BMVC 2017 Programme

 Monday, 4 Sep

13:30 -- Registration, RGS

14:30 -- 16:30 Tutorials, RGS Theatre

Chair: Stefan Leutenegger and Stefanos Zafeiriou

14 :30 Probabilistic and Deep Models for 3D Reconstruction. Andreas Geiger (Max Planck Institute)

15 :30 Intro to Reinforcement Learning. Shimon Whiteson (University of Oxford) 

16:30 -- 17:00 Break, RGS

17:00 -- 19:00 Tutorials, RGS Theatre

Chair: Andrew Davison and Tae-Kyun Kim

17 :00 Deep Learning for 3D Localization. Vincent Lepetit (University of Bordeaux)

18 :00 3D Reconstruction of Dynamic Scenes from Monocular Video. Lourdes Agapito (University College London) 

19:00 -- 21:00 Reception, RGS


 Tuesday, 5 Sep

7:30 --  Registration, RGS

8:00 -- 8:30 Coffee \& pastry, RGS

8:30 -- 8:45 Welcome, RGS Theatre

8:45 -- 9:30 Spotlights, RGS Theatre

8 :45 1. Semantics-Preserving Locality Embedding for Zero-Shot Learning. Shih-Yen Tao (Academia Sinica), Yi-Ren Yeh and Yu-Chiang Frank Wang

8 :49 2. Hyperspectral CNN Classification with Limited Training Samples. Lloyd Windrim (University of Sydney), Rishi Ramakrishnan Arman Melkumyan and Richard Murphy

8 :53 3. Which is the better inpainted image? Learning without subjective annotation. Mariko Isogawa (NTT), Dan Mikami Kosuke Takahashi and Hideaki Kimata

8 :57 4. Spatio-Temporal Consistency to Detect and Segment Carried Objects. Farnoosh Ghadiri (Laval University), Robert Bergevin and Guillaume-Alexandre Bilodeau

9 :01 5. Improved Image Segmentation via Cost Minimization of Multiple Hypotheses. Marc Bosch Ruiz (The Johns Hopkins University), Christopher Gifford Austin Dress Clare Lau and Jeffrey Skibo

9 :05 6. Face Parsing via Recurrent Propagation. Sifei Liu (UCMERCED), Jianping Shi Liang Ji and Ming-Hsuan Yang

9 :09 7. Accurate Camera Registration in Urban Environments Using High-Level Feature Matching. Anil Armagan (TU GRAZ), Martin Hirzer Peter Roth and Vincent Lepetit

9 :13 8. The Devil is in the Decoder. Zbigniew Wojna (University College London), Jasper Uijlings Sergio Guadarrama Nathan Silberman Liang-Chieh Chen Alireza Fathi and Vittorio Ferrari

9 :17 9. Virtual to Real Reinforcement Learning for Autonomous Driving. Xinlei Pan (UC Berkeley), Yurong You Ziyan Wang and Cewu Lu

9 :21 10. Real-Time Salient Closed Boundary Tracking using Perceptual Grouping and Shape Priors. Xuebin Qin (University of Alberta), Shida He Zichen Zhang Masood Dehghan and Martin Jagersand

9:30 -- 10:30 Orals: Pose Estimation, RGS Theatre

Chair: Roberto Cipolla

9 :30 11. Kinematic-Layout-aware Random Forests for Depth-based Action Recognition. Seungryul Baek (Imperial College London), Zhiyuan Shi Masato Kawade and Tae-Kyun Kim

9 :45 12. Total Capture: 3D Human Pose Estimation Fusing Video and Inertial Sensors. Matthew Trumble (University of Surrey), Andrew Gilbert Charles Malleson Adrian Hilton and John Collomosse

10 :00 13. Indirect deep structured learning for 3D human body shape and pose prediction. Ignas Budvytis (Department of Engineering), Vince Tan and Roberto Cipolla

10 :15 14. Real-time Visual-Inertial Odometry for Event Cameras using Keyframe-based Nonlinear Optimization. Henri Rebecq (University of Zurich), Timo Horstschaefer and Davide Scaramuzza

10:30 -- 11:15 Break, RGS

11:15 -- 12:15 Keynote, RGS Theatre

Chair: Krystian Mikolajczyk

11 :15Visual Reconstruction and Image-Based Rendering . Richard Szeliski (Facebook)

12:15 -- 13:00 Lunch, RGS

13:00 -- 15:00 Posters, RGS

 15. Weakly Supervised Semantic Segmentation Based on Co-segmentation. Tong Shen (The University of Adelaide ), Guosheng Lin Lingqiao Liu Chunhua Shen and Ian Reid

 16. Semantic Segmentation with Reverse Attention. Qin Huang (University of Southern Califor), Chihao Wu Chunyang Xia Ye Wang and C.-C. Jay Kuo

 17. Double Expansion for Optimization of Multilabel Energies. Yelena Gorelick (Western University), Zhengqin Li and Olga Veksler

 18. Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation. Arslan Chaudhry (University of Oxford), Puneet Kumar Dokania and Philip Torr

 19. Adapting Models to Signal Degradation using Distillation. Jong-Chyi Su (UMass-Amherst), and Subhransu Maji

 20. Localizing Actions from Video Labels and Pseudo-Annotations. Pascal Mettes (University of Amsterdam), Cees Snoek and Shih-Fu Chang

 21. Introduction to Coherent Depth Fields for Dense Monocular Surface Recovery. Vladislav Golyanik (DFKI), Torben Fetzer and Didier Stricker

 22. Real-time Factored ConvNets: Extracting the X Factor in Human Parsing. James Charles (University of Cambridge), Ignas Budvytis and Roberto Cipolla

 23. Holistic, Instance-level Human Parsing. Qizhu Li (University of Oxford), Anurag Arnab and Philip Torr

 24. CT from Motion: Volumetric Capture of Moving Shapes using X-rays. Julien Pansiot (Inria), and Edmond Boyer

 25. Concise Radiometric Calibration Using The Power of Ranking. Han Gong (University of East Anglia), Graham Finlayson and Maryam Darrodi

 26. Scale Exploiting Minimal Solvers for Relative Pose with Calibrated Cameras. Stephan Liwicki (Toshiba Research Europe Ltd), and Christopher Zach

 27. Multiple Instance Curriculum Learning for Weakly Supervised Object Detection. Siyang Li (USC), Xiangxin Zhu Qin Huang Hao Xu and C.-C. Jay Kuo

 28. Fast Feature Fool: A data independent approach to universal adversarial perturbations. Konda Reddy Mopuri (Indian Institute of Science), Utsav Garg and Venkatesh Babu Radhakrishnan

 29. 3D Color charts for computer vision. Rada Deeb Damien Muselet Mathieu Hebert Alain Tremeau and Joost van de Weijer

 30. Guided Robust Matte-Model Fitting for Accelerating Multi-light Reflectance Processing Techniques. Ruggero Pintus (CRS4), Andrea Giachetti Giovanni Pintore and Enrico Gobbetti

 31. Fast Event-based Corner Detection. Elias Mueggler (University of Zurich), Chiara Bartolozzi and Davide Scaramuzza

 32. PCN: Part and Context Information for Pedestrian Detection with CNNs. Shiguang Wang, UESTC

 33. Adaptive Local Contrast Normalization for Robust Object Detection and Pose Estimation. Mahdi Rad (TUG), Vincent Lepetit and Peter Roth

 34. Object-Extent Pooling for Weakly Supervised Single-Shot Localization. Amogh Gudi (TU Delft), Nicolai van Rosmalen Marco Loog and Jan van Gemert

 35. Transformed Anti-Sparse Hashing. Zhangyang Wang (TAMU), Ji Liu Shuai Huang Xinchao Wang and Shiyu Chang

 36. Deeply Supervised 3D Recurrent FCN for Salient Object Detection in Videos. Trung-Nghia Le (NII), and Akihiro Sugimoto

 37. Robust Dense Depth Maps Generations from Sparse DVS Stereos. Dongqing Zou (Samsung Electronic), Feng Shi Weiheng Liu Jia Li Qiang Wang Paul-K.J. Park and Hyunsurk Eric Ryu

 38. Adaptive Temporal Pooling for Object Detection using Dynamic Vision Sensor. Jia Li (Samsung - SAIT China Lab), Feng Shi Weiheng Liu Dongqing Zou Qiang Wang Paul-K.J. Park and Hyunsurk Eric Ryu

 39. High-Resolution Stereo Matching based on Sampled Photoconsistency Computation. Chloe Legendre (usc), Konstantinos Batsos and Philippos Mordohai

 40. Generative OpenMax for Multi-Class Open Set Classification. Zongyuan Ge (IBM), Sergey Demyanov and Rahil Garnavi

 41. ANSAC: Adaptive Non-Minimal Sample and Consensus. Victor Fragoso (West Virginia University), Christopher Sweeney Pradeep Sen and Matthew Turk

 42. Color Restoration of Underwater Images. Dana Menaker (Tel Aviv University), Tali Treibitz and Shai Avidan

 43. Fine-Grained Image Retrieval: the Text/Sketch Input Dilemma. Jifei Song (Queen Mary), Yi-zhe Song Tony Xiang and Timothy Hospedales

 44. Cross-domain Generative Learning for Fine-Grained Sketch-Based Image Retrieval. Kaiyue Pang (QMUL), Yi-zhe Song Tony Xiang and Timothy Hospedales

 45. Epipolar Plane Diffusion: An Efficient Approach for Light Field Editing. Oriel Frigo, INRIA

 46. Group Cost-sensitive Boosting with Multi-scale Decorrelated Filters for Pedestrian Detection. Chengju Zhou (NTU), Meiqing Wu and SiewKei Lam

 47. Moving Object Segmentation in Jittery Videos by Stabilizing Trajectories Modeled in Kendall's Shape Space. Geethu Jacob (Indian Institute of Technology), and Sukhendu Das

 48. Urban Image Stitching using Planar Perspective Guidance. Joo Ho Lee (KAIST), Seung-Hwan Baek and Min H. Kim

 49. Detecting Parts for Action Localization. Nicolas Chesneau (Inria), Gregory Rogez Karteek Alahari and Cordelia Schmid

 50. Cascaded Boundary Regression for Temporal Action Detection. Jiyang Gao (USC), Zhenheng Yang and Ram Nevatia

 51. Confidence and Diversity for Active Selection of Feedback in Image Retrieval. Bhavin Modi and Adriana Kovashka

 52. Shape Generation using Spatially Partitioned Point Clouds. Matheus Gadelha (University of Massachusetts Am), Subhransu Maji and Rui Wang

 53. Person Re-Identification by Localizing Discriminative Regions. Tanzila Rahman (University of Manitoba), Mrigank Rochan and Yang Wang

 54. Adapting Object Detectors from Images to Weakly Labeled Videos. Omit Chanda (University of Manitoba), Eu Wern Teh Mrigank Rochan Zhenyu Guo and Yang Wang

 55. Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding. Alex Kendall (University of Cambridge), Vijay Badrinarayanan and Roberto Cipolla

 56. DepthComp: Real-time Depth Image Completion Based on Prior Semantic Scene Segmentation. Amir Atapour Abarghouei (Durham University), and Toby Breckon

 57. DEEP eye contact detector: Robust eye contact bid detection using convolutional neural network. Yu Mitsuzumi (Kyoto University), Atsushi Nakazawa and Toyoaki Nishida

 58. BiSeg: Simultaneous Instance Segmentation and Semantic Segmentation with Fully Convolutional Networks. Viet Pham (Toshiba), Satoshi Ito and Tatsuo Kozakaya

 59. Salient Object Detection using a Context-Aware Refinement Network. Md Amirul Islam (University of Manitoba), Mahmoud Kalash Mrigank Rochan Neil Bruce and Yang Wang

 60. Visual Odometry with Drift-Free Rotation Estimation Using Indoor Scene Regularities. Pyojin Kim (Seoul National University), Brian Coltin and Hyounjin Kim

 61. One For All: Adaptive Learning-based Temporal Tracker for 3D Head Shape Models. David Joseph Tan (Technische Universität München), Federico Tombari and Nassir Navab

 62. Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition.. Chu Wang (McGill University), Marcello Pelillo and Kaleem Siddiqi

 63. A Generalised Formulation for Collaborative Representation of Image Patches (GP-CRC). Tapabrata Chakraborti (University of Otago), Brendan McCane Steven Mills and Umapada Pal

 64. DeepShoe: A Multi-Task View-Invariant CNN for Street-to-Shop Shoe Retrieval. Huijing Zhan (NTU EEE), boxin shi and ALEX KOT

 65. Weakly Supervised Saliency Detection with A Category-Driven Map Generator. Kuang-Jui Hsu (National Taiwan University ), Yen-Yu Lin and Yung-Yu Chuang

 66. Saliency Detection by Compactness Diffusion. Qi Zheng (Huazhong Univ. of Sci. \& Tech.), Peng Zhang and Xinge You

 67. Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization. Yang Zhou (Beijing University of Chemical), Kai Yu Biao Leng zhang Zhang Dangwei Li and Kaiqi Huang

 68. AST-Net: An Attribute-based Siamese Temporal Network for Real-Time Emotion Recognition. Shu-Hui Wang (National Tsing Hua University), and Chiou-Ting Hsu

 69. Combined Internal and External Category-Specific Image Denoising. Saeed Anwar (ANU), Cong Huynh and Fatih Porikli

 70. Temporal Perceptive Network for Skeleton-Based Action Recognition. Yueyu Hu (Peking University), Chunhui Liu Yanghao Li and Jiaying Liu

 71. Detecting Semantic Parts on Partially Occluded Objects. Jianyu Wang Zhishuai Zhang Cihang Xie Jun Zhu Lingxi Xie and Alan Yuille

 72. Place Recognition in Semi-Dense Maps. Yawei Ye (ETH Zurich), Titus Cieslewski Antonio Loquercio and Davide Scaramuzza

 73. Image Completion with Intrinsic Reflectance Guidance. Soomin Kim (KAIST), Taeyoung Kim Min H. Kim and Sung-Eui Yoon

 74. Enhancement of SSD by concatenating feature maps for object detection. Jisoo Jeong (Seoul National University), Hyojin Park and Nojun Kwak

 75. Colour Constancy: Biologically-inspired Contrast Variant Pooling Mechanism. Arash Akbarinia (Centre de Visió per Computador), Raquel Gil Rodríguez and C. Alejandro Parraga

 76. Superpixel-based semantic segmentation trained by statistical process control. Hyojin Park (Seoul National University), Jisoo Jeong Youngjoon Yoo and Nojun Kwak

 77. Robust Pixel-wise Dehazing Algorithm based on Advanced Haze-Relevant Features. Guisik Kim (CAU), and Junseok Kwon

 78. General Deep Image Completion with Lightweight Conditional Generative Adversarial Networks. Ching-Wei Tseng (National Tsing Hua University), Hung Jin Lin and Shang-Hong Lai

 79. Augmented Reality meets Deep Learning. Hassan Abu Alhaija (TU Dresden), Siva Karthik Mustikovela Lars Mescheder Andreas Geiger and Carsten Rother

 80. Improved IR-Colorization using Adversarial Training and Estuary Networks. Matthias Limmer (Daimler AG), and Hendrik Lensch

 81. Realtime Novel View Synthesis with Eigen-Texture Regression. Yuta Nakashima (Osaka University), Fumio Okura Norihiko Kawai ryosuke Kimura Hiroshi Kawasaki Katsushi Ikeuchi and Ambrosio Blanco

 82. Human Action Recognition Using A Multi-Modal Hybrid Deep Learning Model. Hany El-Ghaish (Egypt-Japan University(EJUST)), Mohamed Hussein and Amin Shoukry

 83. Probabilistic Image Colorization. Amelie Royer Alexander Kolesnikov and Christoph Lampert

 84. Iterated Lifting for Robust Cost Optimization. Christopher Zach (Toshiba Cambridge Research Laboratory), and Guillaume Bourmaud

15:00 -- 15:30 Tea break, RGS

15:30 -- 16:45 Orals: Scene Understanding, RGS Theatre

Chair: Pushmeet Kohli

15 :30 85. Slanted Stixels: Representing San Francisco's Steepest Streets. Daniel Hernandez-Juarez (UAB), Lukas Schneider Antonio Espinosa Juan Moure David Vazquez Antonio López Uwe Franke and Marc Pollefeys

15 :45 86. Deformable Part-based Fully Convolutional Network for Object Detection. Taylor Mordan (LIP6), Nicolas Thome Gilles Henaff and Matthieu Cord

16 :00 87. Multiple Instance Visual-Semantic Embedding. Zhou Ren (Snap Inc.), Hailin Jin Zhe Lin Chen Fang and Alan Yuille

16 :15 88. Thinking Outside the Box: Spatial Anticipation of Semantic Categories. Martin Garbade (Uni Bonn), and Juergen Gall

16 :30 89. Visually Aligned Word Embeddings for Improving Zero-shot Learning. Ruizhi Qiao (The University of Adelaide), Lingqiao Liu Chunhua Shen and Anton van den Hengel

16:45 -- 17:15 Break, RGS

17:15 -- 18:30 Orals: Action Recognition, RGS Theatre

Chair: Rahul Sukthankar

17 :15 90. Real-Time Temporal Action Localization in Untrimmed Videos by Sub-Action Discovery. Rui Hou (University of Central Florida), Rahul Sukthankar and Mubarak Shah

17 :30 91. RED: Reinforced Encoder-Decoder Networks for Action Anticipation. Jiyang Gao (USC), Zhenheng Yang and Ram Nevatia

17 :45 92. End-to-End, Single-Stream Temporal Action Detection in Untrimmed Videos. Shyamal Buch (Stanford University), Victor Escorcia Bernard Ghanem and Juan Carlos Niebles

18 :00 93. Recognizing and Curating Photo Albums via Event-Specific Image Importance. Yufei Wang (UCSD), Zhe Lin Xiaohui Shen Radomir Mech Gavin Miller and Garrison Cottrell

18 :15 94. Spatio-Temporal Action Detection with Cascade Proposal and Location Anticipation. Zhenheng Yang (USC), Jiyang Gao and Ram Nevatia


 Wednesday, 6 Sep

7:30 --  Registration, RGS

8:00 -- 8:30 Coffee & pastry, RGS

8:30 -- 8:45 Welcome, RGS Theatre

8:45 -- 9:30 Spotlights, RGS Theatre

8 :45 1. Video Segmentation with Background Motion Models. Scott Wehrwein (Cornell University), and Richard Szeliski

8 :49 2. Orientation-boosted Voxel Nets for 3D Object Recognition. Nima Sedaghat (University of Freiburg), Mohammadreza Zolfaghari Ehsan Amiri and Thomas Brox

8 :53 3. Semantic 3D Reconstruction with Finite Element Bases. Audrey Richard (ETH Zurich), Christoph Vogel Maros Blaha Thomas Pock and Konrad Schindler

8 :57 4. SilNet : Single- and Multi-View Reconstruction by Learning from Silhouettes. Olivia Wiles (Oxford University), and Andrew Zisserman

9 :01 5. A Differential Approach to Shape from Polarization. Roberto Mecca (University of Cambridge), Fotios Logothetis and Roberto Cipolla

9 :05 6. Fast dense feature extraction with convolutional neural networks that have pooling or striding layers. Christian Bailer (DFKI), tewodros Habtegebrial Kiran Varanasi and Didier Stricker

9 :09 7. Local Visual Microphones: Improved Sound Extraction from Silent Video. Mohammad Amin Sadeghi (University of Tehran), Mohammad Amin Shabani and Laleh Samadfam

9 :13 8. Unsupervised Deep Generative Hashing. Yuming Shen (University of East Anglia), li Liu and Ling Shao

9 :17 9. Sampled Image Tagging and Retrieval Methods on User Generated Content. Karl Ni (In-Q-Tel), Kyle Zaragoza Alexander Gude Yonas Tesfaye Carmen Carrano Charles Foster and Barry Chen

9 :21 10. Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking. James Tompkin (Brown University), Kwang In Kim Hanspeter Pfister and Christian Theobalt

9:30 -- 10:30 Orals: Face Analysis, RGS Theatre

Chair: Josef Kittler

9 :30 11. Now You See Me: Deep Face Hallucination for Unviewed Sketches. Conghui Hu (Queen Mary Uni. of Londo), Da Li Yi-zhe Song and Timothy Hospedales

9 :45 12. From Benedict Cumberbatch to Sherlock Holmes: Character Identification in TV series without a Script. Arsha Nagrani (Oxford University), and Andrew Zisserman

10 :00 13. Quantifying Facial Age by Posterior of Age Comparisons. Yunxuan Zhang (Sensetime), Li Liu Cheng Li and Chen-Change Loy

10 :15 14. You said that?. Joon Son Chung (University of Oxford), Amir Jamaludin and Andrew Zisserman

10:30 -- 11:15 Break, RGS

11:15 -- 12:15 Keynote, RGS Theatre

Chair: Gabriel Brostow

11 :15   Visipedia - A universal visual expert . Pietro Perona (California Institute of Technology)

12:15 -- 13:00 Lunch, RGS

13:00 -- 15:00 Posters, RGS

 15. Reflectance and Shape Estimation with Handy Camera under Natural Illumination. Trung Ngo (Osaka University), Hajime Nagahara Ko Nishino Rin-ichiro Taniguchi and Yasushi Yagi

 16. GeneGAN: Learning Object Transfiguration and Object Subspace from Unpaired Data. Shuchang Zhou (Megvii Inc.), Taihong Xiao Yi Yang Dieqiao Feng Qinyao He and Weiran He

 17. PixColor: Pixel Recursive Colorization. Sergio Guadarrama (Google), Ryan Dahl David Bieber Jonathon Shlens Mohammad Norouzi and Kevin Murphy

 18. Depth Estimation and Blur Removal from a Single Out-of-focus Image. Saeed Anwar (ANU), Zeeshan Hayder and Fatih Porikli

 19. Exploring the structure of a real-time, arbitrary neural artistic stylization network. Golnaz Ghiasi (Google Inc.), Honglak Lee Manjunath Kudlur Vincent Dumoulin and Jonathon Shlens

 20. Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization. Frederick Tung (Simon Fraser University), Srikanth Muralidharan and Greg Mori

 21. Online Adaptation of Convolutional Neural Networks for Video Object Segmentation. Paul Voigtlaender (RWTH Aachen University), and Bastian Leibe

 22. Improved Bilinear Pooling with CNNs. Tsung-Yu Lin (UMass Amherst), and Subhransu Maji

 23. Video to Text Summary: Joint Video Summarization and Captioning with Recurrent Neural Networks. Bor-Chun Chen (University of Maryland), Yan-Ying Chen and Francine Chen

 24. A Recurrent Variational Autoencoder for Human Motion Synthesis. Ikhsanul Habibie (University of Edinburgh), Daniel Holden Jonathan Schwarz Joe Yearsley and Taku Komura

 25. A deep learning pipeline for semantic facade segmentation. Radwa Fathalla (AAST), and George Vogiatzis

 26. Deep Reinforcement Learning Attention Selection For Person Re-Identification. XU LAN (Queen Mary University of Londo), HangXiao Wang Shaogang Gong and Xiatian Zhu

 27. Case-Based Histopathological Malignancy Diagnosis using Convolutional Neural Networks. Qicheng Lao (Concordia University), and Thomas Fevens

 28. Labelless Scene Classification with Semantic Matching. Meng Ye (Temple University), and Yuhong Guo

 29. Patch-based Interferometric Phase Estimation via Mixture of Gaussian Density Modelling \& Non-local Averaging in the Complex Domain. Joshin Krishnan (Instituto de Telecomunicações), and José Bioucas-Dias

 30. Feature Sequence Representation Via Slow Feature Analysis For Action Classification. Takumi Kobayashi, National Institute of AIST

 31. A Convolutional Temporal Encoder for Video Caption Generation. Qingle Huang (Zhejiang University), and Zicheng Liao

 32. Marginalized CNN: Learning Deep Invariant Representations. Jian ZHAO (NUS), Jianshu Li Fang Zhao Xuecheng Nie Yunpeng Chen Shuicheng Yan and Jiashi Feng

 33. Correlation Hashing Network for Efficient Cross-Modal Retrieval. Yue Cao (Tsinghua University), Mingsheng Long and Jianmin Wang

 34. Sunrise or Sunset: Selective Comparison Learning for Subtle Attribute Recognition. Hong-Yu Zhou (Nanjing University), Bin-Bin Gao and Jianxin Wu

 35. BIM: Ball Intersection Multi Template Matching. Bat El Shlomo, Tel Aviv University

 36. Visual Textbook Network: Watch Carefully before Answering Visual Questions. Difei Gao (ICT), Ruiping Wang Shiguang Shan and Xilin Chen

 37. Key Person Aided Re-identification in Partially Ordered Pedestrian Set. Chen Chen (Chinese academy of sciences), Min Cao and Silong Peng

 38. Learning confidence measures in the wild. Fabio Tosi (University of Bologna), Matteo Poggi Stefano Mattoccia Alessio Tonioni and Luigi Di Stefano

 39. Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model. M. Saquib Sarfraz (KIT), Arne Schumann Yan Wang and Rainer Stiefelhagen

 40. Divide and Fuse: A Re-ranking Approach for Person Re-identification. Rui Yu (Huazhong University of Science and Technology), Zhichao Zhou Song Bai and Xiang Bai

 41. Joint Optimization of Coded Illumination and Grayscale Conversion for One-Shot Raw Material Classification. Chao Wang (Kyushu Institute of Technoloigy), and Takahiro Okabe

 42. Hand Pose Learning: Combining Deep Learning and Hierarchical Refinement for 3D Hand Pose Estimation. Min-Yu Wu (National Taiwan University), Ya Hui Tang, Pai-Wei Ting and Li-Chen Fu

 43. Learning Cross-scale Correspondence and Patch-based Synthesis for Reference-based Super-Resolution. Haitian Zheng (HKUST), Mengqi Ji Lei Han Ziwei Xu Haoqian Wang Yebin Liu and Lu Fang

 44. Anomaly Detection using a Convolutional Winner-Take-All Autoencoder. Hanh Tran (University of Leeds), and David Hogg

 45. A Parallel Architecture for High Frame Rate Stereo using Semi-Global Matching. Akshay Jain (IIIT Delhi), Alexander Fell and Saket Anand

 46. Accelerating Computation of Exemplar-SVM by Binary Approximation based on Matrix Decomposition. Takato Kurokawa (Chubu University), Yuji Yamauchi Mitsuru Ambai Takayoshi YAMASHITAand Hironobu Fujiyoshi

 47. Sparse and Noisy to Dense Depth Map Upsampling Based on Mesh and Colour Consistency. Hanshin Lim (Electronics and Telecommunications Research Institute), and Junseok Lee

 48. Efficient 3D Tracking in Urban Environments with Semantic Segmentation. Martin Hirzer (Graz University of Technology), Peter Roth and Vincent Lepetit

 49. Class Weighted Convolutional Features for Visual Instance Search. Albert Jimenez Jose Alvarez and Xavier Giro-i-Nieto

 50. Dynamic Steerable Blocks in Deep Residual Networks. Jörn-Henrik Jacobsen (University of Amsterdam), Bert De Brabandere and Arnold Smeulders

 51. Towards Complete Scene Reconstruction from Single-View Depth and Human Motion. Sam Fowler (University of Surrey), Hansung Kim and Adrian Hilton

 52. Flow Based Video Super-Resolution with Spatio-temporal Patch Similarity. Joan Duran (Universitat Illes Balears), and Antoni Buades

 53. BV-CNNs: Binary Volumetric Convolutional Networks for 3D Object Recognition. Chao Ma (NUDT), Wei An Yinjie Lei and Yulan Guo

 54. Combining Edge Images and Depth Maps for Robust Visual Odometry. Fabian Schenk (TU Graz), and Friedrich Fraundorfer

 55. Order-Adaptive and Illumination-Aware Variational Optical Flow Refinement. Daniel Maurer (University of Stuttgart), Michael Stoll and Andres Bruhn

 56. Large-scale Continual Road Inspection: Visual Infrastructure Assessment in the Wild. Ke Ma (Stony Brook University), Minh Hoai and Dimitris Samaras

 57. Correlation Filter Tracking: Beyond an Open-loop System. Qingyong Hu (National University of Defense), Yulan Guo Yunjin Chen Jingjing Xiao and Wei An

 58. Photorealistic Style Transfer with Screened Poisson Equation. Roey Mechrez (Technion), Eli Shechtman and Lihi Zelnik-Manor

 59. Probabilistic Spatial Regression using a Deep Fully Convolutional Neural Network. S M Masudur Rahman Al Arif (City University of London), Karen Knapp and Greg Slabaugh

 60. Lip Reading in Profile. Joon Son Chung (University of Oxford), and Andrew Zisserman

 61. Adversarial Robustness: Softmax versus Openmax. Andras Rozsa (UCCS), Manuel Gunther and Terrance Boult

 62. Generative 3D Hand Tracking with Spatially Constrained Pose Sampling. Konstantinos Roditakis (FORTH), Alexandros Makris and Antonis Argyros

 63. Efficient Online Surface Correction for Real-time Large-Scale 3D Reconstruction. Robert Maier (Technische Universität München), Raphael Schaller and Daniel Cremers

 64. Long Range Stereo from Synchronized Monocular Optical Flow Streamss. Darius Burschka, Technical University of Munich

 65. Learning temporal structures for human activity recognition. Tiantian Xu (New York University), and Edward Wong

 66. End-to-end multi-view lipreading. Stavros Petridis (Imperial College), Yujiang Wang Zuwei Li and Maja Pantic

 67. Supervised Scale-Regularized Linear Convolutionary Filters. Marco Loog and Francois Lauze

 68. Sparse Deep Feature Representation for Object Detection from Wearable Cameras. Quanfu Fan (IBM), and Richard Chen

 69. Human Action Segmentation using 3D Fully Convolutional Network. Pei Yu (Northwestern University), Jiang Wang and Ying Wu

 70. Deep fisher faces. Harald Hanselmann (HLTPR Group at RWTH Aachen), Shen Yan and Hermann Ney

 71. Improving target tracking robustness with Bayesian data fusion. Yevgeniy Reznichenko (Marquette University), and Henry Medeiros

 72. One-Shot Learning for Semantic Segmentation. Amirreza Shaban (Georgia Institute of Tech.), Shray Bansal Zhen Liu Irfan Essa and Byron Boots

 73. Efficent Traffic-Sign Recognition with Scale-aware CNN. Yuchen Yang (BJUT), Shuo Liu Wei Ma Qiuyuan Wang and Zheng Liu

 74. Plane-Aided Visual-Inertial Odometry for Pose Estimation of a 3D Camera based Indoor Blind Navigation System. He Zhang (Univ. of Arkansas at LR (UALR)), and cang Ye

 75. Dissecting scale from pose estimation in visual odometry. Rong yuan (Brown University), Hongyi Fan and Benjamin Kimia

 76. Automatic Image transformation for inducing affect. MOhsen Ali (Information Technology Uni.), and Afsheen Rafaqat

 77. Subpixel Semantic Flow. Berk Sevilmis (Brown University), and Benjamin Kimia

 78. Light Cascaded Convolutional Neural Networks for Accurate Player Detection. Keyu Lu (National University of Defense Technology), Jianhui Chen James Little and Hangen He

 79. Exploiting Protrusion Cues for Fast and Effective Shape Modeling via Ellipses. Alex Wong (UCLA), Alan Yuille and Brian Taylor

 80. A CNN-Based Approach for Automatic License Plate Recognition in the Wild. Meng Dong (University of Science and Technology of China), Dongliang He Chong Luo Dong Liu and Wenjun Zeng

 81. Multi-Region Ensemble Convolutional Neural Network for High Accuracy Age Estimation. Yiliang Chen (Macau University of Science and Technology), zichang Tan Alex Po Leung Jun Wan and Jianguo Zhang

 82. Primitive-based Surface Regularization for Urban 3D Reconstruction. Thomas Holzmann (Graz University of Technology), Martin Oswald Marc Pollefeys Friedrich Fraundorfer and Horst Bischof

 83. Cross-modal Retrieval via Memory Network. Ge Song (Nanjing University of Aeronaut), and Xiaoyang Tan

 84. A Compact Parametric Solution to Depth Sensor Calibration. Andrew Spek (Monash University), and Tom Drummond

 85. Pansharpening via Locality-Constrained Sparse Representation. Songze Tang (Nanjing Forest Police College), Nan zhou and Liang Xiao

 86. Residual Conv-Deconv Grid Network for Semantic Segmentation. Damien Fourure (Université Jean Monnet), Rémi Emonet Elisa Fromont Damien Muselet Alain Tremeau and Christian Wolf

 87. Deep GrabCut for Object Selection. Ning Xu (University of illinois), Brian Price Scott Cohen Jimei Yang and Thomas Huang

 88. Solar Power Plant Detection on Multi-Spectral Satellite Imagery using Weakly-Supervised CNN with Feedback Features and m-PCNN Fusion. Nevrez Imamoglu (AIST), Motoki Kimura Hiroki Miyamoto Aito Fujita and Ryosuke Nakamura

15:00 -- 15:30 Tea break, RGS

15:30 -- 17:00 Orals: Matching, RGS Theatre

Chair: Tom Drummond

15 :30 89. Multiple-Kernel Local-Patch Descriptor. Arun Mukundan (CMP), Giorgos Tolias and Ondrej Chum

15 :45 90. AutoScaler: Scale-Attention Networks for Visual Correspondence. Shenlong Wang (University of Toronto), Linjie Luo Ning Zhang and Jia Li

16 :00 91. Cross-View GAN Based Vehicle Generation for Re-identification. Yi Zhou (Northumbria University), and Ling Shao

16 :15 92. Efficient Video Summarization Using Principal Person Appearance for Video-Based Person Re-Identification. Seongro Yoon (INRIA), Furqan Khan and Francois Bremond

16 :30 93. Fine-Grained Forensic Matching. Bailey Kong (UC Irvine), James Supancic Deva Ramanan and Charless Fowlkes

16 :45 94. Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization. Yinpeng Dong (Tsinghua University), Jianguo Li and Renkun Ni

19:00 -- 21:00 Banquet, Millennium Gloucester Hotel


 Thursday, 7 Sep

7:30 --   Registration, RGS

8:00 -- 8:30 Coffee \& pastry, RGS

8:30 -- 8:45 Welcome, RGS Theatre

8:45 -- 10:15 Orals: Segmentation, RGS Theatre

Chair: Alan Yuille

8 :45 Weakly Supervised Semantic Segmentation Based on Co-segmentation. Tong Shen (The University of Adelaide ), Guosheng Lin Lingqiao Liu Chunhua Shen and Ian Reid

9 :00 Semantic Segmentation with Reverse Attention. Qin Huang (University of Southern Califor), Chihao Wu Chunyang Xia Ye Wang and C.-C. Jay Kuo

9 :15 Double Expansion for Optimization of Multilabel Energies. Yelena Gorelick (Western University), Zhengqin Li and Olga Veksler

9 :30 Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation. Arslan Chaudhry (University of Oxford), Puneet Kumar Dokania and Philip Torr

9 :45 Online Adaptation of Convolutional Neural Networks for Video Object Segmentation. Paul Voigtlaender (RWTH Aachen University), and Bastian Leibe

10 :00 Improved Bilinear Pooling with CNNs. Tsung-Yu Lin (UMass Amherst), and Subhransu Maji

10:15 -- 11:00 Break, RGS

11:00 -- 12:30 Orals: Enhancement, RGS Theatre

Chair: Lihi Zelnik-Manor 

11 :15 Reflectance and Shape Estimation with Handy Camera under Natural Illumination. Trung Ngo (Osaka University), Hajime Nagahara Ko Nishino Rin-ichiro Taniguchi and Yasushi Yagi

11 :30 GeneGAN: Learning Object Transfiguration and Object Subspace from Unpaired Data. Shuchang Zhou (Megvii Inc.), Taihong Xiao Yi Yang Dieqiao Feng Qinyao He and Weiran He

11 :45 PixColor: Pixel Recursive Colorization. Sergio Guadarrama (Google), Ryan Dahl David Bieber Jonathon Shlens Mohammad Norouzi and Kevin Murphy

12 :00 Depth Estimation and Blur Removal from a Single Out-of-focus Image. Saeed Anwar (ANU), Zeeshan Hayder and Fatih Porikli

12 :15 Exploring the structure of a real-time, arbitrary neural artistic stylization network. Golnaz Ghiasi (Google Inc.), Honglak Lee Manjunath Kudlur Vincent Dumoulin and Jonathon Shlens

12 :30 Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization. Frederick Tung (Simon Fraser University), Srikanth Muralidharan and Greg Mori

12:30 -- 13:15 Lunch, RGS


Workshop Programme: Thursday, 7 Sep

 13:30 -- 14:15 Workshops Keynote, ICL Huxley Bld.

Chair: Yannis Panagakis

13 :30   HoloLens: Computer Vision meets Mixed Reality. Jamie Shotton (Microsoft Research)

14:15 -- 16:00 5th Activity Monitoring by Multiple Distributed Sensing (AMMDS 2017), ICL Huxley Bld.

Chair: Pier Luigi Mazzeo, Paolo Spagnolo (National Research Council Italy)

14 :15 Welcome

14 :20 Superpixels based Manifold Structured Sparse RPCA for Moving Object Detection.   Sajid Javed, Arif Mahmood, Thierry Bouwmans, Soon Ki Jung 

14 :45 ATLAS: Adaptive Single Object Tracking using Off line Learned Motion and Visual Patterns.   Ruxandra G. Tapu, Bogdan Mocanu, Titus Zaharia 

15 :10 Vehicle Re-Identification by Fine-Grained Cross-Level Deep Learning. Aytaç Kanacı, Xiatian Z hu, Shaogang Gong 

15 :35 Geometry-Based Multiple Camera Head Detection in Dense Crowds.   Nicola Pellicano, Emanuel Aldea, Sylvie Le Hegarat-Mascle

14:15 -- 16:00 Deep Learning on Irregular Domains (DLID 2017), ICL Huxley Bld.

Chair: Xianghua Xie, Michael Edward (Swansea University), Pierre Vandergheynst, Michaël Defferrard (École Polytechnique Fédérale de Lausanne)

14 :15 Welcome

14 :20 Invited Speaker -- Michael Defferrard (EPFL)

14 :50 Invited Speaker -- Joost Bastings (University of Amsterdam)

15 :20 Invited Speaker -- Michael Edwards (Swansea University)

15 :50 Speaker -- Gilles Puy (Technicolor)

14:15 -- 16:00 Lip-Reading using deep learning methods (LRDLM 2017), ICL Huxley Bld.

Chair: Themos Stafylakis,  Georgios Tzimiropoulos (University of Nottingham), Stavros Petridis, Maja Pantic (Imperial College London)

14 :25 Welcome

14 :30 Keynote -- Andrew Zisserman and Joon Son Chung (University of Oxford \& Google DeepMind)

15 :30 Invited Speaker -- Helen L. Bear (University of East London)

14:15 -- 16:00 Automatic Face Analytics for Human Behavior Understanding (FaceHUB 2017), ICL Huxley Bld.

Chair: Xiaohua Huang, Guoying Zhao (University of Oulu)

14 :15 Welcome

14 :20 Oral Session

15 :00 Keynote -- Hatice Gunes (University of Cambridge)

16:00 -- 16:30 Tea break, ICL Huxley Bld.

16:30 -- 18:30 5th Activity Monitoring by Multiple Distributed Sensing (AMMDS 2017), ICL Huxley Bld.

Chair: Pier Luigi Mazzeo, Paolo Spagnolo (National Research Council Italy)

16 :30 Knowledge Driven Activity Recognition from Patterns of Object Use.  Isibor Kennedy Ihianle, Usman Naeem, Syed Islam 

16 :55 Extraction of Spatio temporal Descriptors for Maritime Vessel Detection using Attentive Sensing.  Roman Palenychka, Rafael Falcon, Rami Abielmona, Emil Petriu  

17 :20 Dense Net with pre-activated deconvolution for estimating depth map from single imageSaurav Sharma, Ram P Padhy, Suman Choudhury, Nabarun Goswami, Pankaj Kumar Sa 

17 :45 Fine segmentation for Activity of Daily Living analysis in a wide-angle multi-camera set-up.  Philipe Ambrozio Dias, Henry Medeiros, Francesca Odone

16:30 -- 18:30 Deep Learning on Irregular Domains (DLID 2017), ICL Huxley Bld.

Chair: Xianghua Xie, Michael Edward (Swansea University), Pierre Vandergheynst, Michaël Defferrard (École Polytechnique Fédérale de Lausanne)

16 :30 Invited Speaker -- Federico Monti

17 :00 Speaker -- Sei-ichiro Kamata

17 :15Speaker --  Jan P Siebert

17 :30Speaker -- Abhinav Agarwalla

17 :45Speaker --  Aditya Nigam

16:30 -- 18:30 Lip-Reading using deep learning methods (LRDLM 2017), ICL Huxley Bld.

Chair: Themos Stafylakis,  Georgios Tzimiropoulos (University of Nottingham), Stavros Petridis, Maja Pantic (ICL Huxley Bld.)

16 :30 Oral Session

17 :30 Poster Session

16:30 -- 18:30 Automatic Face Analytics for Human Behavior Understanding (FaceHUB 2017), ICL Huxley Bld.

Chair: Xiaohua Huang, Guoying Zhao (University of Oulu)

16 :30 Keynote -- Javier Orozo (Realeyes)

17 :30 Oral Session