ECCV2016 paper list （完整版）

来源：互联网发布：淘宝允许卖开刃刀吗编辑：程序博客网时间：2024/05/17 08:07

摘自ECCV2016的会议论文：

Oral Session 1A: Detection, Recognition & Retrieval
Tuesday, October 11; 09:00 – 10:00
Chairs: Bernt Schiele (MPI), Vincent Lepetit (TU Graz)

O-1A-01. pdf_icon_1 CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples, Filip Radenovic, CMP, CVUT; Giorgos Tolias, CMP, CVUT; Ondra Chum, CMP, CVUT

O-1A-02. pdf_icon_1 SSD: Single Shot MultiBox Detector, Wei Liu, UNC Chapel Hill; Dragomir Anguelov, Zoox; dumitru Erhan, Google; Christian Szegedy, Google; Scott Reed, University of Michigan, Ann-Arbor; Cheng-Yang Fu, UNC Chapel Hill; Alex Berg, UNC Chapel Hill

O-1A-03. pdf_icon_1 A Recurrent Encoder-Decoder Network for Sequential Face Alignment, Xi Peng, Rutgers University; Rogerio Feris, IBM Research Center, USA; Xiaoyu Wang, Snapchat Research; Dimitris Metaxas, Rutgers University

O-1A-04. pdf_icon_1 Robust Facial Landmark Detection via Recurrent Attentive-Refinement Networks, Shengtao Xiao, National University of Singapore; Jiashi Feng, NUS; Junliang Xing, Chinese Academy of Sciences; Hanjiang Lai, SUN YAT-SEN UNIVERSITY; Shuicheng Yan, National University of Singapore; Ashraf Kassim, National University of Singapore

Spotlight Session 1A: Segmentation
Tuesday, October 11; 10:00 – 10:30
Chairs: Vittorio Ferrari (University of Edinburgh), Cristian Sminchisescu (Lund University)

S-1A-05. pdf_icon_1 Learning to Refine Object Segments, Pedro Pinheiro, EPFL; Tsung-Yi Lin, Cornell; Ronan Collobert, Facebook; Piotr Dollar, Facebook

S-1A-06. pdf_icon_1 Deep Automatic Portrait Matting, Xiaoyong Shen, CUHK; Xin Tao, CUHK; Hongyun Gao, CUHK; Chao Zhou, ; Jiaya Jia, Chinese University of Hong Kong

S-1A-07. pdf_icon_1 Segmentation from Natural Language Expressions, Ronghang Hu, UC Berkeley; Marcus Rohrbach, UC Berkeley; Trevor Darrell

S-1A-08. pdf_icon_1 Semantic Object Parsing with Graph LSTM, Xiaodan Liang, Sun Yat-sen University; Xiaohui Shen, Adobe; Jiashi Feng, NUS; Liang Lin, Sun Yat-sen University; Shuicheng Yan, NUS

S-1A-09. pdf_icon_1 SSHMT: Semi-supervised Hierarchical Merge Tree for Electron Microscopy Image Segmentation, Ting Liu, University of Utah; Miaomiao Zhang, MIT; Mehran Javanmardi, University of Utah; Nisha Ramesh, University of Utah; Tolga Tasdizen, University of Utah

Poster Session 1A
Tuesday, October 11; 11:00 – 12:30
Chairs: Jasper Uijlings (University of Edinburgh), Roberto Valenti (Sightcorp)

O-1A-01. pdf_icon_1 CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples, Filip Radenovic, CMP, CVUT; Giorgos Tolias, CMP, CVUT; Ondra Chum, CMP, CVUT

S-1A-05. pdf_icon_1 Learning to Refine Object Segments, Pedro Pinheiro, EPFL; Tsung-Yi Lin, Cornell; Ronan Collobert, Facebook; Piotr Dollar, Facebook

S-1A-06. pdf_icon_1 Deep Automatic Portrait Matting, Xiaoyong Shen, CUHK; Xin Tao, CUHK; Hongyun Gao, CUHK; Chao Zhou, ; Jiaya Jia, Chinese University of Hong Kong

S-1A-07. pdf_icon_1 Segmentation from Natural Language Expressions, Ronghang Hu, UC Berkeley; Marcus Rohrbach, UC Berkeley; Trevor Darrell

S-1A-08. pdf_icon_1 Semantic Object Parsing with Graph LSTM, Xiaodan Liang, Sun Yat-sen University; Xiaohui Shen, Adobe; Jiashi Feng, NUS; Liang Lin, Sun Yat-sen University; Shuicheng Yan, NUS

P-1A-10. pdf_icon_1 Fundamental Matrices from Moving Objects Using Line Motion Barcodes, Yoni Kasten, Hebrew University; Gil Ben Artzi, Hebrew University of Jerusalem; Shmuel Peleg, Hebrew University; Michael Werman

P-1A-11. pdf_icon_1 Human pose estimation using deep consensus voting, Ita Lifshitz, Weizmann Inst.; Ethan Fetaya, Weizmann Inst.; Shimon Ullman, Weizmann Inst.

P-1A-12. pdf_icon_1 Deep Learning the City: Quantifying Urban Perception At A Global Scale, Abhimanyu Dubey, ; Nikhil Naik, MIT ; Devi Parikh, Virginia Tech; Ramesh Raskar, MIT Media Lab; Cesar Hidalgo, MIT

P-1A-13. pdf_icon_1 4D Match Trees for Non-rigid Surface Alignment, Armin Mustafa, University of Surrey; Hansung Kim, U.Surrey; Adrian Hilton, University of Surrey

P-1A-14. pdf_icon_1 Eigen Appearance Maps of Dynamic Shapes, Adnane Boukhayma, Inria; vagia Tsiminaki, Inria; Jean-Sebastien Franco, LJK, Université Grenoble Alpes, Inria; Edmond Boyer, Inria

P-1A-15. pdf_icon_1 Learnable Histogram: Statistical Context Features for Deep Neural Networks, Zhe Wang, CUHK; Hongsheng Li, CUHK; Wanli Ouyang, Chinese University of Hong Kong; Xiaogang Wang, The Chinese University of Hong Kong

P-1A-16. pdf_icon_1 Pedestrian Behavior Understanding and Prediction with Deep Neural Networks, Shuai Yi, CUHK; Hongsheng Li, CUHK; Xiaogang Wang, The Chinese University of Hong Kong

P-1A-17. pdf_icon_1 Real-time RGB-D Activity Prediction by Soft Regression, Jian-Fang Hu, Sun Yat-sen University; Wei-Shi Zheng, ; Lianyang Ma, ; Gang Wang, ; Jianhuang Lai

P-1A-18. pdf_icon_1 A 3D Morphable Eye Region Model for Gaze Estimation, Erroll Wood, University of Cambridge; Tadas Baltrušaitis, Carnegie Mellon University; Louis-Philippe Morency, Carnegie Mellon University; Peter Robinson, University of Cambridge; Andreas Bulling, Max Planck Institute for Informatics

P-1A-19. pdf_icon_1 Foreground Segmentation via Dynamic Tree-Structured Sparse RPCA, Salehe Erfanian Ebadi, Queen Mary University of London; Ebroul Izquierdo, Queen Mary University of London

P-1A-20. pdf_icon_1 Contextual Priming & Feedback for Faster R-CNN, Abhinav Shrivastava, Carnegie Mellon University; Abhinav Gupta

P-1A-21. pdf_icon_1 Efficient Multi-view Surface Refinement with Adaptive Resolution Control, Shiwei Li, HKUST; Sing Yu Siu, HKUST; Tian Fang, HKUST; Long Quan, The Hong Kong University of Science and Technology, Hong Kong

P-1A-22. pdf_icon_1 Gaussian Process Density Counting from Weak Supervision, Matthias von Borstel, Heidelberg University; Melih Kandemir, Heidelberg University; Philip Schmidt, Heidelberg University; Madhavi Kachur Rao, Robert Bosch; Kumar Rajamani, Bosch India; Fred Hamprecht, Heidelberg University

P-1A-23. pdf_icon_1 Region-based semantic segmentation with end-to-end training, Holger Caesar, University of Edinburgh; Jasper Uijlings, Univ. of Edinburgh; Vittorio Ferrari

P-1A-24. pdf_icon_1 Fast 6D Pose Estimation from a Monocular Image using Hierarchical Pose Trees, Yoshinori Konishi, OMRON Corporation; Yuki Hanzawa, OMRON Corporation; Masato Kawade, OMRON Corporation; Manabu Hashimoto, Chukyo University

P-1A-25. pdf_icon_1 Learning Models for Actions and Person-Object Interactions with Transfer to Question Answering, Arun Mallya, UIUC; Svetlana Lazebnik

P-1A-26. pdf_icon_1 A Software Platform for Manipulating the Camera Imaging Pipeline, Hakki Karaimer, NUS; Michael Brown, NUS

P-1A-27. pdf_icon_1 A Benchmark and Simulator for UAV Tracking, Matthias Mueller, KAUST; Bernard Ghanem, KAUST; Neil Smith, KAUST

P-1A-28. pdf_icon_1 Scene depth profiling using Helmholtz Stereopsis, Hironori Mori, Sony Deutschland GmbH; Roderick Koehle, ; Markus Kamm,

P-1A-29. pdf_icon_1 Projective Bundle Adjustment from Arbitrary Initialization using the Variable Projection Method, Je Hyeong Hong, University of Cambridge; Christopher Zach, Toshiba Research Europe; Andrew Fitzgibbon, Microsoft Research; Roberto Cipolla

P-1A-30. pdf_icon_1 Localizing and Orienting Street Views Using Overhead Imagery, Nam Vo, Georgia Institute of Technology; James Hays, Georgia Institute of Technology

P-1A-31. pdf_icon_1 Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding, Gunnar Sigurdsson, Carnegie Mellon University; Gul Varol, INRIA; Xiaolong Wang, CMU; Ali Farhadi, University of Washington; Ivan Laptev, ; Abhinav Gupta

P-1A-32. pdf_icon_1 Shuffle and Learn: Unsupervised Learning using Temporal Order Verification, Ishan Misra, CMU; Larry Zitnick, ; Martial Hebert, Carnegie Mellon University

P-1A-33. pdf_icon_1 DOC: Deep OCclusion Estimation From a Single Image, Peng Wang, UCLA; Alan Yuille, UCLA

P-1A-34. pdf_icon_1 RepMatch: Robust Feature Matching and Pose for Reconstructing Modern Cities, Wen-Yan Lin, ADSC; Siying Liu, UIUC; Nianjuan Jiang, Advanced Digital Sciences Center (ADSC); Minh Do, University of Illinois at Urbana-Champaign; ping tan, ; Jiangbo Lu, ADSC Singapore

P-1A-35. pdf_icon_1 Convolutional Oriented Boundaries, Kevis-Kokitsi Maninis, ETH Zürich; Jordi Pont-Tuset, ETHZ; Pablo Arbelaez, Universidad de los Andes, Colombia; Luc Van Gool, ETH Zurich

P-1A-36. pdf_icon_1 Superpixel Convolutional Networks using Bilateral Inceptions, Raghudeep Gadde, Ecole des Ponts Paris Tech; Varun Jampani, MPI-IS; Martin Kiefel, MPI for Intelligent Systems; Daniel Kappler, MPI Intelligent Systems; Peter Gehler

P-1A-37. pdf_icon_1 Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies, Emanuel Laude, Technical University of Munich; Thomas Möllenhoff, ; Michael Moeller, TUM; Jan Lellmann, ; Daniel Cremers

P-1A-38. pdf_icon_1 Building Dual-Domain Representations for Compression Artifacts Reduction, Jun Guo, Sun Yat-Sen University; Hongyang Chao, Sun Yat-sen University

P-1A-39. pdf_icon_1 Geometric Neural Phrase Pooling: Modeling the Spatial Co-occurrence of Neurons, Lingxi Xie, UCLA; Qi Tian, ; John Flynn, UCLA; Jingdong Wang, Microsoft Research; Alan Yuille, UCLA

P-1A-40. pdf_icon_1 Photo Aesthetics Ranking Network with Attributes and Content Adaptation, Shu Kong, UCI; Xiaohui Shen, Adobe; Zhe Lin, Adobe Systems, Inc.; Radomir Mech, Adobe; Charless Fowlkes

P-1A-41. pdf_icon_1 SDF-2-SDF: Highly Accurate 3D Object Reconstruction, Miroslava Slavcheva, Siemens AG; Wadim Kehl, TU München; Nassir Navab, ; Slobodan Ilic, TUM

P-1A-42. pdf_icon_1 Knowledge transfer for scene-specific motion prediction, Lamberto Ballan, Stanford University; Francesco Castaldo, Seconda Università di Napoli; Alexandre Alahi, Stanford University; Francesco Palmieri, Seconda Università di Napoli; Silvio Savarese

P-1A-43. pdf_icon_1 Weakly Supervised Localization using Deep Feature Maps, Archith Bency, UCSB; Heesung Kwon, US Army Research Laboratory; Hyungtae Lee, US Army Research Laboratory; Karthikeyan Shanmuga Vadivel, Synaptics; B.S. Manjunath, UCSB

P-1A-44. pdf_icon_1 Embedding Deep Metric for Person Re-identification A Study Against Large Variations, Hailin Shi, NLPR; Yang Yang, Institute of Automation; Xiangyu Zhu, ; Shengcai Liao, Institute of Automation, Chinese Academy of Sciences; Zhen Lei, ; Wei-Shi Zheng, ; Stan Li

P-1A-45. pdf_icon_1 Learning to Track at 100 FPS with Deep Regression Networks, David Held, UC Berkeley; Sebastian Thrun, Stanford; Silvio Savarese

P-1A-46. pdf_icon_1 Matching Handwritten Document Images, Praveen Krishnan, IIIT H; C.V. Jawahar, IIIT Hyderabad

P-1A-47. pdf_icon_1 Semantic Clustering for Robust Fine-Grained Scene Recognition, Marian George, ETH Zurich; Dixit Mandar, University of California, San Diego; Gábor Zogg, ETH Zurich; Nuno Vasconcelos

Demos
Tuesday, October 11; 11:00 – 12:30

D-1A-48. pdf_icon_1 Real-Time Monocular Segmentation and Pose Tracking of Multiple Objects, Henning Tjaden, RheinMain University of Applied Sciences; Ulrich Schwanecke, RheinMain University of Applied Sciences; Elmar Schömer, Johannes Gutenberg Universität Mainz

D-1A-49. pdf_icon_1 Live Template-based 3D tracking and 3D reconstruction of deformable objects in 2D videos, Toby Collins, ALCoV, Université d’Auvergne; Adrien Bartoli, ALCoV, Université d’Auvergne

Oral Session 1B: Scene Understanding
Tuesday, October 11; 14:00 – 15:00
Chairs: Cordelia Schmid (INRIA), Abhinav Gupta (CMU)

O-1B-01. pdf_icon_1 Ambient sound provides supervision for visual learning, Andrew Owens, MIT; Jiajun Wu, MIT; Josh Mcdermott, MIT; Antonio Torralba, MIT; William Freeman, MIT

O-1B-02. pdf_icon_1 Grounding of Textual Phrases in Images by Reconstruction, Anna Rohrbach; Marcus Rohrbach, UC Berkeley; Ronghang Hu, UC Berkeley; Trevor Darrell, UC Berkeley; Bernt Schiele

O-1B-03. pdf_icon_1 Improving Multi-label Learning with Missing Labels by Structured Semantic Correlations, Hao Yang, NTU; Joey Tianyi Zhou, IHPC; Jianfei Cai, NTU

O-1B-04. pdf_icon_1 Visual Relationship Detection with Language Priors, Cewu Lu, Stanford University; Ranjay Krishna, Stanford University; Michael Bernstein, Stanford University; Fei-Fei Li, Stanford University

Spotlight Session 1B: Recognition & Scene Understanding
Tuesday, October 11; 15:00 – 15:30
Chairs: Svetlana Lazebnik (UIUC), Andreas Geiger (MPI)

S-1B-05. pdf_icon_1 The Curious Robot: Learning Visual Representations via Physical Interactions, Lerrel Pinto, Carnegie Mellon University; Dhiraj Gandhi, ; Yuanfeng Han, ; Yong-Lae Park, ; Abhinav Gupta

S-1B-06. pdf_icon_1 Image Co-localization by Mimicking a Good Detector’s Confidence Score Distribution, Yao Li, University of Adelaide; Lingqiao Liu, University of Adelaide; Chunhua Shen, University of Adelaide; Anton Van den Hengel, University of Adelaide

S-1B-07. pdf_icon_1 Facilitating and Exploring Planar Homogeneous Texture for Indoor Scene Understanding, Shahzor Ahmad, National University of Singapo; Loong-Fah Cheong, National University of Singapore

S-1B-08. pdf_icon_1 An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild, Wei-Lun Chao, USC; Soravit Changpinyo, U. of Southern California; Boqing Gong, University of Central Florida; Fei Sha, UCLA

S-1B-09. pdf_icon_1 Modeling Context in Referring Expressions, Licheng Yu, University of North Carolina; Patrick Poirson, ; Shang Yang, ; Alex Berg, ; Tamara Berg, University on North Carolina

Poster Session 1B
Tuesday, October 11; 16:00 – 17:30
Chairs: Jasper Uijlings (University of Edinburgh), Roberto Valenti (Sightcorp)

O-1B-01. pdf_icon_1 Ambient sound provides supervision for visual learning, Andrew Owens, MIT; Jiajun Wu, MIT; Josh Mcdermott, MIT; Antonio Torralba, MIT; William Freeman, MIT

O-1B-02. pdf_icon_1 Grounding of Textual Phrases in Images by Reconstruction, Anna Rohrbach; Marcus Rohrbach, UC Berkeley; Ronghang Hu, UC Berkeley; Trevor Darrell, UC Berkeley; Bernt Schiele

O-1B-03. pdf_icon_1 Improving Multi-label Learning with Missing Labels by Structured Semantic Correlations, Hao Yang, NTU; Joey Tianyi Zhou, IHPC; Jianfei Cai, NTU

S-1B-09. pdf_icon_1 Modeling Context in Referring Expressions, Licheng Yu, University of North Carolina; Patrick Poirson, ; Shang Yang, ; Alex Berg, ; Tamara Berg, University on North Carolina

P-1B-10. pdf_icon_1 Taxonomy-Regularized Semantic Deep Convolutional Neural Networks, Wonjoon Goo, Seoul National University; Juyong Kim, Seoul National University; Gunhee Kim, Seoul National University; Sung Ju Hwang, UNIST

P-1B-11. pdf_icon_1 Playing for Data: Ground Truth from Computer Games, Stephan Richter, TU Darmstadt; Vibhav Vineet, Intel Labs; Stefan Roth, TU Darmstadt; Vladlen Koltun, Intel Labs

P-1B-12. pdf_icon_1 Human Re-identification in Crowd Videos using Personal, Social and Environmental Constraints, Shayan Modiri Assari, University of Central Florida; Haroon Idrees, University of Central Florida; Mubarak Shah, University of Central Florida

P-1B-13. pdf_icon_1 Revisiting additive quantization, Julieta Martinez, University of British Columbia; Joris Clement, University of British Columbia; Holger Hoos, University of British Columbia; Jim Little, University of British Columbia

P-1B-14. pdf_icon_1 Single Image Dehazing via Multi-Scale Convolutional Neural Networks, Wenqi Ren, Tianjin University; Si Liu, Chinese Academy of Sciences; Hua Zhang, iie.ac.cn; Jinshan Pan, UC Merced; Xiaochun Cao, Chinese Academy of Sciences; Ming-Hsuan Yang, UC Merced

P-1B-15. pdf_icon_1 Photometric Stereo under Non-uniform Light Intensities and Exposures, Donghyeon Cho, KAIST; Yasuyuki Matsushita, ; Yu-Wing Tai, Korea Advanced Institute of Science and Technology; In So Kweon, KAIST

P-1B-16. pdf_icon_1 Visual Motif Discovery via First-Person Vision, Ryo Yonetani, University of Tokyo; Kris Kitani, Carnegie Mellon University; Yoichi Sato

P-1B-17. pdf_icon_1 A Cluster Sampling Method for Image Matting via Sparse Coding, Xiaoxue Feng, Beihang University; Xiaohui Liang, State Key Lab. of Virtual Reality Technology and Systems; Zili Zhang, State Key Lab. of Virtual Reality Technology and Systems

P-1B-18. pdf_icon_1 What’s the Point: Semantic Segmentation with Point Supervision, Amy Bearman, Stanford University; Olga Russakovsky, Stanford University; Vittorio Ferrari, ; Fei-Fei Li, Stanford University

P-1B-19. pdf_icon_1 Fashion Landmark Detection in the Wild, Ziwei Liu, The Chinese Univ. of Hong Kong; Sijie Yan, The Chinese Univ. of Hong Kong; Ping Luo, The Chinese University of Hong Kong; Xiaogang Wang, The Chinese University of Hong Kong; Xiaoou Tang, Chinese University of Hong Kong

P-1B-20. pdf_icon_1 Person Re-identification by Unsupervised \ell_1 Graph Learning, Elyor Kodirov, QMUL; Tao Xiang, Queen Mary University of London; Zhenyong Fu, ; Shaogang Gong, Queen Mary University

P-1B-21. pdf_icon_1 Leveraging Visual Question Answering for Image-Caption Ranking, Xiao Lin, Virginia Tech; Devi Parikh, Virginia Tech

P-1B-22. pdf_icon_1 DAVE: A Unified Framework for Fast Vehicle Detection and Annotation, Yi Zhou, Northumbria University; Li Liu, Northumbria University; Ling Shao, Northumbria University; Matt Mellor, Createc Ltd.

P-1B-23. pdf_icon_1 Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input, Srinath Sridhar, MPI for Informatics; Franziska Mueller, MPI Informatics; Michael Zollhoefer, MPI Informatics; Dan Casas, MPI; Antti Oulasvirta, Aalto University; Christian Theobalt, MPI Informatics

P-1B-24. pdf_icon_1 DeepWarp: Photorealistic Image Resynthesis for Gaze Manipulation, Yaroslav Ganin, Skoltech; Daniil Kononenko, Skoltech; Diana Sungatullina, Skoltech; Victor Lempitsky, Skolkovo Institute of Science and Technology

P-1B-25. pdf_icon_1 Non-Rigid 3D Shape Retrieval via Large Margin Nearest Neighbor Embedding, Ioannis Chiotellis, TUM; Rudolph Triebel, TU Munich; Thomas Windheuser, TU Muenchen; Daniel Cremers

P-1B-26. pdf_icon_1 Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation, Xun Xu, Queen Mary University of Londo; Timothy Hospedales, Queen Mary University of London; Shaogang Gong, Queen Mary University

P-1B-27. pdf_icon_1 Fine-grained material classification using micro-geometry and reflectance, Christos Kampouris, Imperial College London; Stefanos Zafeiriou, Imperial College London; Abhijeet Ghosh, Imperial College London; Sotirios Malassiotis, Centre for Research and Technology Hellas

P-1B-28. pdf_icon_1 Support Discrimination Dictionary Learning for Image Classification, Yang Liu, University of Cambridge; Wei Chen, University of Cambridge; Qingchao Chen, University College London; Ian Wassell, University of Cambridge

P-1B-29. pdf_icon_1 Accelerating the Super-Resolution Convolutional Neural Network, CHAO DONG, The Chinese University of HK; Chen-Change Loy, the Chinese University of Hong Kong; Xiaoou Tang, Chinese University of Hong Kong

P-1B-30. pdf_icon_1 Symmetric Non-Rigid Structure from Motion for Category-Specific Object Structure Estimation, Yuan Gao, City University of Hong Kong; Alan Yuille, UCLA

P-1B-31. pdf_icon_1 Peak-Piloted Deep Network for Facial Expression Recognition, Xiangyun Zhao, University of California, San Diego; Xiaodan Liang, Sun Yat-sen University; Luoqi Liu, Qihoo/360; Teng Li, Anhui University; Yugang Han, 360 AI Institute; Nuno Vasconcelos, ; Shuicheng Yan

P-1B-32. pdf_icon_1 Is Faster R-CNN Doing Well for Pedestrian Detection?, Liliang Zhang, Sun Yat-sen University; Liang Lin, Sun Yat-sen University; Xiaodan Liang, Sun Yat-sen University; Kaiming He, Microsoft Research Asia

P-1B-33. pdf_icon_1 Coarse-to-fine Planar Regularization for Dense Monocular Depth Estimation, Stephan Liwicki, ; Christopher Zach, Toshiba Research Europe; Ondrej Miksik, University of Oxford; Philip Torr, Oxford University

P-1B-34. pdf_icon_1 Deep Attributes Driven Person Re-identification, Chi Su, Peking University; Shiliang Zhang, Peking University; Junliang Xing, Chinese Academy of Sciences; Wen Gao, Peking University; Qi Tian

P-1B-35. pdf_icon_1 An Occlusion-Resistant Ellipse Detection Method by Joining Coelliptic Arcs, Halil Cakir, Dumlupinar University; Cihan Topal, ; Cuneyt Akinlar

P-1B-36. pdf_icon_1 Branching Path Following for Graph Matching, Tao Wang, Beijing Jiaotong University; Haibin Ling, Temple University; Congyan Lang, Beijing Jiaotong University; Jun Wu, Beijing Jiaotong University

P-1B-37. pdf_icon_1 Higher Order Conditional Random Fields in Deep Neural Networks, Anurag Arnab, University of Oxford; Sadeep Jayasumana, University of Oxford; Shuai Zheng, University of Oxford; Philip Torr, Oxford University

P-1B-38. pdf_icon_1 LSTM-CF: Unifying Context Modeling and Fusion with LSTMs for RGB-D Scene Labeling, Zhen Li, The University of Hong Kong; Yukang Gan, Sun Yat-sen University; Xiaodan Liang, Sun Yat-sen University; Yizhou Yu, The University of Hong Kong; Hui Cheng, ; Liang Lin, Sun Yat-sen University

P-1B-39. pdf_icon_1 Stereo Video Deblurring, Anita Sellent, Technische Universität Darmstadt, Technische Universität Dresden; Carsten Rother, ; Stefan Roth, TU Darmstadt

P-1B-40. pdf_icon_1 Robust Image and Video Dehazing with Visual Artifact Suppression via Gradient Residual Minimization, Chen Chen, UIUC; Minh Do, University of Illinois at Urbana-Champaign; Jue Wang, Adobe Research

P-1B-41. pdf_icon_1 Smooth Neighborhood Structure Mining on Multiple Affinity Graphs with Applications to Context-sensitive Similarity, Song Bai, HUST; Shaoyan Sun, University of Science and Technology of China; Xiang Bai, Huazhong University of Science and Technology; Zhaoxiang Zhang, Institute of Automation, Chinese Academy of Sciences; Qi Tian

P-1B-42. pdf_icon_1 Title Generation for User Generated Videos, Kuo-Hao Zeng, National Tsing Hua University; Tseng-Hung Chen, National Tsing Hua University; Juan Carlos Niebles, Stanford University; Min Sun, National Tsing Hua University

P-1B-43. pdf_icon_1 Natural Image Matting using Deep Convolutional Neural Networks, Donghyeon Cho, KAIST; Yu-Wing Tai, Korea Advanced Institute of Science and Technology; In So Kweon, KAIST

P-1B-44. pdf_icon_1 Double-Opponent Vectorial Total Variation, Freddie Astrom, Heidelberg University; Christoph Schnoerr, Heidelberg University

P-1B-45. pdf_icon_1 Learning to Count with CNN Boosting, Elad Walach , Tel Aviv University; Lior Wolf

P-1B-46. pdf_icon_1 Amodal Instance Segmentation, Ke Li, UC Berkeley; Jitendra Malik, UC Berkeley

P-1B-47. pdf_icon_1 Perceptual Losses for Real-Time Style Transfer and Super-Resolution, Justin Johnson, Stanford University; Alexandre Alahi, Stanford University; Fei-Fei Li, Stanford University

Demos
Tuesday, October 11; 16:00 – 17:30

D-1B-48. pdf_icon_1 Object Detection and Retrieval using Natural Language, Ronghang Hu, UC, Berkeley and ICSI; XingChao Peng, Boston University; Tao Zhou, Canon USA Innovation Center; Jie Yu, Canon USA Innovation Center; Sandra Skaff, Canon USA Innovation Center; Trevor Darrell, UC, Berkeley and ICSI; Kate Saenko, Boston University

D-1B-49. pdf_icon_1 ZFace, László A. Jeni, Carnegie Mellon University; Jeffrey F. Cohn, Carnegie Mellon University and University of Pittsburgh; Takeo Kanade, Carnegie Mellon University

Oral Session 2A: Optimization
Wednesday, October 12; 09:00 – 10:00
Chairs: Carsten Rother (TU Dresden), Ramin Zabih (Cornell)

O-2A-01. pdf_icon_1 An Efficient Fusion Move Algorithm for the Minimum Cost Lifted Multicut Problem, Thorsten Beier, University of Heidelberg; Bjoern Andres, Max-Planck Institute for Informatics; Ullrich Koethe, University of Heidelberg; Fred Hamprecht, Heidelberg University

O-2A-02. pdf_icon_1 \ell^0-Sparse Subspace Clustering, Yingzhen Yang, UIUC; Jiashi Feng, NUS; Nebojsa Jojic, Microsoft Research; Jianchao Yang, Snapchat; Thomas Huang, UIUC

O-2A-03. pdf_icon_1 Normalized Cut meets MRF, Meng Tang, UWO; Dmitrii Marin, UWO; Ismail Ben Ayed, École de technologie supérieure; Yuri Boykov, University of Western Ontario

O-2A-04. pdf_icon_1 Fast Global Registration, Qian-Yi Zhou, Intel Labs; Jaesik Park, Intel Labs; Vladlen Koltun, Intel Labs

Spotlight Session 2A: Optimization & Mathematical Models
Wednesday, October 12; 10:00 – 10:30
Chairs: Frederik Kahl (Chalmers University of Technology), Christoph Lampert (IST Austria)

S-2A-05. pdf_icon_1 Polysemous Codes, Matthijs Douze; Herve Jegou; Florent Perronnin, Facebook

S-2A-06. pdf_icon_1 Binary Hashing with Semidefinite Relaxation and Augmented Lagrangian, Thanh-Toan Do, SUTD; Dung Doan, SUTD; Duc-Thanh Nguyen, University of Wollongong; Ngai-Man Cheung, SUTD

S-2A-07. pdf_icon_1 Efficient Continuous Relaxations for Dense CRF, Rudy Bunel, University of Oxford; Alban Desmaison, University of Oxford; M. Pawan Kumar, University of Oxford; Philip Torr, Oxford University; Pushmeet Kohli, Microsoft Research Cambridge

S-2A-08. pdf_icon_1 Complexity of Discrete Energy Minimization Problems, Mengtian Li, Carnegie Mellon University; Alexander Shekhovtsov, Graz University of Technology; Daniel Huber

S-2A-09. pdf_icon_1 A Convex Solution to Spatially-Regularized Correspondence Problems, Thomas Windheuser, TU Muenchen; Daniel Cremers

Poster Session 2A
Wednesday, October 12; 11:00 – 12:30
Chairs: Jasper Uijlings (University of Edinburgh), Roberto Valenti (Sightcorp)

O-2A-02. pdf_icon_1 \ell^0-Sparse Subspace Clustering, Yingzhen Yang, UIUC; Jiashi Feng, NUS; Nebojsa Jojic, Microsoft Research; Jianchao Yang, Snapchat; Thomas Huang, UIUC

O-2A-03. pdf_icon_1 Normalized Cut meets MRF, Meng Tang, UWO; Dmitrii Marin, UWO; Ismail Ben Ayed, École de technologie supérieure; Yuri Boykov, University of Western Ontario

O-2A-04. pdf_icon_1 Fast Global Registration, Qian-Yi Zhou, Intel Labs; Jaesik Park, Intel Labs; Vladlen Koltun, Intel Labs

S-2A-05. pdf_icon_1 Polysemous Codes, Matthijs Douze; Herve Jegou; Florent Perronnin, Facebook

S-2A-06. pdf_icon_1 Binary Hashing with Semidefinite Relaxation and Augmented Lagrangian, Thanh-Toan Do, SUTD; Dung Doan, SUTD; Duc-Thanh Nguyen, University of Wollongong; Ngai-Man Cheung, SUTD

S-2A-08. pdf_icon_1 Complexity of Discrete Energy Minimization Problems, Mengtian Li, Carnegie Mellon University; Alexander Shekhovtsov, Graz University of Technology; Daniel Huber

S-2A-09. pdf_icon_1 A Convex Solution to Spatially-Regularized Correspondence Problems, Thomas Windheuser, TU Muenchen; Daniel Cremers

P-2A-10. pdf_icon_1 Jensen Bregman LogDet Divergence Optimal Filtering in the Manifold of Positive Definite Matrices, Yin Wang, northeastern University; Octavia Camps, Northeastern University; Mario Sznaier, Northeastern University; Biel Roig Solvas, Northeastern University

P-2A-11. pdf_icon_1 Reflection Symmetry Detection via Appearance of Structure Descriptor, Ibragim Atadjanov, KHU; Seungkyu Lee, Kyung Hee University

P-2A-12. pdf_icon_1 Faceless Person Recognition; Privacy Implications in Social Media, Seong Joon Oh, MPI-INF; Rodrigo Benenson, MPI Informatics; Mario Fritz, ; Bernt Schiele

P-2A-13. pdf_icon_1 Segmental Spatiotemporal CNNs for Fine-grained Action Segmentation, Colin Lea, Johns Hopkins University; Austin Reiter, Johns Hopkins University; Rene Vidal, Johns Hopkins University; Gregory Hager, Johns Hopkins University

P-2A-14. pdf_icon_1 Structure from motion on a sphere, Jonathan Ventura, University of Colorado Colorad

P-2A-15. pdf_icon_1 Evaluation of LBP and Deep Texture Descriptors with A New Robustness Benchmark, Li Liu, NUDT; Paul Fieguth, ; Xiaogang Wang, The Chinese University of Hong Kong; Matti Pietikainen, University of Oulu; Dewen Hu

P-2A-16. pdf_icon_1 MS-Celeb-1M: A Dataset and Benchmark for Large Scale Face Recognition, Yandong Guo, Microsoft Corporation; Lei Zhang, Microsoft Corporation; Yuxiao Hu, Microsoft Corporation; Xiaodong He, Microsoft Corporation; Jianfeng Gao, Microsoft Corporation

P-2A-17. pdf_icon_1 Hierarchical Beta Process with Gaussian Process prior for Hyperspectral Image Super Resolution, Naveed Akhtar, Uni. of Western Australia; Faisal Shafait, ; Ajmal Mian, UWA

P-2A-18. pdf_icon_1 A 4D Light-Field Dataset and CNN Architectures for Material Recognition, Ting-Chun Wang, UC Berkeley; Jun-Yan Zhu, UC BERKELEY; Hiroaki Ebi, University of California, San ; Manmohan Chandraker, NEC Labs America; Alexei Efros, ; Ravi Ramamoorthi

P-2A-19. pdf_icon_1 Graph-Based Consistent Matching for Structure-from-Motion, Tianwei Shen, HKUST; Siyu Zhu, HKUST; Tian Fang, HKUST; Runze Zhang, HKUST; Long Quan, The Hong Kong University of Science and Technology

P-2A-20. pdf_icon_1 All-around Depth from Small Motion with A Spherical Panoramic Camera, Sunghoon Im, KAIST; Hyowon Ha, KAIST; Francois Rameau, ; Hae-Gon Jeon, KAIST; Gyeongmin Choe, KAIST; In So Kweon, KAIST

P-2A-21. pdf_icon_1 On Shape Reconstruction from Implicit Forms, Li Wang, Inria; Franck Hétroy-Wheeler, University Grenoble Alpes; Edmond Boyer, Inria

P-2A-22. pdf_icon_1 Multi-attributed Graph Matching with Multi-layer Random Walks, Han-Mu Park, GIST; Kuk-Jin Yoon, Gwangju Institute of Science and Technology

P-2A-23. pdf_icon_1 Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimation, Wadim Kehl, TU München; Fausto Milletari, Technische Universität München; Federico Tombari, University of Bologna; Slobodan Ilic, TUM; Nassir Navab

P-2A-24. pdf_icon_1 A Neural Approach to Blind Motion Deblurring, Ayan Chakrabarti, TTI-Chicago

P-2A-25. pdf_icon_1 Joint Face Representation Adaptation and Clustering in Videos, Zhanpeng Zhang, The Chinese University of HK; Ping Luo, The Chinese University of Hong Kong; Chen-Change Loy, the Chinese University of Hong Kong; Xiaoou Tang, Chinese University of Hong Kong

P-2A-26. pdf_icon_1 Uncovering Symmetries in Polynomial Systems, Viktor Larsson, Lund University; Kalle Astroem, Lund University

P-2A-27. pdf_icon_1 ATGV-Net: Accurate Depth Super-Resolution, Gernot Riegler, Graz University of Technology; Matthias Rüther, Graz University of Technology; Horst Bischof, Graz University of Technology

P-2A-28. pdf_icon_1 Indoor-Outdoor 3D Reconstruction Alignment, Andrea Cohen, ETHZ; Johannes Schönberger, ETH Zürich; Pablo Speciale, ETHZ; Torsten Sattler, ETH Zurich; Jan-Michael Frahm, ; Marc Pollefeys, ETH

P-2A-29. pdf_icon_1 The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition, Jonathan Krause, Stanford University; Benjamin Sapp, Google; Andrew Howard, Google; Howard Zhou, Google; Alexander Toshev, Google; Tom Duerig, Google; James Philbin, Google; Fei-Fei Li, Stanford University

P-2A-30. pdf_icon_1 A simple hierarchical pooling data structure for loop closure, Xiaohan Fei, UCLA; Konstantine Tsotsos, ; Stefano Soatto, University of California, Los Angeles

P-2A-31. pdf_icon_1 A Versatile Approach for Solving PnP, PnPf, and PnPfr Problems, Gaku Nakano, NEC Corporation

P-2A-32. pdf_icon_1 Depth Map Super Resolution by Deep Multi-Scale Guidance, Tak-Wai Hui, The Chinese University of HK; Chen-Change Loy, the Chinese University of Hong Kong; Xiaoou Tang, Chinese University of Hong Kong

P-2A-33. pdf_icon_1 SEAGULL: Seam-guided Local Alignment for Parallax-tolerant Image Stitching, Kaimo Lin, NUS; Nianjuan Jiang, Advanced Digital Sciences Center (ADSC); Loong-Fah Cheong, National University of Singapore; Minh Do, University of Illinois at Urbana-Champaign; Jiangbo Lu, ADSC Singapore

P-2A-34. pdf_icon_1 Grid Loss: Detecting Occluded Faces, Michael Opitz, Graz University of Technology; Georg Waltner, TU Graz; Georg Poier, Graz University of Technology; Horst Possegger, Graz University of Technology; Horst Bischof, Graz University of Technology

P-2A-35. pdf_icon_1 Large-scale R-CNN with Classifier Adaptive Quantization, Ryota Hinami, The University of Tokyo; Shin’ichi Satoh, National Institute of Informatics, Japan

P-2A-36. pdf_icon_1 Face Detection with End-to-End Integration of a ConvNet and a 3D Model, Yunzhu Li, Peking University; Benyuan Sun, PKU; Tianfu Wu, UCLA; Yizhou Wang, Peking University

P-2A-37. pdf_icon_1 Large Scale Asset Extraction for Urban Images, Lama Affara, KAUST; Liangliang Nan, KAUST; Bernard Ghanem, KAUST; Peter Wonka

P-2A-38. pdf_icon_1 Multi-label Active Learning Based on Maximum Correntropy Criterion: Towards Robust and Discriminative Labeling, Zengmao Wang, Wuhan University; Bo Du, ; Lefei Zhang, Wuhan University; Liangpei Zhang, Wuhan University; Meng Fang, ; Dacheng Tao, University of Technology, Sydney

P-2A-39. pdf_icon_1 Shading-aware Multi-view Stereo, Fabian Langguth, TU Darmstadt; Kalyan Sunkavalli, Adobe Systems Inc.; Sunil Hadap, ; Michael Goesele, TU Darmstadt

P-2A-40. pdf_icon_1 Fine-Scale Surface Normal Estimation using a Single NIR Image, Youngjin Yoon, KAIST; Gyeongmin Choe, KAIST; Namil Kim, KAIST; Joon-Young Lee, Adobe ; In So Kweon, KAIST

P-2A-41. pdf_icon_1 Pixelwise View Selection for Unstructured Multi-View Stereo, Johannes Schönberger, ETH Zürich; Enliang Zheng, UNC Chapel Hill; Marc Pollefeys, ETH; Jan-Michael Frahm

P-2A-42. pdf_icon_1 Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation, Golnaz Ghiasi, University of California, Irvine; Charless Fowlkes

P-2A-43. pdf_icon_1 Generic 3D Representation via Pose Estimation and Matching, Amir Zamir, Stanford University; Pulkit Agrawal, UC Berkeley; Silvio Savarese, ; Tilman Wekel, Stanford University; Colin Wei, Stanford University; Jitendra Malik, UC Berkeley

P-2A-44. pdf_icon_1 Hand pose estimation from local surface normals, Chengde Wan, ETHZ; Angela Yao, University of Bonn; Luc Van Gool, ETH Zurich

P-2A-45. pdf_icon_1 Abundant Inverse Regression using Sufficient Reduction and its applications, Hyunwoo Kim, UW-Madison; Brandon Smith, UW-Madison; Nagesh Adluru, UW-Madison; Charles Dyer, University of Wisconsin – Madison; Sterling Johnson, UW-Madison; Vikas Singh, University of Wisconsin-Madison

P-2A-46. pdf_icon_1 Learning Diverse Models: The Coulomb Structured Support Vector Machine, Martin Schiegg, University of Heidelberg; Robert Bosch GmbH; Ferran Diego, University of Heidelberg, HCI; Fred Hamprecht, Heidelberg University

P-2A-47. pdf_icon_1 Pose Hashing with Microlens Arrays, Ian Schillebeeckx, Washington University in St. L; Robert Pless, Washington University in St. Louis

Demos
Wednesday, October 12; 11:00 – 12:30

D-2A-48. pdf_icon_1 Multi-person Body Pose Estimation, Eldar Insafutdinov, Max Planck Institute for Informatics; Leonid Pishchulin, Max Planck Institute for Informatics; Evgeny Levinkov, Max Planck Institute for Informatics; Bjoern Andres, Max Planck Institute for Informatics; Mykhaylo Andriluka, Max Planck Institute for Informatics; Bernt Schiele, Max Planck Institute for Informatics

D-2A-49. pdf_icon_1 Realtime Multiperson Pose Estimation , Zhe Cao, Carnegie Mellon University; ShihEn Wei, Carnegie Mellon University; Tomas Simon, Carnegie Mellon University; Yaser Sheikh, Carnegie Mellon University

Oral Session 2B: Image & Video Processing
Wednesday, October 12; 14:00 – 15:00
Chairs: Larry Zitnick (Facebook), Peter Gehler (MPI)

O-2B-01. pdf_icon_1 The Fast Bilateral Solver, Jonathan Barron, Google; Ben Poole, Stanford University

O-2B-02. pdf_icon_1 Phase-based Modification Transfer for Video, Simone Meyer, ETH Zurich; Alexander Sorkine-Hornung, Disney Research Zurich; Markus Gross, ETH Zurich

O-2B-03. pdf_icon_1 Colorful Image Colorization, Richard Zhang, UC Berkeley; Phillip Isola, MIT; Alexei Efros

O-2B-04. pdf_icon_1 Focal flow: Measuring depth and velocity from defocus and differential motion, Emma Alexander, Harvard University; Qi Guo, Harvard University; Sanjeev Koppal, University of Florida; Steven Gortler; Todd Zickler

Spotlight Session 2B – Image Processing & Computational Photography
Wednesday, October 12; 15:00 – 15:30
Chairs: Stefan Roth (TU Darmstadt), Joost van de Weijer (CVC)

S-2B-05. pdf_icon_1 An evaluation of computational imaging techniques for heterogeneous inverse scattering, Ioannis Gkioulekas, Harvard University; Todd Zickler, ; Anat Levin, Weizmann Institute of Science

S-2B-06. pdf_icon_1 Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks, Chuan Li, University of Mainz; Michael Wand, University of Mainz

S-2B-07. pdf_icon_1 Fast Guided Global Interpolation for Depth and Motion, Yu Li, Advanced Digital Sci. Center; Dongbo Min, Chungnam National University; Minh Do, University of Illinois at Urbana-Champaign; Jiangbo Lu, ADSC Singapore

S-2B-08. pdf_icon_1 Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs, Lei Xiao, University of British Columbia; Jue Wang, Adobe Research; Wolfgang Heidrich, KAUST; Michael Hirsch

S-2B-09. pdf_icon_1 Multi-View Inverse Rendering under Arbitrary Illumination and Albedo, Kichang Kim, Tokyo Institute of Technology; Akihiko Torii, Tokyo Institute of Technology; Masatoshi Okutomi, Tokyo Institute of Technology

Poster Session 2B
Wednesday, October 12; 16:00 – 17:30
Chairs: Jasper Uijlings (University of Edinburgh), Roberto Valenti (Sightcorp)

O-2B-01. pdf_icon_1 The Fast Bilateral Solver, Jonathan Barron, Google; Ben Poole, Stanford University

O-2B-02. pdf_icon_1 Phase-based Modification Transfer for Video, Simone Meyer, ETH Zurich; Alexander Sorkine-Hornung, Disney Research Zurich; Markus Gross, ETH Zurich

O-2B-03. pdf_icon_1 Colorful Image Colorization, Richard Zhang, UC Berkeley; Phillip Isola, MIT; Alexei Efros

S-2B-06. pdf_icon_1 Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks, Chuan Li, University of Mainz; Michael Wand, University of Mainz

P-2B-10. pdf_icon_1 DAPs: Deep Action Proposals for Action Understanding, Victor Escorcia, KAUST; FABIAN CABA HEILBRON, KAUST; Juan Carlos Niebles, Stanford University; Bernard Ghanem, KAUST

P-2B-11. pdf_icon_1 A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning., Terrell Mundhenk, Lawrence Livermore National L.; Wesam Sakla, LLNL; Goran Konjevod, LLNL; Kofi Boakye, LLNL

P-2B-12. pdf_icon_1 Reliable Attribute-Based Object Recognition Using High Predictive Value Classifiers, Wentao Luan, University of Maryland; Yezhou Yang, University of Maryland; Cornelia Fermuller, University of Maryland; John Baras, University of Maryland

P-2B-13. pdf_icon_1 Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition, Jun Liu, Nanyang Technological University; Amir Shahroudy, Nanyang Technological University; Dong Xu, ; Gang Wang

P-2B-14. pdf_icon_1 Going Further with Point Pair Features, Stefan Hinterstoisser, Google; Vincent Lepetit, ; Kurt Konolige, Google; Naresh Rajkumar, Google

P-2B-15. pdf_icon_1 Webly-supervised Video Recognition by Mutually Voting for Relevant Web Images and Web Video Frames, Chuang Gan, Tsinghua University; Chen Sun, USC; Lixin Duan, Amazon; Boqing Gong, University of Central Florida

P-2B-16. pdf_icon_1 HFS: Hierarchical Feature Selection for Efficient Image Segmentation, Ming-Ming Cheng, Nankai University; Yun Liu, Nankai University; Qibin Hou, Nankai University; Jiawang Bian, Nankai University; Philip Torr, Oxford University; Shimin Hu, Tsinghua University; Zhuowen Tu

P-2B-17. pdf_icon_1 Generating Visual Explanations, Lisa Anne Hendricks, UC Berkeley; Zeynep Akata, ; Marcus Rohrbach, UC Berkeley; Jeff Donahue, UC Berkeley; Bernt Schiele, ; Trevor Darrell

P-2B-18. pdf_icon_1 Marker-less 3D Human Motion Capture with Monocular Image Sequence and Height-Maps, Yu Du, ; Yongkang Wong, ; Yonghao Liu, ; Feilin Han, Zhejiang University; Yilin Gui, ; Zhen Wang, ; Mohan Kankanhalli, National University of Singapore; Weidong Geng

P-2B-19. pdf_icon_1 Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons, Piotr Koniusz, NICTA; Anoop Cherian, ANU; Fatih Porikli, ANU / NICTA

P-2B-20. pdf_icon_1 Manhattan-world Urban Reconstruction from Point Clouds, Minglei Li, Nanjing University of Aeronautics and Astronautics; Peter Wonka, ; Liangliang Nan, KAUST

P-2B-21. pdf_icon_1 From Multiview Image Curves to 3D Drawings, Anil Usumezbas, Brown University; Ricardo Fabbri, State University of Rio de Janeiro; Benjamin Kimia, Brown University

P-2B-22. pdf_icon_1 Shape from Selfies : Human Body Shape Estimation using CCA Regression Forests, Endri Dibra, ETH Zurich; Cengiz Oztireli, ETH Zurich; Remo Ziegler, Vizrt; Markus Gross, ETH Zurich

P-2B-23. pdf_icon_1 Can we Jointly Register and Reconstruct Creased Surfaces by Shape-from-Template Accurately?, Mathias Gallardo, ISIT, UMR 6284 CNRS/UdA; Toby Collins, Universite d’Auvergne; Adrien Bartoli, Universite d’Auvergne

P-2B-24. pdf_icon_1 Distractor-supported single target tracking in extremely cluttered scenes, Jingjing Xiao, University of Birmingham; LINBO QIAO, ; Rustam Stolkin, ; Aleš Leonardis

P-2B-25. pdf_icon_1 Connectionist Temporal Modeling for Weakly Supervised Action Labeling, De-An Huang, Stanford University; Fei-Fei Li, Stanford University; Juan Carlos Niebles, Stanford University

P-2B-26. pdf_icon_1 Deep Joint Image Filter, Yijun Li, UC Merced; Jia-Bin Huang, University of Illinois, Urbana-Champaign; Narendra Ahuja, University of Illinois at Urbana-Champaign; Ming-Hsuan Yang, UC Merced

P-2B-27. pdf_icon_1 Efficient Multi-Frequency Phase Unwrapping using Kernel Density Estimation, Felix Jaremo-Lawin, Linkoping University; Per-Erik Forssen, Linkoping University; Hannes Ovren, Linköping university

P-2B-28. pdf_icon_1 A Multi-Scale CNN for Affordance Segmentation in RGB Images, Anirban Roy, Oregon State University; Sinisa Todorovic, Oregon State University

P-2B-29. pdf_icon_1 Hierarchical Dynamic Parsing and Encoding for Action Recognition, Bing Su, Chinese Academy of Sciences; JIAHUAN ZHOU, Northwestern University; Xiaoqing Ding, Tsinghua University; Hao Wang, Chinese Academy of Sciences; Ying Wu, Northwestern University

P-2B-30. pdf_icon_1 Distinct Class Saliency Maps for Weakly Supervised Semantic Segmentation, Wataru Shimoda, The University of Electro-Communications, Tokyo; Keiji Yanai, The University of Electro-Communications

P-2B-31. pdf_icon_1 A Diagram Is Worth A Dozen Images, Aniruddha Kembhavi, AI2; Michael Salvato, Allen Institute for Artificial; Eric Kolve, Allen Institute for AI; Minjoon Seo, University of Washington; Hannaneh Hajishirzi, University of Washington; Ali Farhadi, University of Washington

P-2B-32. pdf_icon_1 Automatic Attribute Discovery with Neural Activations, Sirion Vittayakorn, University of North Carolina at Chapel Hill; Takayuki Umeda, NTT; Kazuhiko Murasaki, NTT; Kyoko Sudo, NTT; Takayuki Okatani, Tohoku University; Kota Yamaguchi, Tohoku University

P-2B-33. pdf_icon_1 “What happens if…” Learning to predict the effect of forces in images, Roozbeh Mottaghi, Allen Institute for AI; Mohammad Rastegari, AI2; Abhinav Gupta, ; Ali Farhadi, University of Washington

P-2B-34. pdf_icon_1 View synthesis by appearance flow, Tinghui Zhou, UC Berkeley; Shubham Tulsiani, UC Berkeley; Weilun Sun, UC Berkeley; Jitendra Malik, UC Berkeley; Alexei Efros

P-2B-35. pdf_icon_1 Top-down Learning for Structured Labeling with Convolutional Pseudoprior, Saining Xie, UCSD; Xun Huang, ; Zhuowen Tu

P-2B-36. pdf_icon_1 Generative Image Modeling using Style and Structure Adversarial Networks, Xiaolong Wang, CMU; Abhinav Gupta

P-2B-37. pdf_icon_1 Joint learning of Semantic and Latent Attributes, Peixi Peng, Peking University; Yonghong Tian, Peking University; Tao Xiang, Queen Mary University of London; Yaowei Wang, Beijing Institute of Technology; Tiejun Huang, Peking University

P-2B-38. pdf_icon_1 A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection, Zhaowei Cai, ucsd.edu; Quanfu Fan, IBM; Rogerio Feris, IBM Research Center; Nuno Vasconcelos

P-2B-39. pdf_icon_1 Deep Specialized Network for Illuminant Estimation, Wu Shi, The Chinese University of HK; Chen-Change Loy, the Chinese University of Hong Kong; Xiaoou Tang, Chinese University of Hong Kong

P-2B-40. pdf_icon_1 Weakly-Supervised Semantic Segmentation using Motion Cues, Pavel Tokmakov, INRIA Grenoble Rhône-Alpes; Karteek Alahari, Inria; Cordelia Schmid

P-2B-41. pdf_icon_1 Human-In-The-Loop Person Re-Identification, Hanxiao Wang, Queen Mary, Univ. of London; Shaogang Gong, Queen Mary University; Xiatian Zhu, ; Tao Xiang, Queen Mary University of London

P-2B-42. pdf_icon_1 Real-Time Monocular Segmentation and Pose Tracking of Multiple Objects, Henning Tjaden, RheinMain University of Applied Sciences; Ulrich Schwanecke, RheinMain University of Applied Sciences; Elmar Schömer, Johannes Gutenberg University Mainz

P-2B-43. pdf_icon_1 Estimation of Human Body Shape in Motion with Wide Clothing, Jinlong Yang, Inria; Jean-Sebastien Franco, LJK, Université Grenoble Alpes, Inria; Franck Hétroy-Wheeler, University Grenoble Alpes; Stefanie Wuhrer, INRIA

P-2B-44. pdf_icon_1 A Shape-based Approach for Salient Object Detection Using Deep Learning, Jongpil Kim, Rutgers Univ.; Vladimir Pavlovic, Rutgers University

P-2B-45. pdf_icon_1 Fast Optical Flow using Dense Inverse Search, Till Kroeger, ETH Zuerich; Radu Timofte, ETH Zurich; Dengxin Dai, ETH Zurich; Luc Van Gool, ETH Zurich

P-2B-46. pdf_icon_1 Global Registration of 3D Point Sets via LRS decomposition, Federica Arrigoni, University of Udine; Beatrice Rossi, AST; Andrea Fusiello, University of Udine

P-2B-47. pdf_icon_1 Recognition from Hand Cameras: A Revisit with Deep Learning, Cheng-Sheng Chan, ; Shou-Zhong CHEN, ; Pei-Xuan Xie, ; CHIUNG-CHIH CHANG, ; Min Sun, National Tsing Hua University

Demos
Wednesday, October 12; 16:00 – 17:30

D-2B-48. pdf_icon_1 Mobile AR for Dentistry: Virtual Try-On in Live 3D, Gábor Sörös, Kapanu AG and ETH Zurich; Marcel Lancelle, Kapanu AG and ETH Zurich; Nicolas Degen, Kapanu AG and ETH Zurich; Roland Mörzinger, Kapanu AG and ETH Zurich

D-2B-49. pdf_icon_1 Facial Tracking, Nial Stewart, ULSee Inc.

Oral Session 3A: Learning
Thursday, October 13; 09:00 – 10:00
Chairs: Raquel Urtasun (University of Toronto), Iasonas Kokkinos (ECP)

O-3A-01. pdf_icon_1 XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks, Mohammad Rastegari, AI2; Vicente Ordonez, Allen Institute for AI; Joe Redmon; Ali Farhadi, University of Washington

O-3A-02. pdf_icon_1 Top-down Neural Attention by Excitation Backprop, Jianming Zhang; Zhe Lin, Adobe Systems, Inc.; Jonathan Brandt; Xiaohui Shen, Adobe; Stan Sclaroff, Boston University

O-3A-03. pdf_icon_1 Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network, Sifei Liu, UC Merced; Jinshan Pan, UC Merced; Ming-Hsuan Yang, UC Merced

O-3A-04. pdf_icon_1 Learning Representations for Automatic Colorization, Gustav Larsson, University of Chicago; Michael Maire, Toyota Technological Institute at Chicago; Greg Shakhnarovich, TTI Chicago, USA

Spotlight Session 3A: CNNs
Thursday, October 13; 10:00 – 10:30
Chairs: Laurens van der Maaten (Facebook), Xiaogang Wang (CUHK)

S-3A-05. pdf_icon_1 Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation, Muhammad Ghifary, VUW, Weta Digital; Bastiaan Kleijn, Victoria University of Wellington; Mengjie Zhang, Victoria University of Wellington; David Balduzzi, Victoria University of Wellington; Wen Li, ETH Zurich

S-3A-06. pdf_icon_1 Learning without Forgetting, Zhizhong Li, UIUC; Derek Hoiem, UIUC

S-3A-07. pdf_icon_1 Identity Mappings in Deep Residual Networks, Kaiming He, Microsoft Research Asia; Xiangyu Zhang, Xi’an Jiaotong University; Shaoqing Ren, University of Science & Technology of China; Jian Sun, Microsoft Research China

S-3A-08. pdf_icon_1 Deep Networks with Stochastic Depth, Gao Huang, Cornell University; Yu Sun, Cornell University; Zhuang Liu, Tsinghua University; Daniel Sedra, Cornell University; Kilian Weinberger, Cornell University

S-3A-09. pdf_icon_1 Less is More: Towards Compact CNNs, Hao Zhou, University of Maryland; Jose M. Alvarez, Data61 / CSIRO; Fatih Porikli, Australian National University

Poster Session 3A
Thursday, October 13; 11:00 – 12:30
Chairs: Jasper Uijlings (University of Edinburgh), Roberto Valenti (Sightcorp)

O-3A-02. pdf_icon_1 Top-down Neural Attention by Excitation Backprop, Jianming Zhang; Zhe Lin, Adobe Systems, Inc.; Jonathan Brandt; Xiaohui Shen, Adobe; Stan Sclaroff, Boston University

O-3A-03. pdf_icon_1 Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network, Sifei Liu, UC Merced; Jinshan Pan, UC Merced; Ming-Hsuan Yang, UC Merced

S-3A-06. pdf_icon_1 Learning without Forgetting, Zhizhong Li, UIUC; Derek Hoiem, UIUC

S-3A-09. pdf_icon_1 Less is More: Towards Compact CNNs, Hao Zhou, University of Maryland; Jose M. Alvarez, Data61 / CSIRO; Fatih Porikli, Australian National University

P-3A-10. pdf_icon_1 Unsupervised Visual Representation Learning by Graph-based Consistent Constraints, Dong Li, Tsinghua University; Wei-Chih Hung, USC; Jia-Bin Huang, University of Illinois at Urbana-Champaign; Shengjin Wang, wgsgj@tsinghua.edu.cn; Narendra Ahuja, University of Illinois at Urbana-Champaign; Ming-Hsuan Yang, UC Merced

P-3A-11. pdf_icon_1 Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation, Alexander Kolesnikov, IST Austria; Christoph Lampert, IST Austria

P-3A-12. pdf_icon_1 Patch-based low-rank matrix completion for learning of shape and motion models from few training samples, Jan Ehrhardt, ; Matthias Wilms, University of Lübeck; Heinz Handels

P-3A-13. pdf_icon_1 Chained Predictions Using Convolutional Neural Networks, Georgia Gkioxari, ; Navdeep Jaitly, Google; Alexander Toshev, Google

P-3A-14. pdf_icon_1 Multi-region two-stream R-CNN for action detection, Xiaojiang Peng, INRIA; Cordelia Schmid

P-3A-15. pdf_icon_1 Semantic Co-segmentation in Videos, Yi-Hsuan Tsai, UC Merced; Guangyu Zhong, DalianUniversityofTechnolog; Ming-Hsuan Yang, UC Merced

P-3A-16. pdf_icon_1 Attribute2Image: Conditional Image Generation from Visual Attributes, Xinchen Yan, University of Michigan; Jimei Yang, Abode Research; Kihyuk Sohn, NEC Lab; Honglak Lee

P-3A-17. pdf_icon_1 Modeling Context Between Objects for Referring Expression Understanding, Varun Nagaraja, University of Maryland; Vlad Morariu, University of Maryland; Larry Davis, University of Maryland

P-3A-18. pdf_icon_1 Friction from Reflectance: Deep Reflectance Codes for Predicting Physical Surface Properties from One-Shot In-Field Reflectance, Hang Zhang, Rutgers University; Kristin Dana, Rutgers University; Ko Nishino, Drexel University

P-3A-19. pdf_icon_1 Saliency Detection with Recurrent Fully Convolutional Networks, Linzhao Wang; Lijun Wang, Dalian University of Technology; Huchuan Lu, ; Pingping Zhang, Dalian University of Technolog; Xiang Ruan

P-3A-20. pdf_icon_1 Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks, Junyuan Xie, University of Washington; Ross Girshick, ; Ali Farhadi, University of Washington

P-3A-21. pdf_icon_1 Temporal Model Adaptation for Person Re-Identification, Niki Martinel, University of Udine; Abir Das, University of Massachusetts Lowell; Christian Micheloni, University of Udine; Amit Roy-Chowdhury, UC Riverside

P-3A-22. pdf_icon_1 Image Quality Assessment Using Similar Scene as Reference, Yudong Liang, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University; Jinjun Wang, ; Xingyu Wan, xjtu.edu.cn; Yihong Gong, ; Nanning Zheng, Xi;an Jiaotong University

P-3A-23. pdf_icon_1 MOON: A Mixed Objective Optimization Network for the Recognition of Facial Attributes, Ethan Rudd, UCCS; Manuel Günther, UCCS; Terrance Boult, University of Colorado Colorado Springs

P-3A-24. pdf_icon_1 Degeneracies in Rolling Shutter SfM, Cenek Albl, Czech Technical University; Akihiro Sugimoto, NII; Tomas Pajdla

P-3A-25. pdf_icon_1 Deep Deformation Network for Object Landmark Localization, Xiang Yu, NEC Labs; Feng Zhou, NEC Lab; Manmohan Chandraker, NEC Labs America

P-3A-26. pdf_icon_1 Learning Visual Storylines with Skipping Recurrent Neural Networks, Gunnar Sigurdsson, Carnegie Mellon University; Xinlei Chen, CMU; Abhinav Gupta

P-3A-27. pdf_icon_1 Towards large-scale city reconstruction from satellites, liuyun Duan, ; Florent Lafarge

P-3A-28. pdf_icon_1 Weakly Supervised Object Localization Using Size Estimates, Miaojing SHI, University of Edinburgh; Vittorio Ferrari

P-3A-29. pdf_icon_1 Supervised Transformer Network for Efficient Face Detection, Dong Chen, Microsoft Research; Gang Hua, Microsoft Research; Fang Wen, Microsoft Research; Jian Sun, Microsoft Research China

P-3A-30. pdf_icon_1 A Geometric Approach to Image Labeling, Freddie Astrom, Heidelberg University; Stefania Petra, ; Bernhard Schmitzer, Université Paris-Dauphine; Christoph Schnoerr, Heidelberg University

P-3A-31. pdf_icon_1 ActionSnapping: Motion-based Video Synchronization, Jean-Charles Bazin, ETHZ; Alexander Sorkine-Hornung, Disney Research Zurich

P-3A-32. pdf_icon_1 A Minimal Solution for Non-Perspective Pose Estimation from Line Correspondences, Gim Hee Lee, NUS

P-3A-33. pdf_icon_1 Natural Image Stitching with the Global Similarity Prior, Yu-Sheng Chen, National Taiwan University; Yung-Yu Chuang, National Taiwan University

P-3A-34. pdf_icon_1 Minimal Solvers for Generalized Pose and Scale Estimation from Two Rays and One Point, Federico Camposeco, ETHZ; Torsten Sattler, ETH Zurich; Marc Pollefeys, ETH

P-3A-35. pdf_icon_1 Learning to Hash with Binary Deep Neural Network, Thanh-Toan Do, SUTD; Dung Doan, SUTD; Ngai-Man Cheung, SUTD

P-3A-36. pdf_icon_1 Automatically selecting inference algorithms for discrete energy minimisation, Paul Henderson, University of Edinburgh; Vittorio Ferrari

P-3A-37. pdf_icon_1 Ego2Top: Matching Viewers in Egocentric and Top-view Videos, Shervin Ardeshir, University of Central Florida; Ali Borji, University of Cenreal Florida

P-3A-38. pdf_icon_1 Online Action Detection, Roeland De Geest , KU Leuven; Stratis Gavves, University of Amsterdam; Amir Ghodrati, ; Zhenyang Li, ; Cees Snoek, University of Amsterdam; Tinne Tuytelaars, KU Leuven

P-3A-39. pdf_icon_1 Cross-modal Supervision for Learning Active Speaker Detection in Video, Punarjay Chakravarty, KU Leuven; Tinne Tuytelaars, KU Leuven

P-3A-40. pdf_icon_1 Recurrent Temporal Deep Field for Semantic Video Labeling, Peng Lei, Oregon State University; Sinisa Todorovic, Oregon State University

P-3A-41. pdf_icon_1 Ultra Resolution by Discriminative Generative Networks, Xin Yu, Australian National University; Fatih Porikli, Australian National University

P-3A-42. pdf_icon_1 A Discriminative Framework for Anomaly Detection in Large Videos, Allison Del Giorno, Carnegie Mellon University; Martial Hebert, Carnegie Mellon University; J. Andrew Bagnell, Carnegie Mellon University

P-3A-43. pdf_icon_1 ContextLocNet: Context-aware Deep Network Models for Weakly Supervised Localization, Vadim Kantorov, INRIA; Maxime Oquab, INRIA; Minsu Cho, INRA; Ivan Laptev

P-3A-44. pdf_icon_1 Network flow formulations for Learning Binary Hashing, Lopamudra Mukherjee, University of Wisc Whitewater; Jiming Peng, University of Houston; Trevor Sigmund, Univ of Wisconsin Whitewater; Vikas Singh, University of Wisconsin-Madison

P-3A-45. pdf_icon_1 SPICE: Semantic Propositional Image Caption Evaluation, Peter Anderson, Australian National University; Basura Fernando, ANU; Mark Johnson, Macquarie University; Stephen Gould, Australian National University

P-3A-46. pdf_icon_1 Transfer Neural Trees for Heterogeneous Domain Adaptation, Wei Yu Chen, NTU; Academia Sinica; Tzu-Ming Hsu, ; Yao-Hung Tsai, Academia Sinica; Yu-Chiang Frank Wang, Academia Sinica; Ming-Syan Chen, National Taiwan University

P-3A-47. pdf_icon_1 Tracking Persons-of-Interest via Adaptive Discriminative Features, Shun Zhang, Xi’an Jiaotong University; Yihong Gong, ; Jia-Bin Huang, University of Illinois at Urbana-Champaign; Jongwoo Lim, Hanyang University; Jinjun Wang, ; Narendra Ahuja, University of Illinois at Urbana-Champaign; Ming-Hsuan Yang, UC Merced

Demos
Thursday, October 13; 11:00 – 12:30

D-3A-48. pdf_icon_1 DeepXCam: Very Fast CNN-based Mobile Applications: Multiple Style Transfer and Object Recognition, Ryusuke Tanno, The University of Electro-Communication, Tokyo; Wataru Shimoda, The University of Electro-Communication, Tokyo; Keiji Yanai, The University of Electro-Communication, Tokyo

D-3A-49. pdf_icon_1 DeepWarp: Photorealistic Image Resynthesis for Gaze Manipulation, Yaroslav Ganin, Skolkovo Institute of Science and Technology; Daniil Kononenko, Skolkovo Institute of Science and Technology; Diana Sungatullina, Skolkovo Institute of Science and Technology; Victor Lempitsky, Skolkovo Institute of Science and Technology

Spotlight Session 3B-3C: 3D & Structure from Motion
Thursday, October 13; 14:00 – 15:00
Chairs: Daniel Cremers (TU Munchen), Tomas Pajdla(CVUT)

S-3B-05. pdf_icon_1 When is Rotations Averaging Hard?, Kyle Wilson, Washington College; David Bindel, Cornell University; Noah Snavely

S-3B-06. pdf_icon_1 Capturing Dynamic Textured Surfaces of Moving Targets, Ruizhe Wang, USC; Lingyu Wei, USC; Etienne Vouga, UT Austin; Qixing Huang, TTI-Chicago; Duygu Ceylan, Adobe Research; Gerard Medioni, University of Southern California; Hao Li, USC

S-3B-07. pdf_icon_1 ShapeFit and ShapeKick for Robust, Scalable Structure from Motion, Tom Goldstein, University of Maryland, College Park; Paul Hand, ; Vladislav Voroninski, MIT; Stefano Soatto, University of California, Los Angeles; Choongbum Lee

S-3B-08. pdf_icon_1 Heat Diffusion Long-Short Term Memory Learning for 3D Shape Analysis, Fan Zhu, NYUAD; Jin Xie, NYUAD; Yi Fang, New York University Abu Dhabi

S-3B-09. pdf_icon_1 Multi-view 3D Models from Single Images With a Convolutional Network, Maxim Tatarchenko, University of Freiburg; Alexey Dosovitskiy, University of Freiburg; Thomas Brox

S-3C-05. pdf_icon_1 Linear depth estimation from an uncalibrated, monocular polarisation image, William Smith, University of York; Ravi Ramamoorthi, ; Silvia Tozza

S-3C-06. pdf_icon_1 Online Variational Bayesian Motion Averaging, Guillaume Bourmaud, Toshiba CRL

S-3C-07. pdf_icon_1 Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fields, Seungryong Kim, Yonsei University; Kihong Park, Yonsei Univ.; Kwanghoon Sohn, Yonsei university; Stephen Lin, Microsoft Research Asia, China

S-3C-08. pdf_icon_1 ObjectNet3D: A Large Scale Database for 3D Object Recognition, Yu Xiang, University of Michigan; Wonhui Kim, University of Michigan; Wei Chen, Stanford University; Jingwei Ji, Stanford University; Christopher Choy, Stanford University; Hao Su, Stanford; Roozbeh Mottaghi, Allen Institute for AI; Leonidas J. Guibas, ; Silvio Savarese

S-3C-09. pdf_icon_1 Branching Gaussian Processes with Applications to Spatiotemporal Reconstruction of 3D Trees, Kyle Simek, University of Arizona; Ravishankar Palanivelu, University of Arizona; Kobus Barnard, University of Arizona

Poster Session 3B
Thursday, October 13; 15:00 – 16:30
Chairs: Jasper Uijlings (University of Edinburgh), Roberto Valenti (Sightcorp)

S-3B-05. pdf_icon_1 When is Rotations Averaging Hard?, Kyle Wilson, Washington College; David Bindel, Cornell University; Noah Snavely

S-3B-08. pdf_icon_1 Heat Diffusion Long-Short Term Memory Learning for 3D Shape Analysis, Fan Zhu, NYUAD; Jin Xie, NYUAD; Yi Fang, New York University Abu Dhabi

S-3B-09. pdf_icon_1 Multi-view 3D Models from Single Images With a Convolutional Network, Maxim Tatarchenko, University of Freiburg; Alexey Dosovitskiy, University of Freiburg; Thomas Brox

P-3B-10. pdf_icon_1 Extending Long Short-Term Memory for Multi-View Structured Learning, Shyam Sundar Rajagopalan, University of Canberra; Louis-Philippe Morency, Carnegie Mellon University; Tadas Baltrušaitis, Carnegie Mellon University; Roland Goecke, University of Canberra

P-3B-11. pdf_icon_1 Gated Bi-directional CNN for Object Detection, Xingyu Zeng, The Chinese University of Hong Kong; Wanli Ouyang, Chinese University of Hong Kong; Bin Yang, NLPR, CASIA; Junjie Yan, National Laboratory of Pattern Recognition, Chinese Academy of Sciences; Xiaogang Wang, The Chinese University of Hong Kong

P-3B-12. pdf_icon_1 Graph Based Skeleton Motion Representation and Similarity Measurement for Action Recognition, Pei Wang, Chinese Academy of Sciences; Chunfeng Yuan, ; Weiming Hu, ; Bing Li, ; yanning Zhang, Northwestern Polytechnical University

P-3B-13. pdf_icon_1 Reliable Fusion of ToF and Stereo Depth Driven by Confidence Measures, Giulio Marin, University of Padova; Pietro Zanuttigh, University of Padova; Stefano Mattoccia, University of Bologna

P-3B-14. pdf_icon_1 Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs, Siddhartha Chandra, INRIA; Iasonas Kokkinos, INRIA

P-3B-15. pdf_icon_1 Kernel-Based Supervised Discrete Hashing for Image Retrieval, Xiaoshuang Shi, University of Florida; Fuyong Xing, University of Florida; Jinzheng Cai, University of Florida; Zizhao Zhang, University of Florida; Yuanpu Xie, University of Florida; Lin Yang, University of Florida

P-3B-16. pdf_icon_1 Iterative Reference Driven Metric Learning for Signer Independent Isolated Sign Language Recognition, Fang Yin, ICT,CAS; Xiujuan Chai, ICT, CAS; Xilin Chen, Institute of Computing Technology, Chinese Academy of Sciences

P-3B-17. pdf_icon_1 Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering, Huijuan Xu, UMass Lowell; Kate Saenko, University of Massachusetts Lowel

P-3B-18. pdf_icon_1 Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks, Li Shen, UCAS; Zhouchen Lin, Peking University; Qingming Huang, University of Chinese Academy of Sciences

P-3B-19. pdf_icon_1 Counting in The Wild, Carlos Arteta, Oxford University; Victor Lempitsky, Skolkovo Institute of Science and Technology; Andrew Zisserman, University of Oxford

P-3B-20. pdf_icon_1 A Discriminative Feature Learning Approach for Deep Face Recognition, Yandong Wen, ; Kaipeng Zhang, ; Zhifeng LI, SIAT, CAS; Yu Qiao, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences

P-3B-21. pdf_icon_1 Network of Experts for Large-Scale Image Categorization, Karim Ahmed, Dartmouth; Mohammad Haris Baig, Dartmouth College; Lorenzo Torresani, Dartmouth College

P-3B-22. pdf_icon_1 Zero-Shot Recognition via Structured Prediction, Ziming Zhang, Boston University; Venkatesh Saligrama,

P-3B-23. pdf_icon_1 A Generalized Successive Shortest Paths Solver for Tracking Dividing Targets, Carsten Haubold, University of Heidelberg; Janez Ales, ; Steffen Wolf, ; Fred Hamprecht, Heidelberg University

P-3B-24. pdf_icon_1 Accurate and Linear Time Pose Estimation from Points and Lines, Alexander Vakhitov, SPbSU; Jan Funke, Institut de Robòtica i Informà; Francesc Moreno-Noguer, Institut de Robotica i Informatica Industrial (UPC/CSIC)

P-3B-25. pdf_icon_1 Pseudo-Geometric Formulation for Fitting Equidistant Parallel Lines, FAISAL AZHAR, HP Labs; STEPHEN POLLARD, HP Labs.

P-3B-26. pdf_icon_1 Towards perspective-free object counting with deep learning, Daniel Oñoro Rubio, University of Alcalá; Roberto Lopez-Sastre, University of Alcala

P-3B-27. pdf_icon_1 Information Bottleneck Domain Adaptation with Privileged Information for Visual Recognition, Saeid Motiian, West Virginia University; Gianfranco Doretto, West Virginia University

P-3B-28. pdf_icon_1 Template-free 3D Reconstruction of Poorly-textured Nonrigid Surfaces, Xuan Wang, Xi’an Jiaotong University; Mathieu Salzmann, EPFL; Fei Wang, Xi’an Jiaotong University; Jizhong Zhao, Xi’an Jiaotong university

P-3B-29. pdf_icon_1 FigureSeer: Parsing Result-Figures in Research Papers, Noah Siegel, ; Zachary Horvitz, ; Roie Levin, ; Santosh Kumar Divvala, Allen Institute for Artificial Intelligence; Ali Farhadi, University of Washington

P-3B-30. pdf_icon_1 Approximate search with quantized sparse representations, Himalaya Jain, Inria; Patrick Perez, Technicolor, France; Rémi Gribonval, ; joaquin Zepeda, Technicolor; Hervé Jegou,

P-3B-31. pdf_icon_1 Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition, Cesar De Souza, Xerox Research Center Europe; Adrien Gaidon, ; Eleonora Vig, German Aerospace Center; Antonio Lopez, Centro de Visio per Computador, UAB

P-3B-32. pdf_icon_1 Human pose estimation via Convolutional Part Heatmap Regression, Adrian Bulat, University of Nottingham; Georgios Tzimiropoulos, Nottingham University

P-3B-33. pdf_icon_1 Collaborative Layer-wise Discriminative Learning in Deep Neural Networks, XIAOJIE JIN, National Univ. of Singapore; YUNPENG CHEN, NUS; Jian Dong, Qihoo/360; Jiashi Feng, NUS; Shuicheng Yan,

P-3B-34. pdf_icon_1 Deep Decoupling of Defocus and Motion Blur for Dynamic Segmentation, Abhijith Punnappurath, IIT Madras; YOGESH BALAJI, IIT MADRAS; Mahesh Mohan M R, IIT Madras; A N Rajagopalan, Indian Institute of Technology, Madras

P-3B-35. pdf_icon_1 Video Summarization with Long Short-term Memory, Ke Zhang, USC; Wei-Lun Chao, USC; Fei Sha, UCLA; Kristen Grauman, University of Texas at Austin

P-3B-36. pdf_icon_1 Leaving Some Stones Unturned: Dynamic Feature Prioritization for Activity Detection in Streaming Video, Yu-Chuan Su, University of Texas at Austin; Kristen Grauman, University of Texas at Austin

P-3B-37. pdf_icon_1 Robust and Accurate Line- and/or Point-Based Pose Estimation without Manhattan Assumptions, Yohann Salaun, LIGM-Imagine; Renaud Marlet, ; Pascal Monasse, Universite Paris-Est

P-3B-38. pdf_icon_1 MARLow: A Joint Multiplanar Autoregressive and Low-Rank Approach for Image Completion, Mading Li, Peking University; Jiaying Liu, Peking University; Zhiwei Xiong, ; Xiaoyan Sun, ; Zongming Guo, Peking University

P-3B-39. pdf_icon_1 An Uncertain Future: Forecasting from Static Images using Variational Autoencoders, Jacob Walker, Carnegie Mellon University; Carl Doersch, Carnegie Mellon University; Abhinav Gupta, ; Martial Hebert, Carnegie Mellon University

P-3B-40. pdf_icon_1 Carried Object Detection based on an Ensemble of Contour Exemplars, FARNOOSH GHADIRI, Laval University; ROBERT BERGEVIN, Laval university; GUILLAUME-ALEXANDRE BILODEAU, École Polytechnique de Montréal

P-3B-41. pdf_icon_1 Query-Focused Extractive Video Summarization, Aidean Sharghi Karganroodi, University of Central Florida; Boqing Gong, University of Central Florida; Mubarak Shah, University of Central Florida

P-3B-42. pdf_icon_1 Temporal Segment Networks: Towards Good Practices for Deep Action Recognition, Limin Wang, ETHZ; Yuanjun Xiong, The Chinese University of HK; Zhe Wang, SIAT, CAS; Yu Qiao, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Dahua Lin, CUHK; Xiaoou Tang, Chinese University of Hong Kong; Luc Van Gool, ETH Zurich

P-3B-43. pdf_icon_1 PlaNet – Photo Geolocation with Convolutional Neural Networks, Tobias Weyand, Google; Ilya Kostrikov, RWTH Aachen University; James Philbin, Zoox

P-3B-44. pdf_icon_1 Detecting Text in Natural Image with Connectionist Text Proposal Network, Zhi Tian, SIAT; Weilin Huang, The University of Oxford; Tong He, Wuhan University; Pan He, SIAT,MMLAB; Yu Qiao, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences

P-3B-45. pdf_icon_1 Face recognition using a unified 3D morphable model, GUOSHENG HU, INRIA; fei Yan, ; chi-Ho Chan, CVSSP, University of Surrey; Weihong Deng, BUPT; william Christmas, CVSSP; Josef Kittler, University of Surrey; Neil Robertson, Queen’s University of Belfast

P-3B-46. pdf_icon_1 Augmented Feedback in Semantic Segmentation under Image Level Supervision, Xiaojuan Qi, CUHK; Zhengzhe liu, ; Jianping Shi, SenseTime; Hengshuang Zhao, ; Jiaya Jia, Chinese University of Hong Kong

P-3B-47. pdf_icon_1 Towards Viewpoint Invariant 3D Human Pose Estimation, Albert Haque, Stanford University; Boya Peng, Stanford University; Zelun Luo, Stanford University; Alexandre Alahi, Stanford University; Serena Yeung, Stanford University; Fei-Fei Li, Stanford University

Demos
Thursday, October 13; 15:00 – 16:30

D-3B-48. pdf_icon_1 RGB-D SLAM with fast and robust relocalization and HDR texture mapping, Shuda Li, University of Bristol; Andrew Calway, University of Bristol

D-3B-49. pdf_icon_1 Extracting Driving Behavior: Global Metric Localization from Dashcam Videos in the Wild, Shao-Pin Chang, National Tsing Hua University; Jui-Ting Chien, National Tsing Hua University; Fu-En Wang, National Tsing Hua University; Shang-Da Yang, National Tsing Hua University; Hwann-Tzong Chen, National Tsing Hua University; Min Sun, National Tsing Hua University

Poster Session 3C
Thursday, October 13; 16:45 – 18:15
Chairs: Jasper Uijlings (University of Edinburgh), Roberto Valenti (Sightcorp)

S-3C-05. pdf_icon_1 Linear depth estimation from an uncalibrated, monocular polarisation image, William Smith, University of York; Ravi Ramamoorthi, ; Silvia Tozza

S-3C-06. pdf_icon_1 Online Variational Bayesian Motion Averaging, Guillaume Bourmaud, Toshiba CRL

P-3C-10. pdf_icon_1 Tracking Completion, Yao Sui, University of Kansas; Guanghui Wang, University of Kansas; Yafei Tang, China Unicom Research; Li Zhang, Tsinghua University

P-3C-11. pdf_icon_1 Inter-Battery Topic Representation Learning, Cheng Zhang, KTH Royal Institute of Technology; Hedvig Kjellstrom, ; Carl Henrik Ek

P-3C-12. pdf_icon_1 Online Adaptation for Joint Scene and Object Classification, Md Jawadul Bappy, University of California, Riverside; Sujoy Paul, University of California, Riverside; Amit Roy-Chowdhury, UC Riverside

P-3C-13. pdf_icon_1 Real-Time Facial Segmentation and Performance Capture from RGB Input, Shunsuke Saito, USC; Tianye Li, USC; Hao Li, USC

P-3C-14. pdf_icon_1 Learning Temporal Transformations From Time-Lapse Videos, Yipin Zhou, UNC; Tamara Berg, University on North Carolina

P-3C-15. pdf_icon_1 Interactive Image Segmentation Using Constrained Dominant Sets, Eyasu Zemene, Ca’Foscari University; Marcello Pelillo, University of Venice

P-3C-16. pdf_icon_1 Deep Markov Random Field for Image Modeling, Zhirong Wu, The Chinese University of Hong Kong; Dahua Lin, CUHK; Xiaoou Tang, Chinese University of Hong Kong

P-3C-17. pdf_icon_1 A Symmetry Prior for Convex Variational 3D Reconstruction, Pablo Speciale, ETHZ; Martin R. Oswald, ETH Zurich; Andrea Cohen, ETHZ; Marc Pollefeys, ETH

P-3C-18. pdf_icon_1 SPLeaP: Soft Pooling of Learned Parts for Image Classification, Praveen Kulkarni, Technicolor; Frederic Jurie, University of Caen; joaquin Zepeda, Technicolor; Patrick Perez, Technicolor, France; Louis Chevallier, Technicolor

P-3C-19. pdf_icon_1 Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation, Qi Ye, ; Shanxin Yuan, Imperial College London; Tae-Kyun Kim, Imperial College London

P-3C-20. pdf_icon_1 VolumeDeform: Real-time Volumetric Non-rigid Reconstruction, Matthias Innmann, University Erlangen-Nuremberg; Michael Zollhoefer, MPI Informatics; Matthias Niessner, Stanford University; Christian Theobalt, MPI Informatics; Marc Stamminger, University of Erlangen-Nuremberg

P-3C-21. pdf_icon_1 \piMatch: Monocular vSLAM and Piecewise Planar Reconstruction using Fast Plane Correspondences, Carolina Raposo, University of Coimbra; Joao Barreto, Universidade de Coimbra

P-3C-22. pdf_icon_1 Peripheral Expansion of Depth Information via Layout Estimation with Fisheye Camera, Alejandro Perez-Yus, Universidad de Zaragoza; Gonzalo Lopez-Nicolas, Universidad de Zaragoza; Josechu Guerrero, Universidad de Zaragoza

P-3C-23. pdf_icon_1 Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation, Fatemehsadat Saleh, The Australian National University/CSIRO; Mohammad Sadegh Aliakbarian, National ICT Australia; Mathieu Salzmann, EPFL; Lars Petersson, NICTA; Stephen Gould, Australian National University; Jose M. Alvarez, Data61 / CSIRO

P-3C-24. pdf_icon_1 It’s Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videos, Pia Bideau, Umass Amherst; Erik Miller

P-3C-25. pdf_icon_1 Kernelized Subspace Ranking for Saliency Detection, Tiantian Wang, DalianUniversityofTechnology; Lihe Zhang, DalianUniversityofTechnology; Huchuan Lu, ; Chong Sun, ; Jinqing Qi, DalianUniversityofTechnology

P-3C-26. pdf_icon_1 Depth-aware Motion Magnification, Julian Kooij, Delft University of Technology; Jan van Gemert, Delft University of Technology

P-3C-27. pdf_icon_1 Stacked Hourglass Networks for Human Pose Estimation, Alejandro Newell, University of Michigan; Kaiyu Yang, University of Michigan; Jia Deng, University of Michigan

P-3C-28. pdf_icon_1 Real-time Large-Scale Dense 3D Reconstruction with Loop Closure, Olaf Kahler, University of Oxford; David Murray, Oxford; Victor Prisacariu, Oxford

P-3C-29. pdf_icon_1 Pixel-Level Domain Transfer, Donggeun Yoo, KAIST; Namil Kim, KAIST; Sunggyun Park, KAIST; Anthony Paek, Lunit Inc.; In So Kweon, KAIST

P-3C-30. pdf_icon_1 Accelerating Convolutional Neural Networks with Dominant Convolutional Kernel and Knowledge Pre-regression, Zhenyang Wang, Tsinghua University; Zhidong Deng, Tsinghua University; Shiyao Wang, Tsinghua University

P-3C-31. pdf_icon_1 Learning Social Etiquette: Human TrajectoryUnderstanding in Crowded Scenes, Alexandre Robicquet, Stanford university; Amir Sadeghian, stanford university; Alexandre Alahi, Stanford University; Silvio Savarese

P-3C-32. pdf_icon_1 Bayesian Image based 3D Pose Estimation, Valsamis Ntouskos, Sapienza University of Rome; Fiora Pirri, University of Rome, Sapienza; Marta Sanzari, Sapienza

P-3C-33. pdf_icon_1 Efficient and Robust Semi-supervised Learning over a Sparse-Regularized Graph, Hang Su, Tsinghua University; Jun Zhu, Tsinghua University; Zhaozheng Yin, Missouri University of Science and Technology; Yinpeng Dong, Tsinghua University; Bo Zhang, Tsinghua University

P-3C-34. pdf_icon_1 Novel Coplanar Line-points Invariants for Robust Line Matching Across Views, Qi Jia, Dalian university of technology; Xinkai Gao, Dalian university of technolgy; Xin Fan, Dalian University of Technolog; Zhongxuan Luo, Dalian university of technology; Haojie Li, Dalian university of technology; Ziyao Chen, Dalian university of technology

P-3C-35. pdf_icon_1 Sparse Representation Based Complete Kernel Marginal Fisher Analysis Framework for Computational Art Painting Categorization, Ajit Puthenputhussery, New Jersey Institute of Technology; Qingfeng Liu, New Jersey Institute of Techno; Chengjun Liu, New Jersey Institute of Technology

P-3C-36. pdf_icon_1 3D-R2N2: A unified approach for single and multi-view 3D object reconstruction, Christopher Choy, Stanford University; Danfei Xu, Stanford University; JunYoung Gwak, Stanford; Kevin Chen, Stanford University; Silvio Savarese

P-3C-37. pdf_icon_1 Cascaded Continuous Regression for Real-time Incremental Face Tracking, Enrique Sánchez-Lozano, University of Nottingham; Brais Martinez, University of Nottingham; Georgios Tzimiropoulos, Nottingham University; Michel Valstar, Nottingham University

P-3C-38. pdf_icon_1 Real-Time Visual Tracking: Promoting the Robustness of Correlation Filter Learning, Yao Sui, University of Kansas; Ziming Zhang, Boston University; Guanghui Wang, University of Kansas; Yafei Tang, China Unicom Research; Li Zhang, Tsinghua University

P-3C-39. pdf_icon_1 Deep Self-Correlation Descriptor for Dense Cross-Modal Correspondence, Seungryong Kim, Yonsei University; Dongbo Min, Chungnam National University; Stephen Lin, Microsoft Research Asia, China; Kwanghoon Sohn, Yonsei university

P-3C-40. pdf_icon_1 Structured Matching for Phrase Localization, Mingzhe Wang, University of Michgan; Mahmoud Azab, University of Michigan; Noriyuki Kojima, University of Michigan ; Rada Mihalcea, University of Michigan; Jia Deng, University of Michigan

P-3C-41. pdf_icon_1 Crossing-line Crowd Counting with Two-phase Deep Neural Networks, Zhuoyi Zhao, CUHK; Hongsheng Li, CUHK; Rui Zhao, The Chinese University of Hong Kong; Xiaogang Wang, The Chinese University of Hong Kong

P-3C-42. pdf_icon_1 Revisiting Visual Question Answering Baselines, Allan Jabri, Facebook AI Research; Armand Joulin, Facebook AI Research; Laurens van der Maaten

P-3C-43. pdf_icon_1 Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue, Ravi Garg, University of Adelaide; Vijay Kumar, University of Adelaide; Gustavo Carneiro, University of Adelaide; Ian Reid, University of Adelaide

P-3C-44. pdf_icon_1 A Continuous Optimization Approach for Efficient and Accurate Scene Flow, Zhaoyang Lv, Georgia Tech; Chris Beall, Georgia Tech; Pablo Alcantarilla, iRobot Corporation; Fuxin Li, Oregon State University; Zsolt Kira, Georgia Tech Research Institute; Frank Dellaert

P-3C-45. pdf_icon_1 Improving Multi-Frame Data Association with Sparse Representations for Robust Near-Online Multi-Object Tracking, Loïc Fagot-Bouquet, CEA LIST; Romaric Audigier, CEA LIST; Yoann Dhome, CEA LIST; Frédéric Lerasle, LAAS CNRS

P-3C-46. pdf_icon_1 Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification, Rahul Rama Varior, NTU Singapore; Mrinal Haloi, Nanyang technological Universi; Gang Wang

P-3C-47. pdf_icon_1 Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs, Youbao Tang, Harbin Institute of Technology; Xiangqian Wu, Harbin Institute of Technology

Demos
Thursday, October 13; 16:45 – 18:15

D-3C-48. pdf_icon_1 Aerial Tracking Evaluation using Unreal Engine 4 and VR, Matthias Mueller, King Abdullah University of Science and Technology; Neil Smith, King Abdullah University of Science and Technology; Bernard Ghanem, KAUST

D-3C-49. pdf_icon_1 From Low- to High-Quality Depth Sensors for 3D Object Reconstruction with SDF-2-SDF, Miroslava Slavcheva, Technische Universität München and Siemens AG; Wadim Kehl, Technische Universität München; Nassir Navab, Technische Universität München; Slobodan Ilic, Technische Universität München and Siemens AG

Oral Session 4A: 3D
Friday, October 14; 09:00 – 10:00
Chairs: Jan-Michael Frahm (UNC), Hongdong Li (ANU)

O-4A-01. pdf_icon_1 Real-Time 3D Reconstruction and 6-DoF Tracking with an Event Camera, Hanme Kim, Imperial College London; Stefan Leutenegger, Imperial College London; Andrew Davison

O-4A-02. pdf_icon_1 Single Image 3D Interpreter Network, Jiajun Wu, MIT; Tianfan Xue, MIT; Joseph Lim, MIT; Yuandong Tian, FAIR; Joshua Tenenbaum, MIT; Antonio Torralba, ; William Freeman

O-4A-03. pdf_icon_1 Dual Structured Light 3D using a 1D Sensor, Jian Wang, Carnegie Mellon University; Aswin Sankaranarayanan, Carnegie Mellon University; Mohit Gupta, ; Srinivasa Narasimhan, CMU

O-4A-04. pdf_icon_1 Shape acquisition and registration for 3D endoscope based on grid pattern projection, Ryo Furukawa, Hiroshima City University; Hiroki Morinaga, Kagoshima Univeristy; Yoji Sanomura, Hiroshima University; Shinji Tanaka, Hiroshima University; Shigeto Yoshida, Hiroshima General Hospital of West Japan Railway Company; Hiroshi Kawasaki, Kagoshima University

Spotlight Session 4A: Feature Extraction & Matching
Friday, October 14; 10:00 – 10:30
Chairs: Thomas Brox (U Freiburg), Andrea Vedaldi (U Oxford)

S-4A-05. pdf_icon_1 Target Response Adaptation for Correlation Filter Tracking, Adel Bibi, KAUST; Matthias Mueller, KAUST; Bernard Ghanem, KAUST

S-4A-06. pdf_icon_1 Learning Image Matching by Simply Watching Video, Gucan Long, NUDT; Laurent Kneip, Australian National University; Jose M. Alvarez, Data61 / CSIRO; Hongdong Li, ; Xiaohu Zhang, NUDT; Qifeng Yu, NUDT

S-4A-07. pdf_icon_1 A Distance for HMMs based on Aggregated Wasserstein Metric and State Registration, Yukun Chen, Penn State University; Jianbo Ye, College of Information Sciences and Technology, Penn State University; Jia Li, Department of Statistics, Penn State University

S-4A-08. pdf_icon_1 LIFT: Learned Invariant Feature Transform, Kwang Yi, EPFL; Eduard Trulls, EPFL; Vincent Lepetit, ; Pascal Fua,

S-4A-09. pdf_icon_1 Learning a Predictable and Generative Vector Representation for Objects, Rohit Girdhar, CMU; David Fouhey, Carnegie Mellon University; Mikel Rodriguez, MITRE INRIA; Abhinav Gupta

Poster Session 4A
Friday, October 14; 11:00 – 12:30
Chairs: Jasper Uijlings (University of Edinburgh), Roberto Valenti (Sightcorp)

O-4A-01. pdf_icon_1 Real-Time 3D Reconstruction and 6-DoF Tracking with an Event Camera, Hanme Kim, Imperial College London; Stefan Leutenegger, Imperial College London; Andrew Davison

O-4A-02. pdf_icon_1 Single Image 3D Interpreter Network, Jiajun Wu, MIT; Tianfan Xue, MIT; Joseph Lim, MIT; Yuandong Tian, FAIR; Joshua Tenenbaum, MIT; Antonio Torralba, ; William Freeman

O-4A-03. pdf_icon_1 Dual Structured Light 3D using a 1D Sensor, Jian Wang, Carnegie Mellon University; Aswin Sankaranarayanan, Carnegie Mellon University; Mohit Gupta, ; Srinivasa Narasimhan, CMU

S-4A-05. pdf_icon_1 Target Response Adaptation for Correlation Filter Tracking, Adel Bibi, KAUST; Matthias Mueller, KAUST; Bernard Ghanem, KAUST

S-4A-08. pdf_icon_1 LIFT: Learned Invariant Feature Transform, Kwang Yi, EPFL; Eduard Trulls, EPFL; Vincent Lepetit, ; Pascal Fua,

S-4A-09. pdf_icon_1 Learning a Predictable and Generative Vector Representation for Objects, Rohit Girdhar, CMU; David Fouhey, Carnegie Mellon University; Mikel Rodriguez, MITRE INRIA; Abhinav Gupta

P-4A-10. pdf_icon_1 HouseCraft: Building Houses from Rental Ads and Street Views, Hang Chu, University of Toronto; Shenlong Wang, University of Toronto; Raquel Urtasun, ; Sanja Fidler, University of Toronto

P-4A-11. pdf_icon_1 Superpixel-based Two-view Deterministic Fitting for Multiple-structure Data, Guobao Xiao, Xiamen University; Hanzi Wang, ; Yan Yan, ; David Suter

P-4A-12. pdf_icon_1 Instance-sensitive Fully Convolutional Networks, Jifeng Dai, Microsoft Research Asia; Kaiming He, Microsoft Research Asia; Yi Li, Tsinghua University; Shaoqing Ren, University of Science & Technology of China; Jian Sun, Microsoft Research China

P-4A-13. pdf_icon_1 Domain Adaptive Fisher Vector for Visual Recognition, Li Niu, NTU; Jianfei Cai, ; Dong Xu

P-4A-14. pdf_icon_1 Deep Robust Encoder through Locality Preserving Low-Rank Dictionary, Zhengming Ding, Northeastern University; Ming Shao, Northeastern University; Yun Fu, Northeastern University

P-4A-15. pdf_icon_1 Pattern Mining Saliency, Yuqiu Kong, Dalian University of Technolog; Lijun Wang, Dalian University of Technology; Xiuping Liu, Dalian University of Technology; Huchuan Lu, ; Xiang Ruan

P-4A-16. pdf_icon_1 Streaming Video Segmentation via Short-Term Hierarchical Segmentation and Frame-by-Frame Markov Random Field Optimization, Won-Dong Jang, Korea University; Chang-Su Kim, Korea University

P-4A-17. pdf_icon_1 Learning to Learn: Model Regression Networks for Easy Small Sample Learning, Yu-Xiong Wang, Carnegie Mellon University; Martial Hebert, Carnegie Mellon University

P-4A-18. pdf_icon_1 Shape from Water: Bispectral Light Absorption for Depth Recovery, Yuta Asano, ; Yinqiang Zheng, National Institute of Informatics, Japan; Ko Nishino, Drexel University; Imari Sato, National Institute of Informatics, Japan

P-4A-19. pdf_icon_1 Learning Dynamic Hierarchical Models for Anytime Scene Labeling, Buyu Liu, NICTA; Xuming He, NICTA

P-4A-20. pdf_icon_1 Semantic 3D Reconstruction of Heads, Fabio Maninchedda, ETH Zürich; Christian Haene, ETH Zurich; Bastien Jacquet, ETH Zürich; Amael Delaunoy, ; Marc Pollefeys, ETH

P-4A-21. pdf_icon_1 Human Attribute Recognition by Deep Hierarchical Contexts, Yining Li, IE, CUHK; Chen Huang, The Chinese University of Hong Kong; Chen-Change Loy, the Chinese University of Hong Kong; Xiaoou Tang, Chinese University of Hong Kong

P-4A-22. pdf_icon_1 Person Re-Identification via Recurrent Feature Aggregation, Yichao Yan, Shanghai Jiaotong University; Bingbing Ni, SJTU; Zhichao Song, ; chao Ma, ; Yan Yan, ; xiaokang Yang, SJTU

P-4A-23. pdf_icon_1 Biconvex Relaxation for Semidefinite Programming in Computer Vision, Sohil Shah, University of Maryland; Abhay Yadav, University Of Maryland; Carlos Castillo, University of Maryland, CP; David Jacobs, University of Maryland; Christoph Studer, Cornell University; Tom Goldstein, University of Maryland, College Park

P-4A-24. pdf_icon_1 Image Co-segmentation using Maximum Common Subgraph Matching and Region Co-growing, Avik Hati, IIT Bombay; Subhasis Chaudhuri, IIT Bombay; Rajbabu Velmurugan, IIT Bombay

P-4A-25. pdf_icon_1 End-to-End Localization and Ranking for Relative Attributes, Krishna Kumar Singh, UC Davis; Yong Jae Lee, UC Davis

P-4A-26. pdf_icon_1 Efficient Large Scale Image Classification via Prediction Score Decomposition, Duy-Dinh Le, National Institute of Informat; Tien-Dung Mai, University of Information Technology; Shin’ichi Satoh, National Institute of Informatics, Japan; Thanh Duc Ngo, University of Information Technology; Duc Anh Duong, University of Information Technology

P-4A-27. pdf_icon_1 Stochastic Dykstra Algorithms for Metric Learning with Positive Definite Covariance Descriptors, Tsuyoshi Kato, Gunma University; Tomoki Matsuzawa, Gunma University; Jun Sese, ; Raissa Relator

P-4A-28. pdf_icon_1 MeshFlow: Minimum Latency Online Video Stabilization, Shuaicheng Liu, Uestc.edu.cn; ping tan, ; Lu Yuan, Microsoft Research Asia; Jian Sun, Microsoft Research China; Bing Zeng, uestc.edu.cn

P-4A-29. pdf_icon_1 Large-scale training of shadow detectors with noisily-annotated shadow examples, Tomas F Yago Vicente, Stony Brook University; Le Hou, Stony Brook University; Chen-Ping Yu, Stony Brook University; Minh Hoai, Stony Brook University; Dimitris Samaras, SUNY Stonybrook

P-4A-30. pdf_icon_1 RNN Fisher Vectors for Action Recognition and Image Annotation, Guy Lev, ; Gil Sadeh, ; Benjamin Klein, Tel Aviv University; Lior Wolf

P-4A-31. pdf_icon_1 CDT: Cooperative Detection and Tracking for Tracing Multiple Objects in Video Sequences, Hanul Kim, Korea university; Chang-Su Kim, Korea University

P-4A-32. pdf_icon_1 MARS: A Video Benchmark for Large-Scale Person Re-identification, Liang Zheng, University of Texas at San Ant; Zhi Bie, Tsinghua University; Yifan Sun, Tsinghua University; Jingdong Wang, Microsoft Research; Chi Su, Peking University; Shengjin Wang, wgsgj@tsinghua.edu.cn; Qi Tian

P-4A-33. pdf_icon_1 Angry Crowds: Detecting Violent Events in Videos, Seyed Sadegh Mohammadi, Istituto Italiano di Tecnologi; Alessandro Perina, Microsoft; Hamed Kiani, ; Vittorio Murino, Istituto Italiano di Tecnologia

P-4A-34. pdf_icon_1 Sparse Recovery of Hyperspectral Signal from Natural RGB Images, Boaz Arad, BGU; Ohad Ben-Shahar, Ben-Gurion University

P-4A-35. pdf_icon_1 Light Field Segmentation Using a Ray-Based Graph Structure, Matthieu Hog, Technicolor R&I; Neus Sabater, Technicolor R&I; Christine Guillemot, INRIA

P-4A-36. pdf_icon_1 Design of Kernels in Convolutional Neural Networks for Image Classification, Zhun Sun, Tohoku University; Mete Ozay, Tohoku University; Takayuki Okatani, Tohoku University, Japan

P-4A-37. pdf_icon_1 Learning Visual Features from Large Weakly Supervised Data, Armand Joulin, Facebook AI Research; Laurens van der Maaten, ; Allan Jabri, Facebook AI Research; Nicolas Vasilache, Facebook AI Research

P-4A-38. pdf_icon_1 3D Mask Face Anti-spoofing with Remote Photoplethysmography, Siqi Liu, Hong Kong Baptist University; Pong Chi YUEN, Hong Kong Baptist University; Shengping Zhang, Harbin Institute of Technology; Guoying Zhao, University of Oulu

P-4A-39. pdf_icon_1 Guided Matching based on Statistical Optical Flow for Fast and Robust Correspondence Analysis, Josef Maier, AIT Austrian Institute of Technology; Martin Humenberger, AIT Austrian Institute of Technology; Markus Murschitz, AIT Austrian Institute of Technology; Oliver Zendel, AIT Austrian Institute of Technology; Markus Vincze, TU Wien

P-4A-40. pdf_icon_1 Pose Estimation Errors, the Ultimate Diagnosis, Carolina Redondo-Cabrera, University of Alcalá; Roberto Lopez-Sastre, University of Alcala; Yu Xiang, ; Tinne Tuytelaars, KU Leuven; Silvio Savarese

P-4A-41. pdf_icon_1 A Siamese Long Short-Term Memory Architecture for Human Re-Identification, Rahul Rama Varior, NTU Singapore; Bing Shuai, Nanyang Technological Univ; Jiwen Lu, Tsinghua University; Dong Xu, ; Gang Wang

P-4A-42. pdf_icon_1 Integration of Probabilistic Pose Estimates From Multiple Views, Ozgur Erkent, Innsbruck University; Dadhichi Shukla, ; Justus Piater, University of Innsbruck

P-4A-43. pdf_icon_1 SurfCut: Free-Boundary Surface Extraction, Marei Algarni, KAUST University; Ganesh Sundaramoorthi, KAUST

P-4A-44. pdf_icon_1 CATS: Co-saliency Activated Tracklet Selection for Video Co-localization, Koteswar Jerripothula, NanyangTechnologicalUniversity; Jianfei Cai, ; Junsong Yuan, Nanyang Technological University

P-4A-45. pdf_icon_1 Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks, Yanghao Li, Peking University; Cuiling Lan, Microsoft Research; Junliang Xing, Chinese Academy of Sciences; Wenjun Zeng, Microsoft Research; Chunfeng Yuan, ; Jiaying Liu, Peking University

P-4A-46. pdf_icon_1 SyB3R: A Realistic Synthetic Benchmark for 3D Reconstruction from Images, Andreas Ley, Technische Universität Berlin; Ronny Hänsch, Technische Universität Berlin; Olaf Hellwich, Technische Universität Berlin

P-4A-47. pdf_icon_1 A Deep Learning-based Approach to Progressive Vehicle Re-identification for Urban Surveillance, Xinchen Liu, Beijing University of Posts and Telecommunication; Wu Liu, Beijing University of Posts and Telecommunication; Tao Mei, Microsoft Research Asia; Huadong Ma, Beijing University of Posts and Telecommunication

Oral Session 4B: Action, Activity & Tracking
Friday, October 14; 14:00 – 15:00
Chairs: Rita Cucchiara (U Modena), Juergen Gall (U Bonn)

O-4B-01. pdf_icon_1 Spot On: Action Localization from Pointly-Supervised Proposals, Pascal Mettes, University of Amsterdam; Jan van Gemert, Delft University of Technology; Cees Snoek, University of Amsterdam

O-4B-02. pdf_icon_1 Detecting Engagement in Egocentric Video, Yu-Chuan Su, University of Texas at Austin; Kristen Grauman, University of Texas at Austin

O-4B-03. pdf_icon_1 Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking, Martin Danelljan, Linköping University; Andreas Robinson, Linköping University; Fahad Khan, Linkoping University, Sweden; Michael Felsberg, Link_ping University

O-4B-04. pdf_icon_1 Look-ahead before you leap: end-to-end active recognition by forecasting the effect of motion, Dinesh Jayaraman, UT Austin; Kristen Grauman, University of Texas at Austin

Spotlight Session 4B: Human & Face
Friday, October 14; 15:00 – 15:30
Chairs: Maja Pantic (Imperial College), Albert Ali Salah (Bogazici University)

S-4B-05. pdf_icon_1 General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues, Helge Rhodin, MPI for informatics; Nadia Robertini, Max-Planck-Institute for informatics; Dan Casas, MPI; Christian Richardt, Intel VCI; Hans-Peter Seidel, ; Christian Theobalt, MPI Informatics

S-4B-06. pdf_icon_1 Globally Continuous and Non-Markovian Activity Analysis from Videos, He Wang, Disney Research LA; Carol O’Sullivan, Trinity College Dublin

S-4B-07. pdf_icon_1 Joint Face Alignment and 3D Face Reconstruction, Feng Liu, Sichuan University; Qijun Zhao, Sichuan University; Dan Zeng, Sichuan University; Xiaoming Liu, Michigan State University

S-4B-08. pdf_icon_1 Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image, Federica Bogo, Max Planck Institute Tuebingen; Angjoo Kanazawa, University of Maryland; Christoph Lassner, BCCN Tübingen; Peter Gehler, ; Javier Romero, MPI Intelligent Systems Tuebingen; Michael Black

S-4B-09. pdf_icon_1 Do We Really Need to Collect Millions of Faces for Effective Face Recognition?, Iacopo Masi, USC; Anh Tran, USC; Tal Hassner, Open Univ Israel; Jatuporn Leksut, USC; Gerard Medioni, University of Southern California

Poster Session 4B
Friday, October 14; 16:00 – 17:30
Chairs: Jasper Uijlings (University of Edinburgh), Roberto Valenti (Sightcorp)

O-4B-02. pdf_icon_1 Detecting Engagement in Egocentric Video, Yu-Chuan Su, University of Texas at Austin; Kristen Grauman, University of Texas at Austin

O-4B-04. pdf_icon_1 Look-ahead before you leap: end-to-end active recognition by forecasting the effect of motion, Dinesh Jayaraman, UT Austin; Kristen Grauman, University of Texas at Austin

S-4B-06. pdf_icon_1 Globally Continuous and Non-Markovian Activity Analysis from Videos, He Wang, Disney Research LA; Carol O’Sullivan, Trinity College Dublin

P-4B-10. pdf_icon_1 Generative Visual Manipulation on the Natural Image Manifold, Jun-Yan Zhu, UC BERKELEY; Philipp Krahenbuhl, ; Eli Shechtman, Adobe; Alexei Efros,

P-4B-11. pdf_icon_1 Deep Cascaded Bi-Network for Face Hallucination, Shizhan Zhu, Chinese University of HK; Sifei Liu, UC Merced; Chen-Change Loy, the Chinese University of Hong Kong; Xiaoou Tang, Chinese University of Hong Kong

P-4B-12. pdf_icon_1 Cluster Sparsity Field for Hyperspectral Imagery Denoising, Lei Zhang, NPU; Wei Wei, Northwestern Polytechnical University; yanning Zhang, Northwestern Polytechnical University; Chunhua Shen, University of Adelaide; Anton Van den Hengel, University of Adelaide; Qinfeng Shi, The University of Adelaide

P-4B-13. pdf_icon_1 Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net, Fangting Xia, UCLA; Peng Wang, UCLA; Liang-Chieh Chen, UCLA; Alan Yuille, UCLA

P-4B-14. pdf_icon_1 Learning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks, Jinghua Wang, NTU; Zhenhua Wang, NTU, ROSE Lab; Dacheng Tao, University of Technology, Sydney; Simon See, ; Gang Wang

P-4B-15. pdf_icon_1 MADMM: a generic algorithm for non-smooth optimization on manifolds, Artiom Kovnatsky, USI-Università della Svizzera ; Klaus Glashoff, USI-Università della Svizzera italiana; Michael Bronstein

P-4B-16. pdf_icon_1 Interpreting the Ratio Criterion for Matching SIFT Descriptors, Avi Kaplan, Technion, Israel; Tamar Avraham, Technion; Michael Lindenbaum, Technion

P-4B-17. pdf_icon_1 Semi-supervised learning based on joint diffusion of graph functions and Laplacians, Kwang In Kim, University of Bath

P-4B-18. pdf_icon_1 Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classification, Maxime Bucher, ONERA; Stephane Herbin, ONERA; Frederic Jurie, University of Caen

P-4B-19. pdf_icon_1 A Sequential Approach to 3D Human Pose Estimation: Separation of Localization and Identification of Body Joints, Hoyub Jung, HUFS; Yumin Suh, Seoul National University; Gyeongsik Moon, Seoul National University; Kyoung Mu Lee

P-4B-20. pdf_icon_1 A Novel Tiny Object Recognition Algorithm Based on Unit Statistical Curvature Feature, Yimei Kang, College of Software, Beihang University; Xiang Li, College of Software, Beihang University

P-4B-21. pdf_icon_1 Head Reconstruction from Internet Photos, Shu Liang, ; Linda Shapiro, University of Washington; Ira Kemelmacher, University of Washington

P-4B-22. pdf_icon_1 The Conditional Lucas & Kanade Algorithm, Chen-Hsuan Lin, Carnegie Mellon University; Rui Zhu, Carnegie Mellon University; Simon Lucey, CMU

P-4B-23. pdf_icon_1 Where should saliency models look next?, Zoya Bylinskii, MIT; Adria Recasens, MIT; Ali Borji, University of Central Flordia; Aude Oliva, MIT; Antonio Torralba, ; Fredo Durand

P-4B-24. pdf_icon_1 Robust Face Alignment Using a Mixture of Invariant Experts, Oncel Tuzel, MERL; Tim Marks, MERL; Salil Tambe

P-4B-25. pdf_icon_1 Partial Linearization based Optimization for Multi-class SVM, Pritish Mohapatra, IIIT, Hyderabad; Puneet Dokania, Ecole Centrale Paris; C.V. Jawahar, IIIT Hyderabad; M. Pawan Kumar, University of Oxford

P-4B-26. pdf_icon_1 Search-based Depth Estimation via Coupled Dictionary Learning with Large-Margin Structure Inference, Yan Zhang, HIT; Rongrong Ji, Xiamen University; Xiaopeng Fan, ; Yan Wang, Microsoft; Feng Guo, Xiamen University; Yue Gao, ; debin Zhao

P-4B-27. pdf_icon_1 Scalable Metric Learning via Weighted Approximate Rank Component Analysis, Cijo Jose, Idiap Research Institute; Francois Fleuret

P-4B-28. pdf_icon_1 Spatio-Temporally Consistent Correspondence for Dense Dynamic Scene Modeling, Dinghuang Ji, UNC; Enrique Dunn, UNC Chapel Hill; Jan-Michael Frahm

P-4B-29. pdf_icon_1 3D Image Reconstruction from X-Ray Measurements with Overlap, Maria Klodt, University of Oxford; Raphael Hauser, University of Oxford

P-4B-30. pdf_icon_1 DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model, Eldar Insafutdinov, Max-Planck Institute for Infor; Leonid Pishchulin, MPI Informatik; Bjoern Andres, Max-Planck Institute for Informatics; Mykhaylo Andriluka, Max-Planck Institute for Informatics; Bernt Schiele

P-4B-31. pdf_icon_1 Resonant Deformable Matching: Simultaneous Registration and Reconstruction, John Corring, University of Florida; Anand Rangarajan, University of Florida

P-4B-32. pdf_icon_1 Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles, Mehdi Noroozi, University of Bern; Paolo Favaro

P-4B-33. pdf_icon_1 COCO Attributes: Attributes for People, Animals, and Objects, Genevieve Patterson, Microsoft Research; James Hays, Georgia Institute of Technology

P-4B-34. pdf_icon_1 Temporally Robust Global Motion Compensation by Keypoint-based Congealing, Seyed Morteza Safdarnejad, Michigan State University; Yousef Atoum, Michigan State University; Xiaoming Liu, Michigan State University

P-4B-35. pdf_icon_1 Salient Deconvolutional Networks, Aravindh Mahendran, Oxford; Andrea Vedaldi

P-4B-36. pdf_icon_1 Visualizing Image Priors, Tamar Shaham, Technion; Tomer Michaeli, Technion

P-4B-37. pdf_icon_1 Exploiting Semantic Information and Deep Matching for Optical Flow, Min Bai, University of Toronto; Wenjie Luo, University of Toronto; Kaustav Kundu, University of Toronto; Raquel Urtasun

P-4B-38. pdf_icon_1 Similarity Registration Problems for 2D/3D Ultrasound Calibration, Francisco Vasconcelos, UCL; Sebastien Ourselin, ; Donald Peebles, ; Danail Stoyanov

P-4B-39. pdf_icon_1 Adaptive Signal Recovery on Graphs via Harmonic Analysis for Experiment Design in Neuroimaging, Won Hwa Kim, UW-Madison; Seong Jae Hwang, UW-Madison; Nagesh Adluru, UW-Madison; Sterling Johnson, UW-Madison; Vikas Singh, University of Wisconsin-Madison

P-4B-40. pdf_icon_1 A Benchmark for Automatic Visual Classification of Clinical Skin Disease Images, SUN Xiao Xiao, NanKai University; Jufeng Yang, Nankai University; Ming Sun, NanKai Unverisity; Kai Wang, Nankai University

P-4B-41. pdf_icon_1 Deep learning 3D shape surfaces using geometry images, Ayan Sinha, Purdue University; Jing Bai, Purdue University; Karthik Ramani, Purdue University

P-4B-42. pdf_icon_1 Deep Image Retrieval: Learning Global Representations for Image Search, Albert Gordo, Xerox Research; Jon Almazan, XRCE; Jerome Revaud, Xerox Research; Diane Larlus, Xerox

P-4B-43. pdf_icon_1 Building Scene Models by Completing and Hallucinating Depth and Semantics, Miaomiao Liu, Data61, CSIRO, (NICTA); Xuming He, NICTA; Mathieu Salzmann, EPFL

P-4B-44. pdf_icon_1 Weakly Supervised Learning of Heterogeneous Concepts in Videos, Sohil Shah, University of Maryland; Kuldeep Kulkarni, Arizona State University; Arijit Biswas, Amazon Development Center India; Ankit Gandhi, Xerox Research Centre India; Om Deshmukh, Xerox Research Centre India; Larry Davis, University of Maryland

P-4B-45. pdf_icon_1 Learning Semantic Deformation Flows with 3D Convolutional Networks, M. Ersin Yumer, Adobe Research; Niloy Mitra, University College London

P-4B-46. pdf_icon_1 Recurrent Instance Segmentation, Bernardino Romera-Paredes, University of Oxford; Philip Torr, Oxford University

P-4B-47. pdf_icon_1 Individualness and Determinantal Point Processes for Pedestrian Detection, Donghoon Lee, Seoul National University; Ming-Hsuan Yang, UC Merced; Geonho Cha, Seoul National University; Songhwai Oh, Seoul National University

0 0