welcome to Santa Rosa, CA, and the 17th edition of the Winter Conference on Applications of Computer Vision (WACV), jointly sponsored by the IEEE Computer Society and the IEEE Biometrics Council. WACV is the premier outlet for research advances in applications of computer vision technology.

WACV 2017 spans four days, with a three-day, two-track, core program in which authors will present each accepted paper as a short oral and a poster. In addition, we have keynote talks and social functions, as well as several co-located events, including three workshops, two tutorials, a Ph.D. forum, and demo sessions. Following last year’s conference, WACV 2017 adopted a two-track core program, with two parallel oral sessions, each with 5-minute talks.

We used the Conference Management Toolkit (CMT) provided by Microsoft Research to manage the submission and selection of papers. To select papers for the program, we invited 27 researchers to act as Area Chairs (ACs). We recruited 275 experienced reviewers from the broader computer vision community. We received 320 original unpublished, full paper, submissions to the main conference. The Program Chairs (PCs) assigned the papers to the ACs who made recommendations for reviewers. All papers were reviewed by a minimum of three reviewers. Papers by PCs and GCs were handled to avoid conflict of interests, and the ACs were excluded from any decisions associated with papers from their research groups, affiliated institutions or collaborators. After the reviews were received, authors were offered an opportunity to rebut. Area chairs made initial recommendations based on the reviews, rebuttals, and reviewer discussions. In a few cases, the PCs discussed papers with the ACs to arrive at a final decision. Of the 320 full papers submitted, 144 high-quality papers were accepted to be part of the final program (~ 45% acceptance rate).

The proceedings of WACV 2017 are provided online before, during, and after the conference to all registered attendees. Like last year, there will not be USB proceedings, so participants are encouraged to download the proceedings before the conference. All papers in the main conference and associated workshops will be made available through the IEEE Computer Society Digital Library and IEEE Xplore.

The main conference also includes three keynote speakers: Dr. Richard Szeliski from Facebook & Univ. of Washington, Prof. Marc Pollefeys from Microsoft Research & ETH Zurich, and Prof. Tamara Berg from Shopagon Inc. & UNC-Chapel Hill.

We wish to thank all members of the Organizing Committee, the Area Chairs, reviewers, authors, and the CMT for the immense amount of hard work and professionalism that went into making WACV 2017 a first-rate conference on the applications of computer vision. Our thanks also go to the organizers of past WACV meetings and the steering committee for their helpful advice and support.

We are grateful to our Silver Sponsors, Cognex and Kitware, and Bronze sponsors, Adobe, Disney Research, Amazon, Verisk Analytics, and Google, for their generous support.

Finally, we invite the attendees to be Sonomads for a few days and enjoy Sonoma County’s art, wine, and coffee.

Gérard Medioni, David Michael, Sudeep Sarkar (General Co- Chairs)

Michael S. Brown, Rogério Feris, Conrad Sanderson, Matthew Turk (Program Co-Chairs)

xvi

Organizing Committee & Area Chairs

WACV 2017 Organizing Committee

General Chairs: Gérard Medioni Sudeep Sarkar David Michael Program Chairs: Michael S. Brown Conrad Sanderson Matthew Turk Rogério Feris Steering Committee: Anthony Hoogs Bryan Morse Terrance Boult Bir Bhanu Fatih Porikli

Workshops Chair: Jiwen Lu Tutorials Chair: Xiaoming Liu Finance Chair: Terrance Boult Publications Chairs: Eric Mortensen Revathy Narasimhan Web Chair: Fillipe Souza Demos Chair: Tal Hassner PhD Forum Chair: Song Wang Publicity Chair: Ajay Kumar

WACV 2017 Area Chairs

Teofilo de Campos Liangliang Cao Peter Carr Kristin Dana Victor Fragoso Danna Gurari

Bohyung Han Mehrtash Harandi Tal Hassner Wong Yong Kang Seon Joo Kim Adriana Kovashka

Laura Leal-Taixé Mohammad Mahoor Scott McCloskey Chris McCool Vlad Morariu Fatih Porikli

Andrea Prati Brian Price Behjat Siddiquie Kevin Smith Matt Turek Xiaoyu Wang

Arnold Wiliem Guoying Zhao Wenyi Zhao

xvii

xviii