BMVC 2018 Programme

The proceedings of BMVC 2018 and Workshops are available for download in one file, please do not download it while in the conference venue due to its size (3GB)
Please download the BMVC2018 Booklet for more information.
Monday 3rd September
12:00 Registration, Students Union
13:15 - 13:30 Briefing, Students Union
13:30 - 14:30 Tutorial 1, Students Union
Knowledge transfer and human-machine collaboration for training visual models.
Vittorio Ferrari (University of Edinburgh, Google Research)
14:30 - 15:30 Tutorial 2, Students Union
Towards action understanding with less supervision.
Ivan Laptev (INRIA Paris)
15:30 - 16:15 Tea Break, Students Union
16:15 - 17:15 Tutorial 3, Students Union
Supersizing and Empowering Visual Learning.
Abhinav Gupta (Carnegie Mellon University)
17:15 - 18:15 Tutorial 4, Students Union
Explaining and Representing Novel Concepts With Minimal Supervision.
Zeynep Akata (University of Amsterdam)
18:15 - 18:30 Instructions, Students Union
19:00 - 21:30 Reception, Civic Centre
Tuesday 4th September
7:30 - 7:45 Registration, Students Union
7:45 - 8:15 Coffee & Pastry, Students Union
8:15 - 8:30 Welcome, Students Union
8:30 - 10:00 Orals 1, Students Union: 3D Computer Vision
Chair: Tim Cootes
1. Learning to Generate and Reconstruct 3D Meshes with only 2D Supervision
Paul Henderson*, University of Edinburgh; Vittorio Ferrari, University of Edinburgh

Mirror 1 [PDF]
Mirror 2 [PDF]
2. LieNet: Real-time Monocular Object Instance 6D Pose Estimation
Thanh-Toan Do*, The University of Adelaide; Trung Pham, The University of Adelaide; Ming Cai, The University of Adelaide; Ian Reid, "University of Adelaide, Australia"

Mirror 1 [PDF]
Mirror 2 [PDF]
3. Scene Coordinate and Correspondence Learning for Image-Based Localization
Mai Bui*, TUM; Shadi Albarqouni, Technische Universität München, Germany; Slobodan Ilic, Siemens AG; Nassir Navab, "TU Munich, Germany"

Mirror 1 [PDF]
Mirror 2 [PDF]
4. Non-smooth M-estimator for Maximum Consensus Estimation
Huu Le*, University of Adelaide; Anders Eriksson, QUT; Thanh-Toan Do, The University of Adelaide; Tat-Jun Chin, University of Adelaide; David Suter, University of Adelaide

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
5. Deep Network for Simultaneous Stereo Matching and Dehazing
Taeyong Song, Yonsei University; Youngjung Kim, Yonsei Univ.; Changjae Oh, Queen Mary University of London; Kwanghoon Sohn *, Yonsei Univ.

Mirror 1 [PDF]
Mirror 2 [PDF]
6. SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data
Qi Chen, Johns Hopkins University; Weichao Qiu, Johns Hopkins University; Yi Zhang, Johns Hopkins University; Lingxi Xie*, JHU; Alan Yuille, Johns Hopkins University

Mirror 1 [PDF]
Mirror 2 [PDF]
10:00 - 10:45 Tea Break, Students Union
10:45 - 11:45 Keynote 1, Students Union
People Search In Large Scale Videos.
Shaogang (Sean) Gong (Queen Mary University of London)
Chair: Tim Hospedales
11:45 - 12:30 Spotlights 1, Students Union
7. Inductive Visual Localisation: Factorised Training for Superior Generalisation
Ankush Gupta (University of Oxford)*; Andrea Vedaldi (Oxford University); Andrew Zisserman (University of Oxford)

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
8. Equal But Not The Same: Understanding the Implicit Relationship Between Persuasive Images and Text
Mingda Zhang (University of Pittsburgh)*; Rebecca Hwa (University of Pittsburgh); Adriana Kovashka (University of Pittsburgh)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
9. Multi-task Mid-level Feature Alignment Network for Unsupervised Cross-Dataset Person Re-Identification
Shan Lin (University of Warwick)*; Haoliang Li (Nanyang Technological University); Chang-Tsun Li (Charles Sturt University); Alex Kot (Nanyang Technological University)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
10. EnsembleNet: Improving Grasp Detection using an Ensemble of Convolutional Neural Networks
Umar Asif (IBM Research)*; Jianbin Tang (IBM Research); Stefan Harrer (IBM Research)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
11. Motion Estimation and Segmentation of Natural Phenomena
Da Chen (University of Bath)*; Wenbin Li (Imperial College London); Peter Hall (University of Bath)

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
12. VSE++: Improving Visual-Semantic Embeddings with Hard Negatives
Fartash Faghri (University of Toronto)*; David Fleet (University of Toronto); Jamie Kiros (Google Inc.); Sanja Fidler (University of Toronto)

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
13. Learning to Doodle with Stroke Demonstrations and Deep Q-Networks
Tao Zhou (UCLA)*; CHEN FANG (Adobe Research, San Jose, CA); Zhaowen Wang (Adobe Research); Jimei Yang (Adobe); Byungmoon Kim (Adobe Systems Inc.); Zhili Chen (Adobe Research); Jonathan Brandt (-); Demetri Terzopoulos (University of California, Los Angeles)

Mirror 1 [PDF] [Video] [ZIP]
Mirror 2 [PDF] [Video] [ZIP]
14. Propagating Confidences through CNNs for Sparse Data Regression
Abdelrahman Eldesokey (Linköping University)*; Michael Felsberg (Linköping University); Fahad Shahbaz Khan (Linköping University)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
15. Recognition self-awareness for active object recognition on depth images
Andrea Roberti (University of Verona); Marco Carletti (University of Verona); Francesco Setti (University of Verona)*; Umberto Castellani (University of Verona ); Paolo Fiorini (N/A); Marco Cristani (University of Verona)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
16. Open Logo Detection Challenge
Hang Su (Queen Mary University of London)*; Xiatian Zhu (Queen Mary University, London, UK); Shaogang Gong (Queen Mary University of London)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
12:30 - 14:00 Lunch, Civic Centre
14:00 - 16:15 Posters 1, Students Union
17 - 26 Correspond to Tuesday Spotlights 1
17. Inductive Visual Localisation: Factorised Training for Superior Generalisation
Ankush Gupta (University of Oxford)*; Andrea Vedaldi (Oxford University); Andrew Zisserman (University of Oxford)

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
18. Equal But Not The Same: Understanding the Implicit Relationship Between Persuasive Images and Text
Mingda Zhang (University of Pittsburgh)*; Rebecca Hwa (University of Pittsburgh); Adriana Kovashka (University of Pittsburgh)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
19. Multi-task Mid-level Feature Alignment Network for Unsupervised Cross-Dataset Person Re-Identification
Shan Lin (University of Warwick)*; Haoliang Li (Nanyang Technological University); Chang-Tsun Li (Charles Sturt University); Alex Kot (Nanyang Technological University)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
20. EnsembleNet: Improving Grasp Detection using an Ensemble of Convolutional Neural Networks
Umar Asif (IBM Research)*; Jianbin Tang (IBM Research); Stefan Harrer (IBM Research)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
21. Motion Estimation and Segmentation of Natural Phenomena
Da Chen (University of Bath)*; Wenbin Li (Imperial College London); Peter Hall (University of Bath)

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
22. VSE++: Improving Visual-Semantic Embeddings with Hard Negatives
Fartash Faghri (University of Toronto)*; David Fleet (University of Toronto); Jamie Kiros (Google Inc.); Sanja Fidler (University of Toronto)

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
23. Learning to Doodle with Stroke Demonstrations and Deep Q-Networks
Tao Zhou (UCLA)*; CHEN FANG (Adobe Research, San Jose, CA); Zhaowen Wang (Adobe Research); Jimei Yang (Adobe); Byungmoon Kim (Adobe Systems Inc.); Zhili Chen (Adobe Research); Jonathan Brandt (-); Demetri Terzopoulos (University of California, Los Angeles)

Mirror 1 [PDF] [Video] [ZIP]
Mirror 2 [PDF] [Video] [ZIP]
24. Propagating Confidences through CNNs for Sparse Data Regression
Abdelrahman Eldesokey (Linköping University)*; Michael Felsberg (Linköping University); Fahad Shahbaz Khan (Linköping University)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
25. Recognition self-awareness for active object recognition on depth images
Andrea Roberti (University of Verona); Marco Carletti (University of Verona); Francesco Setti (University of Verona)*; Umberto Castellani (University of Verona ); Paolo Fiorini (N/A); Marco Cristani (University of Verona)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
26. Open Logo Detection Challenge
Hang Su (Queen Mary University of London)*; Xiatian Zhu (Queen Mary University, London, UK); Shaogang Gong (Queen Mary University of London)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
27 - 32 Correspond to Tuesday Orals 1
27. Learning to Generate and Reconstruct 3D Meshes with only 2D Supervision
Paul Henderson (University of Edinburgh)*; Vittorio Ferrari (Google Research)

Mirror 1 [PDF]
Mirror 2 [PDF]
28. SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data
Qi Chen (Johns Hopkins University); Weichao Qiu (Johns Hopkins University); Yi Zhang (Johns Hopkins University); Lingxi Xie (JHU)*; Alan Yuille (Johns Hopkins University)

Mirror 1 [PDF]
Mirror 2 [PDF]
29. Scene Coordinate and Correspondence Learning for Image-Based Localization
Mai Bui (TUM)*; Shadi Albarqouni (Technische Universität München, Germany); Slobodan Ilic (Siemens AG); Nassir Navab ("TU Munich, Germany")

Mirror 1 [PDF]
Mirror 2 [PDF]
30. Non-smooth M-estimator for Maximum Consensus Estimation
Huu Minh Le (Queensland University of Technology)*; Anders Eriksson (QUT); Michael Milford (ACRV and QUT, Australia); Thanh-Toan Do (The University of Adelaide); Tat-Jun Chin (University of Adelaide); David Suter (University of Adelaide)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
31. LieNet: Real-time Monocular Object Instance 6D Pose Estimation
Thanh-Toan Do (The University of Adelaide)*; Trung Pham (NVIDIA); Ming Cai (The University of Adelaide); Ian Reid ("University of Adelaide, Australia")

Mirror 1 [PDF]
Mirror 2 [PDF]
32. Deep Network for Simultaneous Stereo Matching and Dehazing
Taeyong Song (Yonsei University); Youngjung Kim (Yonsei Univ.); Changjae Oh (Queen Mary University of London); Kwanghoon Sohn (Yonsei Univ.)*

Mirror 1 [PDF]
Mirror 2 [PDF]
33 - 39 Correspond to Tuesday Orals 2
33. BAM: Bottleneck Attention Module
Jongchan Park (KAIST)*; Sanghyun Woo (KAIST); Joon-Young Lee (Adobe Research); In So Kweon (KAIST)

Mirror 1 [PDF]
Mirror 2 [PDF]
34. Three for one and one for three: Flow, Segmentation, and Surface Normals
Hoang-An Le (University of Amsterdam)*; Anil S Baslamisli (University of Amsterdam); Thomas Mensink (UvA); Theo Gevers (University of Amsterdam)

Mirror 1 [PDF]
Mirror 2 [PDF]
35. ContextNet: Exploring Context and Detail \\for Semantic Segmentation in Real-time
Rudra P K Poudel (Tosihiba Research Europe)*; Ujwal Bonde (Toshiba Research); Stephan Liwicki (Toshiba Research Europe Ltd); Christopher Zach (Toshiba Research)

Mirror 1 [PDF]
Mirror 2 [PDF]
36. Efficient Progressive Neural Architecture Search
Juan-Manuel Perez-Rua (Orange Labs)*; Moez Baccouche (Orange Labs); Stephane Pateux (Orange Labs)

Mirror 1 [PDF]
Mirror 2 [PDF]
37. Learning on the Edge: Explicit Boundary Handling in CNNs
Carlo Innamorati (University College London)*; Niloy Mitra (University College London)

Mirror 1 [PDF] [ZIP]
Mirror 2 [PDF] [ZIP]
38. Structured Probabilistic Pruning for Convolutional Neural Network Acceleration
"Huan Wang (Zhejiang University); Qiming Zhang (Zhejiang University); Yuehai Wang (Zhejiang University); Haoji Hu (ZJU)*"

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
39. RISE: Randomized Input Sampling for Explanation of Black-box Models
Vitali Petsiuk (Boston University)*; Abir Das (Boston University); Kate Saenko (Boston University)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]

40. Asymmetric Geodesic Distance Propagation for Active Contours
Da CHEN (University Paris Dauphine)*; Jack A Spencer (University of Liverpool); Jean-Marie Mirebeau (University Paris-Sud, University Paris-Saclay); Ke Chen (United Kingdom); Laurent Cohen (University Paris Dauphine)

Mirror 1 [PDF]
Mirror 2 [PDF]
41. iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection
Chen Gao (Virginia Tech)*; Yuliang Zou (Virginia Tech); Jia-Bin Huang (Virginia Tech)

Mirror 1 [PDF]
Mirror 2 [PDF]
42. Parallel Separable 3D Convolution for Video and Volumetric Data Understanding
Felix Gonda (Harvard University)*; Donglai Wei (Harvard/SEAS); Toufiq Parag (Harvard University); hanspeter pfister (harvard university)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
43. Semantic Embedding for Sketch-Based 3D Shape Retrieval
Anran Qi (Queen Mary University of London)*; Yi-Zhe Song (Queen Mary University of London); Tao Xiang (Queen Mary, University of London, UK)

Mirror 1 [PDF]
Mirror 2 [PDF]
44. Stacked Dense U-Nets with Dual Transformers for Robust Face Alignment
Jia Guo (DeepInsight); Jiankang Deng (Imperial College London)*; Niannan Xue (Imperial College London); Stefanos Zafeiriou (Imperial College Londong)

Mirror 1 [PDF]
Mirror 2 [PDF]
45. Unconstrained Control of Feature Map Size Using Non-integer Strided Sampling
Donggyu Joo (KAIST)*; Junho Yim (Korea Advanced Institute of Science and Technology); Junmo Kim (KAIST)

Mirror 1 [PDF]
Mirror 2 [PDF]
46. Mass Displacement Networks
Natalia Neverova (Facebook AI Research)*; Iasonas Kokkinos (Facebook AI Research)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
47. Efficient Correction for EM Connectomics with Skeletal Representation
Konstantin Dimitriev (SUNY, Stony Brook, NY); Toufiq Parag (Harvard University)*; Brian Matejek (Harvard University ); Arie Kaufman (Stony Brook University); Hanspeter Pfister (Harvard University)

Mirror 1 [PDF]
Mirror 2 [PDF]
48. Deep Association Learning for Unsupervised Video Person Re-identification
Yanbei Chen (Queen Mary University of London)*; Xiatian Zhu (Queen Mary University, London, UK); Shaogang Gong (Queen Mary University of London)

Mirror 1 [PDF]
Mirror 2 [PDF]
49. Estimating small differences in car-pose from orbits
Berkay Kicanaoglu (University of Amsterdam)*; Ran Tao (University of Amsterdam); Arnold W.M. Smeulders (University of Amsterdam)

Mirror 1 [PDF]
Mirror 2 [PDF]
50. Weakly-Supervised Video Object Grounding from Text by Loss Weighting and Object Interaction
Luowei Zhou (University of Michigan)*; Nathan Louis (University of Michigan); Jason J Corso (University of Michigan)

Mirror 1 [PDF]
Mirror 2 [PDF]
51. Improving Image Clustering With Multiple Pretrained CNN Feature Extractors
Joris Guerin (ENSAM)*; Byron Boots (Georgia Institute of Technology)

Mirror 1 [PDF]
Mirror 2 [PDF]
52. Informed Democracy: Voting-based Novelty Detection for Action Recognition
Alina Roitberg (KIT)*; Ziad Al-Halah (KIT); Rainer Stiefelhagen (Karlsruhe Institute of Technology)

Mirror 1 [PDF]
Mirror 2 [PDF]
53. Pose Flow: Efficient Online Pose Tracking
Yuliang Xiu (Shanghai Jiao Tong University)*; Jiefeng Li (Shanghai Jiao Tong University); Haoyu Wang (Shanghai Jiao Tong University ); Yinghong Fang (Shanghai Jiao Tong University); Cewu Lu (Shanghai Jiao Tong University)

Mirror 1 [PDF]
Mirror 2 [PDF]
54. Conditional Kronecker Batch Normalization for Compositional Reasoning
"Cheng Shi (Tsinghua University)*; Chun Yuan (Tsinghua University); Jiayin Cai (Xi'an Jiaotong University); Zhuobin Zheng ( Tsinghua University); YangYang Cheng (Tsinghua University); Zhihui Lin (Tsinghua University)"

Mirror 1 [PDF]
Mirror 2 [PDF]
55. 3D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Image
Priyanka Mandikal (Indian Institute of Science)*; Navaneet K L (Indian Institute of Science); Mayank Agarwal (BITS Pilani); Venkatesh Babu RADHAKRISHNAN (Indian Institute of Science)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
56. Zero-Shot Object Detection by Hybrid Region Embedding
Berkan Demirel (HAVELSAN Inc. & METU); Ramazan Gokberk Cinbis (METU)*; Nazli Ikizler-Cinbis (Hacettepe University)

Mirror 1 [PDF]
Mirror 2 [PDF]
57. Story Understanding in Video Advertisements
Keren Ye (University of Pittsburgh)*; Kyle Buettner (University of Pittsburgh); Adriana Kovashka (University of Pittsburgh)

Mirror 1 [PDF]
Mirror 2 [PDF]
58. Not All Words Are Equal: Video-specific Information Loss for Video Captioning
Jiarong Dong (Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China); Ke Gao (Institute of Computing Technology, Chinese )*; Xiaokai Chen (Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China); junbo guo (ICT); Juan Cao (Institute of Computing Technology, Chinese); Yongdong Zhang (Chinese Academy of Sciences)

Mirror 1 [PDF]
Mirror 2 [PDF]
59. Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages
Yuxi Li (Shanghai Jiao Tong University)*; Jiuwei Li (Intel Labs); Weiyao Lin (Shanghai Jiaotong University); Jianguo Li (Intel Labs)

Mirror 1 [PDF]
Mirror 2 [PDF]
60. Incremental Tube Construction for Human Action Detection
Harkirat Singh Behl (IIT Kanpur)*; Michael Sapienza (Samsung Research America); Gurkirt Singh (Oxford Brookes University); Suman Saha (Oxford Brookes University); Fabio Cuzzolin (Oxford Brookes University); Philip Torr (University of Oxford)

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
61. Training Student Networks for Acceleration with Conditional Adversarial Networks
Zheng Xu (Univ. of Maryland)*; Yen-Chang Hsu (Georgia Institute of Technology); Jiawei Huang (Honda Research)

Mirror 1 [PDF]
Mirror 2 [PDF]
62. Super-resolution of Very Low Resolution Faces from Videos
"Esra Ataer-Cansizogle (MERL); Michael Jones (MERL)"

Mirror 1 [PDF]
Mirror 2 [PDF]
63. Semi-supervised Skin Lesion Segmentation via Transformation Consistent Self-ensembling Model
Xiaomeng Li (The Chinese University of Hong Kong)*; Lequan Yu (The Chinese University of Hong Kong); Hao Chen (The Chinese University of Hong Kong); Chi-Wing Fu (The Chinese University of Hong Kong); Pheng-Ann Heng (The Chinese Univsersity of Hong Kong)

Mirror 1 [PDF]
Mirror 2 [PDF]
64. Metric Learning for Novelty and Anomaly Detection
Marc Masana (Computer Vision Center)*; Idoia Ruiz (Computer Vision Center); Joan Serrat (Computer Vision Center); Joost van de Weijer (Computer Vision Center); Antonio M. Lopez (CVC & UAB)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
65. Adversarial Learning for Semi-supervised Semantic Segmentation
Wei-Chih Hung (University of California, Merced)*; Yi-Hsuan Tsai (NEC Labs America); Yan-Ting Liou (National Taiwan University); Yen-Yu Lin (Academia Sinica); Ming-Hsuan Yang (University of California at Merced)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
66. Dynamic Super-Rays for Efficient Light Field Video Processing
Matthieu Hog (Technicolor)*; Neus Sabater (Technicolor); Christine Guillemot (INRIA)

Mirror 1 [PDF] [SUPP] [Video-1] [Video-2] [Video-3] [Video-4] [Video-5] [Video-6] [Video-7] [Video-8]
Mirror 2 [PDF] [SUPP] [Video-1] [Video-2] [Video-3] [Video-4] [Video-5] [Video-6] [Video-7] [Video-8]
67. Holistic and Deep Feature Pyramids for Saliency Detection
Shizhong Dong (Shenzhen Institutes of Advanced Technology); Zhifan Gao (University of Western Ontario); Shanhui Sun (CuraCloud); xin wang (CuraCloud); ming li (Shenzhen Institutes of Advanced Technology); heye zhang (Shenzhen Institutes of Advanced Technology)*; Guang Yang (Imperial College London); Huafeng Liu (Zhejiang University); Shuo Li (University of Western Ontario)

Mirror 1 [PDF]
Mirror 2 [PDF]
68. Sparse Estimation of Light Transport Matrix under Saturated Condition
Naoya Chiba (Graduate School of Information Science, Tohoku University)*; Koichi Hashimoto (Graduate School of Information Science, Tohoku University)

Mirror 1 [PDF]
Mirror 2 [PDF]
69. Synthetic View Generation for Absolute Pose Regression and Image Synthesis
Pulak Purkait (Toshiba Research Europe Ltd)*; Cheng Zhao (Birmingham University); Christopher Zach (Toshiba Research)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
70. Self-supervised Deep Multiple Choice Learning Network for Blind Image Quality Assessment
Kwan-Yee Lin (Peking university)*; Guanxiang Wang (Peking University)

Mirror 1 [PDF]
Mirror 2 [PDF]
71. Classifier Two Sample Test for Video Anomaly Detections
Yusha Liu (Carnegie Mellon University)*; Chun-Liang Li (Carnegie Mellon University); Barnabas Poczos ( Carnegie Mellon University)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
72. A Mixed Classification-Regression Framework for 3D Pose Estimation from 2D Images
Siddharth Mahendran (Johns Hopkins University)*; Haider Ali (Johns Hopkins University); Rene Vidal (Johns Hopkins University)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
73. Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption
Peilun Li (Carnegie Mellon University)*; XIAODAN LIANG (Carnegie Mellon University); Daoyuan Jia (Carnegie Mellon University); Eric Xing (CMU)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
74. Classification-Based Supervised Hashing with Complementary Networks for Image Search
Dong-ju Jeong (Seoul National University)*; Sungkwon Choo (Seoul National University); Wonkyo Seo (Seoul National University); Nam Ik Cho (Seoul National University)

Mirror 1 [PDF]
Mirror 2 [PDF]
75. Semantic Localisation via Globally Unique Instance Segmentation
Ignas Budvytis (Department of Engineering, University of Cambridge)*; Patrick Sauer (Toyota Motor Europe); Roberto Cipolla (University of Cambridge)

Mirror 1 [PDF] [SUPP] [Video-1] [Video-2] [Video-3] [Video-4]
Mirror 2 [PDF] [SUPP] [Video-1] [Video-2] [Video-3] [Video-4]
76. MC-GAN: Multi-conditional Generative Adversarial Network for Image Synthesis
Hyojin Park (Seoul National University)*; Youngjoon Yoo (Clova AI Research, NAVER Corp. ); Nojun Kwak (Seoul National University)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
77. InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset
Wenbin Li (Imperial College London)*; Sajad Saeedi (Imperial College London); John McCormac (Imperial College London); Ronald Clark (Imperial College London); Dimos Tzoumanikas (Imperial College London); Qing Ye (kujiale.com); Yuzhong Huang (University of Southern California); Rui Tang (kujiale.com); Stefan Leutenegger (Imperial College London)

Mirror 1 [PDF]
Mirror 2 [PDF]
78. In Defense of Single-column Networks for Crowd Counting
Ze Wang (Beihang University)*; Zehao Xiao (Beihang University); Kai Xie (Institute of North Electronic Equipment); Qiang Qiu (Duke University); Xiantong Zhen (Beihang University); Xianbin Cao (Beihang University, China)

Mirror 1 [PDF]
Mirror 2 [PDF]
79. Few-Shot Semantic Segmentation with Prototype Learning
Nanqing Dong (Cornell University)*; Eric Xing (Petuum Inc.)

Mirror 1 [PDF]
Mirror 2 [PDF]
80. SymmNet: A Symmetric Convolutional Neural Network for Occlusion Detection
Ang Li (Xi‘an Jiaotong University)*; Zejian Yuan (Xi‘an Jiaotong University)

Mirror 1 [PDF]
Mirror 2 [PDF]
81. Joint Holistic and Partial CNN for Pedestrian Detection
Yun Zhao (Xi'an Jiaotong University)*; Zejian Yuan (Xi‘an Jiaotong University); Hui Zhang (Shenzhen Forward Innovation Digital Technology Co. Ltd. China)

Mirror 1 [PDF]
Mirror 2 [PDF]
82. Think and Tell: Preview Network for Image Captioning
Zhihao Zhu (Xi'an Jiaotong University)*; zhan xue (Xi'an Jiaotong university ); Zejian Yuan (Xi‘an Jiaotong University)

Mirror 1 [PDF]
Mirror 2 [PDF]
83. Adaptive Multi-Scale Information Flow for Object Detection
Xiaoyu Chen (University of Electronic Science and Technology of China)*; Wei Li (University of Electronic Science and Technology of China); Qingbo Wu (University of Electronic Science and Technology of China); Fanman Meng (University of Electronic Science and Technology of China)

Mirror 1 [PDF]
Mirror 2 [PDF]
84. Visual Heart Rate Estimation with Convolutional Neural Network
Radim Spetlik (Center for Machine Perception)*; Vojtech Franc (Center for Machine Perception); Jan Cech (Czech Technical University); Jiri Matas (CMP CTU FEE)

Mirror 1 [PDF]
Mirror 2 [PDF]
85. Visually-Driven Semantic Augmentation for Zero-Shot Learning
Abhinaba Roy (Istituto Italiano di Tecnologia)*; Jacopo Cavazza (Istituto Italiano di Tecnologia); Vittorio Murino (Istituto Italiano di Tecnologia)

Mirror 1 [PDF]
Mirror 2 [PDF]
86. ProFlow: Learning to Predict Optical Flow
Daniel Maurer (University of Stuttgart)*; Andrés Bruhn (University of Stuttgart)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
87. Deep Collaborative Tracking Networks
Xiaolong Jiang (Beihang Unviersity)*; Xiantong Zhen (Beihang University); Baochang Zhang (Beihang University); Jian Yang (Insitute of North Electronic Equipment); Xianbin Cao (Beihang University, China)

Mirror 1 [PDF]
Mirror 2 [PDF]
88. Adaptive Time-Slice Block-Matching Optical Flow Algorithm for Dynamic Vision Sensors
Min Liu (Institute of Neuroinformatics)*; Tobi Delbruck (Nil)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
89. Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid
Di Kang (City University of Hong Kong)*; Antoni Chan (City University of Hong Kong, Hong, Kong)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
90. Multi-Task Deep Networks for Depth-Based 6D Object Pose and Joint Registration in Crowd Scenarios
Juil Sock (Imperial College London)*; Kwang In Kim (University of Bath); Caner Sahin (Imperial College London); Tae-Kyun Kim (Imperial College London)

Mirror 1 [PDF]
Mirror 2 [PDF]
91. Deep active learning for object detection
Soumya Roy (IIT, Kanpur)*; Asim Unmesh (IIT, Kanpur); Vinay P Namboodiri (IIT Kanpur)

Mirror 1 [PDF]
Mirror 2 [PDF]
92. OriNet: A Fully Convolutional Network for 3D Human Pose Estimation
Chenxu Luo (Johns Hopkins University)*; Xiao Chu (Baidu Research (USA)); Alan Yuille (Johns Hopkins University)

Mirror 1 [PDF]
Mirror 2 [PDF]
93. Towards Light-weight Annotations: Fuzzy Interpolative Reasoning for Zero-shot Image Classificaiton
Yang Long (Newcastle University)*; Yao Tan (Northumbria University); Daniel Organisciak (Northumbria University); Longzhi Yang (Northumbria); Ling Shao (Inception Institute of Artificial Intelligence)

Mirror 1 [PDF]
Mirror 2 [PDF]
94. Recurrent Multi-frame Single Shot Detector for Video Object Detection
"Alex Broad (University of Northwestern); Michael Jones (MERL)*; Teng-Yok Lee (Mitsubishi Electric Research Laboratories (MERL))"

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
95. Persuasive Faces: Generating Faces in Advertisements
Christopher L Thomas (University of Pittsburgh)*; Adriana Kovashka (University of Pittsburgh)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
96. The Multiscale Bowler-Hat Transform for Vessel Enhancement in 3D Biomedical Images
Cigdem Sazak (Durham University); Carl J. Nelson (Glasgow University); Boguslaw Obara (Durham University)*

Mirror 1 [PDF]
Mirror 2 [PDF]
97. SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting
Yuhang Song (USC)*; Chao Yang (University of Southern California); Yeji Shen (University of Southern California); Peng Wang (Baidu USA LLC); Qin Huang (University of Southern California); C.-C. Jay Kuo (USC)

Mirror 1 [PDF]
Mirror 2 [PDF]
98. Exemplar-Supported Generative Reproduction for Class Incremental Learning
Chen He (Institute of Computing Technology, Chinese Academy of Sciences); Ruiping Wang (ICT, CAS)*; Shiguang Shan (Chinese Academy of Sciences); Xilin Chen (China)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
99. GAN-based Semi-supervised Learning On Fewer Labeled Samples
Takumi Kobayashi (National Institute of Advanced Industrial Science and Technology)*

Mirror 1 [PDF]
Mirror 2 [PDF]
100. Generative Adversarial Guided Learning for Domain Adaptation
Kai-Ya Wei (National Tsing Hua University); Chiou-Ting Hsu (National Tsing Hua University)*

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
101. IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks
Ke Sun (University of Science and Technology of China)*; Mingjie Li (University of Science and Technology of China); Dong Liu (University of Science and Technology of China); Jingdong Wang (Microsoft Research)

Mirror 1 [PDF]
Mirror 2 [PDF]
102. Self-Supervised Feature Learning for Semantic Segmentation of Overhead Imagery
Suriya Singh (IIIT)*; Anil Batra (IIIT); Guan Pang (Facebook); Lorenzo Torresani (Dartmouth College); Saikat Basu (Facebook); Manohar Paluri (Facebook); C.V. Jawahar (IIIT-Hyderabad)

Mirror 1 [PDF]
Mirror 2 [PDF]
103. Active Learning for Regression Tasks with Expected Model Output Changes
Christoph Käding (Computer Vision Group, Friedrich Schiller University Jena, Germany)*; Erik Rodner (Carl Zeiss AG, Jena, Germany); Alexander Freytag (Carl Zeiss AG, Jena, Germany); Oliver Mothes (Computer Vision Group, Friedrich Schiller University Jena, Germany); Björn Barz (Computer Vision Group, Friedrich Schiller University Jena); Joachim Denzler (Computer Vision Group, Friedrich Schiller University Jena, Germany)

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
104. A Quantitative Platform for Non-Line-of-Sight Imaging Problems
Jonathan Klein (University of Bonn)*; Martin Laurenzis (French-German Research Institute of Saint-Louis (ISL)); Dominik Michels (King Abdullah University of Science and Technology (KAUST)); Matthias B Hullin (University of Bonn)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
105. Few-shot learning of neural networks from scratch by pseudo example optimization
Akisato Kimura (NTT Communication Science Laboratories)*; Zoubin Ghahramani (University of Cambridge); Koh Takeuchi (NTT); Tomoharu Iwata (NTT Communication Science Laboratories); Naonori Ueda (NTT)

Mirror 1 [PDF]
Mirror 2 [PDF]
106. Directional Priors for Multi-Frame Optical Flow
Daniel Maurer (University of Stuttgart)*; Michael Stoll (University of Stuttgart); Andrés Bruhn (University of Stuttgart)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
107. Wide Range Depth Estimation from Binocular Light Field Camera
feng dai (ICT); Xianyu Chen (Institute of Computing Technology, Chinese Academy of Science); Yike Ma (ICT); Guoqing Jin (ICT); Qiang Zhao (The Institute of Computing Technology of the Chinese Academy of Sciences)*

Mirror 1 [PDF]
Mirror 2 [PDF]
108. CaloriNet: From silhouettes to calorie estimation in private environments
Alessandro Masullo (University of Bristol)*; Tilo Burghardt (University of Bristol); Dima Damen (University of Bristol); Sion Hannuna (University of Bristol); Víctor Ponce-López (University of Bristol); Majid Mirmehdi (University of Bristol)

Mirror 1 [PDF]
Mirror 2 [PDF]
109. Identity Preserving Face Completion for Large Ocular Region Occlusion
Yajie Zhao (USC Institute for Creative Technology )*; Weikai Chen (USC Institute for Creative Technology); Jun Xing (Institute for Creative Technologies, USC); Xiaoming Li (Harbin Institute of Technology); Zach Bessinger (University of Kentucky); Fuchang Liu (Hangzhou Normal University); Wangmeng Zuo (Harbin Institute of Technology); Ruigang Yang (University of Kentucky, USA)

Mirror 1 [PDF]
Mirror 2 [PDF]
110. ESTHER: Extremely Simple Image Translation Through Self-Regularization
Chao Yang (University of Southern California)*; Taehwan Kim (ObEN, Inc.); Ruizhe Wang (ObEN, Inc.); Hao Peng (ObEN, Inc.); C.-C. Jay Kuo (USC)

Mirror 1 [PDF]
Mirror 2 [PDF]
111. Multicolumn Networks for Face Recognition
Weidi Xie (University of Oxford)*; Andrew Zisserman (University of Oxford)

Mirror 1 [PDF]
Mirror 2 [PDF]
112. Progressive Attention Networks for Visual Attribute Prediction
Paul Hongsuck Seo (POSTECH)*; Zhe Lin (Adobe Research); Scott Cohen (Adobe Research); Xiaohui Shen (Adobe Research); Bohyung Han (Seoul National University)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
113. Cross-Class Sample Synthesis for Zero-shot Learning
Jinlu Liu (Renmin University of China); Xirong Li (Renmin University of China); Gang Yang (Renmin University of China)*

Mirror 1 [PDF]
Mirror 2 [PDF]
114. Shadow Detection Using Robust Texture Learning
Tianxiang Pan (Tsinghua University)*; Bin Wang (Tsinghua University); guiguang ding (Tsinghua University, China); JunHai Yong (Tsinghua University)

Mirror 1 [PDF]
Mirror 2 [PDF]
115. DeepInsight: Multi-Task Multi-Scale Deep Learning for Mental Disorder Diagnosis
Mingyu Ding (Renmin University of China); Yuqi Huo (Renmin University of China); Jun Hu (School of Information, Renmin University of China); Zhiwu Lu (Renmin University of China)*

Mirror 1 [PDF]
Mirror 2 [PDF]
116. SurReal: enhancing Surgical simulation Realism using style transfer
Imanol Luengo (Touch Surgery)*; Evangello Flouty (Digital Surgery); Petros Giataganas (Touch Surgery); Piyamate Wisanuvej (Digital Surgery); Jean Nehme (Digital Surgery); Danail Stoyanov (Touch Surgery)

Mirror 1 [PDF] [Video] [ZIP]
Mirror 2 [PDF] [Video] [ZIP]
117. Guided Upsampling Network for Real-Time Semantic Segmentation
Davide Mazzini (University of Milano-Bicocca)*

Mirror 1 [PDF]
Mirror 2 [PDF]
118. Point Attention Network for Gesture Recognition Using Point Cloud Data
Cherdsak Kingkan (Graduate School of Information Sciences, Tohoku University)*; Joshua Owoyemi (Graduate School of Information Science, Tohoku University); Koichi Hashimoto (Graduate School of Information Science, Tohoku University)

Mirror 1 [PDF]
Mirror 2 [PDF]
119. A Decomposed Dual-Cross Generative Adversarial Network for Image Rain Removal
Xin Jin (University of Science and Technology of China); Zhibo Chen (University of Science and Technology of China)*; Jianxin Lin (University of Science and Technology of China); Jiale Chen (University of Science and Technology of China); Wei Zhou (University of Science and Technology of China); Chaowei Shan (University of Science and Technology of China)

Mirror 1 [PDF]
Mirror 2 [PDF]
120. Light-Field Intrinsic Dataset
Sumit Shekhar (MPI-Informatik)*; Shida Beigpour (MPI-Informatik); Matthias Ziegler (Fraunhofer IIS); Michał Chwesiuk (West Pomeranian University of Technology); Dawid Paleń (West Pomeranian University of Technology); Karol Myszkowski (MPI-Informatik ); Joachim Keinert (Fraunhofer IIS); Radosław Mantiuk (West Pomeranian University of Technology); Piotr Didyk (Università della Svizzera italiana)

Mirror 1 [PDF] [SUPP-1] [SUPP-2] [Video-1] [Video-2] [Video-3]
Mirror 2 [PDF] [SUPP-1] [SUPP-2] [Video-1] [Video-2] [Video-3]
121. CEREALS – Cost-Effective REgion-based Active Learning for Semantic Segmentation
Radek J Mackowiak (Robert Bosch GmbH)*; Philip Lenz (Robert Bosch GmbH); Omair Ghori (Robert Bosch GmbH); Ferran Diego (Robert Bosch GmbH); Oliver Lange (Robert Bosch GmbH); Carsten Rother (University of Heidelberg)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
122. Large scale evaluation of local image feature detectors on homography datasets
Karel Lenc (University of Oxford)*; Andrea Vedaldi (Oxford University)

Mirror 1 [PDF]
Mirror 2 [PDF]
123. Error Correction Maximization for Deep Image Hashing
Xiang Xu (Carnegie Mellon University)*; Xiaofang Wang (Carnegie Mellon University); Kris Kitani (CMU)

Mirror 1 [PDF]
Mirror 2 [PDF]
124. Learning a Code-Space Predictor by Exploiting Intra-Image-Dependencies
Jan P Klopp (National Taiwan University)*; Yu-Chiang Frank Wang (National Taiwan University); Shao-Yi Chien (National Taiwan University); Liang-Gee Chen (National Taiwan University)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
125. Light-Weight RefineNet for Real-Time Semantic Segmentation
Vladimir Nekrasov (University of Adelaide / ACRV)*; Chunhua Shen (University of Adelaide); Ian Reid ("University of Adelaide, Australia")

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
126. Accurate Detection and Localization of Checkerboard Corners for Calibration
Alexander Duda (Kraken Robotik GmbH)*; Udo Frese (DFKI)

Mirror 1 [PDF]
Mirror 2 [PDF]
127. 3D Object Structure Recovery via Semi-supervised Learning on Videos
Qian He (ShanghaiTech University)*; Desen Zhou (ShanghaiTech University); Xuming He (ShanghaiTech University)

Mirror 1 [PDF]
Mirror 2 [PDF]
128. Deep Video Color Propagation
Simone Meyer (ETH Zurich)*; Victor Cornillere (ETH Zurich); Abdelaziz Djelouah (Disney Research); Christopher Schroers (Disney Research); Markus Gross (ETH Zurich)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
129. 3D Human Pose Estimation with Relational Networks
Sungheon Park (Seoul National University)*; Nojun Kwak (Seoul National University)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
130. Image-derived generative modeling of pseudo-macromolecular structures -- towards the statistical assessment of Electron CryoTomography template matching
Kaiwen Wang (Carnegie Mellon University); Xiangrui Zeng (Carnegie Mellon University); Xiaodan Liang (Carnegie Mellon University); Zhiguang Huo (University of Florida); Eric Xing (CMU); Min Xu (Carnegie Mellon University)*

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
131. Ranking CGANs: Subjective Control over Semantic Image Attributes
Yassir Saquil (University of Bath)*; Kwang In Kim (University of Bath); Peter M Hall (University of Bath)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
132. License Plate Recognition and Super-resolution from Low-Resolution Videos by Convolutional Neural Networks
Vojtech Vasek (Eyedea Recognition Ltd.); Vojtech Franc (Center for Machine Perception)*; Martin Urban (Eyedea Recognition Ltd.)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
133. End-to-End Speech-Driven Facial Animation with Temporal GANs
Konstantinos Vougioukas (Imperial College London)*; Stavros Petridis (Imperial College London); Maja Pantic (Imperial College London)

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
134. 2sRanking-CNN: A 2-stage ranking-CNN for diagnosis of glaucoma from fundus images using CAM-extracted ROI as an intermediate input
Tae Joon Jun (KAIST)*; Dohyeun Kim (KAIST); Hoang Minh Nguyen (KAIST); Daeyoung Kim (KAIST); Youngsub Eom (Korea University College of Medicine)

Mirror 1 [PDF]
Mirror 2 [PDF]
135. DeSTNet: Densely Fused Spatial Transformer Networks
Roberto Annunziata (Onfido)*; Christos Sagonas (Onfido); Jacques Cali (Onfido)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
136. Fewer is More: Image Segmentation Based Weakly Supervised Object Detection with Partial Aggregation
Ce Ge (Beijing University of Posts and Telecommunications)*; Jingyu Wang (Beijing University of Posts and Telecommunications); Qi Qi (Beijing University of Posts and Telecommunications); Haifeng Sun (Beijing University of Posts and Telecommunications); Jianxin Liao (Beijing University of Posts and Telecommunications)

Mirror 1 [PDF]
Mirror 2 [PDF]
137. Future Semantic Segmentation with Convolutional LSTM
Seyed shahabeddin Nabavi (University of Manitoba)*; Mrigank Rochan (University of Manitoba); Yang Wang (University of Manitoba)

Mirror 1 [PDF]
Mirror 2 [PDF]
138. Action Completion: A Temporal Model for Moment Detection
Farnoosh Heidarivincheh (University of Bristol); Majid Mirmehdi (University of Bristol); Dima Damen (University of Bristol)*

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
139. Multiple Object Tracking by Learning Feature Representation and Distance Metric Jointly
Jun Xiang (South-Central University For Nationalities); Guoshuai Zhang (South-Central University For Nationalities); Nong Sang (School of Automation, Huazhong University of Science and Technology); Rui Huang (The Chinese University of Hong Kong, Shenzhen); Jianhua Hou (South-Central University For Nationalities)*

Mirror 1 [PDF]
Mirror 2 [PDF]
140. Highway Driving Dataset for Semantic Video Segmentation
Byungju Kim (KAIST); Junho Yim (Korea Advanced Institute of Science and Technology); Junmo Kim (KAIST)*

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
141. The Minimalist Camera
"Parita Pooj ( Columbia University)*; Michael Grossberg (City University of New York); Peter Belhumeur ( Columbia University); Shree Nayar ( Columbia University)"

Mirror 1 [PDF]
Mirror 2 [PDF]
142. Localization Guided Learning for Pedestrian Attribute Recognition
Pengze Liu (City University of Hong Kong)*; Xihui Liu (The Chinese University of Hong Kong); Junjie Yan (Sensetime Group Limited); Jing Shao (The Chinese University of Hong Kong)

Mirror 1 [PDF]
Mirror 2 [PDF]
143. Local Point Pair Feature Histogram for Accurate 3D Matching
Anders G Buch (University of Southern Denmark)*; Dirk Kraft (Syddansk Universitet)

Mirror 1 [PDF]
Mirror 2 [PDF]
144. Learning Geo-Temporal Image Features
Menghua Zhai (University of Kentucky)*; Tawfiq Salem (University of Kentucky); Connor S Greenwell (University of Kentucky); Scott Workman (University of Kentucky); Robert Pless (George Washington University); Nathan Jacobs (University of Kentucky)

Mirror 1 [PDF]
Mirror 2 [PDF]
16:15 - 16:45 Tea Break, Students Union
16:45 - 18:30 Orals 2, Students Union: Learning and Recognition
Chair: Jungong Han
145. Three for one and one for three: Flow, Segmentation, and Surface Normals
Hoang-An Le*, University of Amsterdam; Anil Baslamisli, University of Amsterdam; Thomas Mensink, UvA; Theo Gevers, University of Amsterdam

Mirror 1 [PDF]
Mirror 2 [PDF]
146. ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time
Rudra Poudel*, Tosihiba Research Europe; Ujwal Bonde, Toshiba Research; Stephan Liwicki, Toshiba Research Europe Ltd; Christopher Zach, Toshiba Research

Mirror 1 [PDF]
Mirror 2 [PDF]
147. BAM: Bottleneck Attention Module
Jongchan Park*, KAIST; Sanghyun Woo, KAIST; Joon-Young Lee, Adobe Research; In So Kweon, KAIST

Mirror 1 [PDF]
Mirror 2 [PDF]
148. Learning on the Edge: Explicit Boundary Handling in CNNs
"Carlo Innamorati (University College London)*; Tobias Ritschel (University College London); Tim Weyrich (University College London); Niloy J. Mitra (University College London) "

Mirror 1 [PDF] [ZIP]
Mirror 2 [PDF] [ZIP]
149. Structured Probabilistic Pruning for Convolutional Neural Network Acceleration
Huan Wang, Zhejiang University; Qiming Zhang, Zhejiang University; Yuehai Wang, Zhejiang University; Haoji Hu*, ZJU

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
150. Efficient Progressive Neural Architecture Search
Juan-Manuel Perez-Rua*, Orange Labs; Moez Baccouche, Orange Labs; Stephane Pateux, Orange Labs

Mirror 1 [PDF]
Mirror 2 [PDF]
151. RISE: Randomized Input Sampling for Explanation of Black-box Models
Vitali Petsiuk*, Boston University; Abir Das, Boston University; Kate Saenko, Boston University

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
19:00 - 21:30 Simple Dinner, Civic Centre
Wednesday 5th September
7:30 - 7:45 Registration, Students Union
7:45 - 8:30 Coffee & Pastry, Students Union
8:30 - 10:00 Orals 3, Students Union: Low Level Vision and Computational Photography
Chair: Dimitris Metaxas
152. Direct Shot Correspondence Matching
"Umer Rafi (RWTH Aachen University)*; Jurgen Gall (University of Bonn); Bastian Leibe (RWTH Aachen University); "

Mirror 1 [PDF]
Mirror 2 [PDF]
153. Gated Fusion Network for Joint Image Deblurring and Super-Resolution
Xinyi Zhang*, National Engineering Laboratory for Vision Information Processing and Application, Xi’an Jiaotong University; Hang Dong, National Engineering Laboratory for Vision Information Processing and Application, Xi'an Jiaotong University; Zhe Hu, Hikvision Research; Wei-Sheng Lai, University of California, Merced; Fei Wang, Xi'an Jiaotong University; Ming-Hsuan Yang, University of California at Merced

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
154. Semantic Priors for Intrinsic Image Decomposition
Saurabh Saini*, International Institute of Information Technology Hyderabad; P. J. Narayanan, IIIT-Hyderabad

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
155. Deep Retinex Decomposition for Low-Light Enhancement
Chen Wei*, Peking University; Wenjing Wang, Peking University; Wenhan Yang, Peking University; Jiaying Liu, Peking University

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
156. Pixel-level Semantics Guided Image Colorization
JIAOJIAO ZHAO*, University of Amsterdam; Li Liu, the inception institute of artificial intelligence; Cees Snoek, University of Amsterdam; Jungong Han, Lancaster University; Ling Shao, Inception Institute of Artificial Intelligence

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
157. Automatic Semantic Content Removal by Learning to Neglect
Siyang Qin*, University of California, Santa Cruz; Jiahui Wei, University of California, Santa Cruz; Roberto Manduchi, University of California Santa Cruz

Mirror 1 [PDF]
Mirror 2 [PDF]
10:00 - 10:45 Tea Break, Students Union
10:45 - 11:45 Keynote 2, Students Union
The Role of Symmetry in Human and Computer Vision.
Sven Dickinson (University of Toronto)
Chair: David Crandall
11:45 - 12:30 Spotlights 2, Students Union
158. CNN-based Action Recognition and Supervised Domain Adaptation on 3D Body Skeletons via Kernel Feature Maps
Yusuf Tas (Data61); Piotr Koniusz (Data61/CSIRO, ANU)*

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
159. Deep Covariance Descriptors for Facial Expression Recognition
Naima OTBERDOUT (Mohammed V University in Rabat, Morocco.)*; Anis Kacem (IMT LILLE-DOUAI, CRIStAL UMR CNRS 8198); Mohamed Daoudi (IMT Lille Douai); Lahoucine Ballihi (Mohammed V University in Rabat); Stefano Berretti (University of Florence, Italy)

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
160. Video Time: Properties, Encoders and Evaluation
Amir Ghodrati (University of Amsterdam)*; Efstratios Gavves (University of Amsterdam ); Cees Snoek (University of Amsterdam)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
161. Modelling Diffusion Process by Deep Neural Networks for Image Retrieval
yan zhao (SCIT, university of wollongong); Lei Wang ("University of Wollongong, Australia")*; Luping Zhou (University of Sydney); Yinghuan Shi (Nanjing University); Yang Gao (Nanjing University)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
162. Memory-efficient Global Refinement of Decision-Tree Ensembles and its Application to Face Alignment
Nenad Markus (n/a); Ivan Gogić (Faculty of Electrical Engineering and Computing, University of Zagreb)*; Igor Pandzic (n/a); Jorgen Ahlberg (TST, Sweden)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
163. A Novel Method For Unsupervised Scanner-Invariance Using A Dual-Channel Auto-Encoder Model
Andrew D Moyes (Queen's University, Belfast)*; Kun Zhang (Queen's University, Belfast); Liping Wang (Queen's University, Belfast); Ming Ji (Queen's University, Belfast); Danny Crookes (Queen's University Belfast); Huiyu Zhou (Queen's University Belfast)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
164. Improved Visual Relocalization by Discovering Anchor Points
Soham Saha (International Institute of Information Technology, Hyderabad)*; Girish Varma (IIIT Hyderabad); C.V. Jawahar (IIIT-Hyderabad)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
165. Bidirectional Long Short-Term Memory Variational Autoencoder
Henglin Shi (University of Oulu); Xin Liu (University of Oulu); xiaopeng hong (University of Oulu, Finland); Guoying Zhao (University of Oulu)*

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
166. Phase retrieval for Fourier Ptychography under varying amount of measurements
Lokesh Boominathan (Aindra Systems)*; Mayug Maniparambil (IIT Madras); Honey Gupta (IIT Madras); Rahul Baburajan (IIT Madras); Kaushik Mitra (IIT Madras)

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
12:30 - 14:00 Lunch, Civic Centre
14:00 - 16:15 Posters 2, Students Union
167 - 175 Correspond to Wednesday Spotlights 2
167. CNN-based Action Recognition and Supervised Domain Adaptation on 3D Body Skeletons via Kernel Feature Maps
Yusuf Tas (Data61); Piotr Koniusz (Data61/CSIRO, ANU)*

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
168. Deep Covariance Descriptors for Facial Expression Recognition
Naima OTBERDOUT (Mohammed V University in Rabat, Morocco.)*; Anis Kacem (IMT LILLE-DOUAI, CRIStAL UMR CNRS 8198); Mohamed Daoudi (IMT Lille Douai); Lahoucine Ballihi (Mohammed V University in Rabat); Stefano Berretti (University of Florence, Italy)

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
169. Video Time: Properties, Encoders and Evaluation
Amir Ghodrati (University of Amsterdam)*; Efstratios Gavves (University of Amsterdam ); Cees Snoek (University of Amsterdam)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
170. Modelling Diffusion Process by Deep Neural Networks for Image Retrieval
yan zhao (SCIT, university of wollongong); Lei Wang ("University of Wollongong, Australia")*; Luping Zhou (University of Sydney); Yinghuan Shi (Nanjing University); Yang Gao (Nanjing University)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
171. Memory-efficient Global Refinement of Decision-Tree Ensembles and its Application to Face Alignment
Nenad Markus (n/a); Ivan Gogić (Faculty of Electrical Engineering and Computing, University of Zagreb)*; Igor Pandzic (n/a); Jorgen Ahlberg (TST, Sweden)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
172. A Novel Method For Unsupervised Scanner-Invariance Using A Dual-Channel Auto-Encoder Model
Andrew D Moyes (Queen's University, Belfast)*; Kun Zhang (Queen's University, Belfast); Liping Wang (Queen's University, Belfast); Ming Ji (Queen's University, Belfast); Danny Crookes (Queen's University Belfast); Huiyu Zhou (Queen's University Belfast)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
173. Improved Visual Relocalization by Discovering Anchor Points
Soham Saha (International Institute of Information Technology, Hyderabad)*; Girish Varma (IIIT Hyderabad); C.V. Jawahar (IIIT-Hyderabad)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
174. Bidirectional Long Short-Term Memory Variational Autoencoder
Henglin Shi (University of Oulu); Xin Liu (University of Oulu); xiaopeng hong (University of Oulu, Finland); Guoying Zhao (University of Oulu)*

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
175. Phase retrieval for Fourier Ptychography under varying amount of measurements
Lokesh Boominathan (Aindra Systems)*; Mayug Maniparambil (IIT Madras); Honey Gupta (IIT Madras); Rahul Baburajan (IIT Madras); Kaushik Mitra (IIT Madras)

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
176 - 181 Correspond to Wednesday Orals 3
176. Pixel-level Semantics Guided Image Colorization
JIAOJIAO ZHAO (University of Amsterdam)*; Li Liu (the inception institute of artificial intelligence); Cees Snoek (University of Amsterdam); Jungong Han (Lancaster University); Ling Shao (Inception Institute of Artificial Intelligence)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
177. Gated Fusion Network for Joint Image Deblurring and Super-Resolution
Xinyi Zhang (National Engineering Laboratory for Vision Information Processing and Application, Xi’an Jiaotong University)*; Hang Dong (National Engineering Laboratory for Vision Information Processing and Application, Xi'an Jiaotong University); Zhe Hu (Hikvision Research); Wei-Sheng Lai (University of California, Merced); Fei Wang (Xi'an Jiaotong University); Ming-Hsuan Yang (University of California at Merced)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
178. Direct Shot Correspondence Matching
Umer Rafi (RWTH Aachen University)*; Bastian Leibe (RWTH Aachen University-); Jurgen Gall (University of Bonn)

Mirror 1 [PDF]
Mirror 2 [PDF]
179. Deep Retinex Decomposition for Low-Light Enhancement
Chen Wei (Peking University)*; Wenjing Wang (Peking University); Wenhan Yang (Peking University); Jiaying Liu (Peking University)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
180. Semantic Priors for Intrinsic Image Decomposition
Saurabh Saini (International Institute of Information Technology Hyderabad)*; P. J. Narayanan (IIIT-Hyderabad)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
181. Automatic Semantic Content Removal by Learning to Neglect
Siyang Qin (University of California, Santa Cruz)*; Jiahui Wei (University of California, Santa Cruz); Roberto Manduchi (University of California Santa Cruz)

Mirror 1 [PDF]
Mirror 2 [PDF]
182 - 188 Correspond to Wednesday Orals 4
182. S3D: Single Shot multi-Span Detector via Fully 3D Convolutional Networks
Da Zhang (UC Santa Barbara)*; Xiyang Dai (UMD); Xin Wang (University of California, Santa Barbara); Yuan-Fang Wang (UC Santa Barbara)

Mirror 1 [PDF]
Mirror 2 [PDF]
183. Budget-Aware Activity Detection with A Recurrent Policy Network
"Behrooz Mahasseni (Apple); Xiaodong Yang (NVIDIA)*; Pavlo Molchanov (NVIDIA); Jan Kautz (NVIDIA)"

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
184. From Coarse Attention to Fine-Grained Gaze: A Two-stage 3D Fully Convolutional Network for Predicting Eye Gaze in First Person Video
Zehua Zhang (Indiana University)*; Sven Bambach (Indiana University); Chen Yu (Indiana University); David Crandall (Indiana University)

Mirror 1 [PDF]
Mirror 2 [PDF]
185. LikeNet: A Siamese Motion Estimation Network Trained in an Unsupervised Way
Aria Ahmadi (Queen Mary University of London)*; Marras Ioannis (Queen Mary University of London); Ioannis Patras (Queen Mary University of London)

Mirror 1 [PDF]
Mirror 2 [PDF]
186. Learning Human Optical Flow
Anurag Ranjan (MPI for Intelligent Systems)*; Javier Romero (MPI-IS); Michael J. Black (Max Planck Institute for Intelligent Systems)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
187. Video Summarisation by Classification with Deep Reinforcement Learning
Kaiyang Zhou (Queen Mary University of London, UK)*; Tao Xiang (Queen Mary, University of London, UK); ANDREA CAVALLARO (Queen Mary University of London, UK)

Mirror 1 [PDF]
Mirror 2 [PDF]
188. QuaterNet: A Quaternion-based Recurrent Model for Human Motion
Dario Pavllo (Facebook)*; David Grangier (Facebook); Michael Auli (Facebook)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
189 - 194 Correspond to Thursday Orals 5
189. It's all Relative: Monocular 3D Human Pose Estimation from Weakly Supervised Data
Matteo Ruggero Ronchi (California Institute of Technology)*; Oisin Mac Aodha (Caltech); Robert Eng (Caltech); Pietro Perona (CALTECH, USA)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
190. 3D Hand Pose Estimation using Simulation and Partial-Supervision with a Shared Latent Space
Masoud Abdi (Institute for Intelligent Systems Research and Innovation - Deakin University)*; Ehsan M Abbasnejad (Adelaide); Chee Peng Lim (Deakin University); Saeid Nahavandi (Institute for Intelligent Systems Research and Innovation (IISRI)/Deakin University)

Mirror 1 [PDF]
Mirror 2 [PDF]
191. Self-supervised learning of a facial attribute embedding from video
Olivia Wiles (University of Oxford); A S Koepke (University of Oxford)*; Andrew Zisserman (University of Oxford)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
192. Face Verification from Depth using Privileged Information
Guido Borghi (University of Modena and Reggio Emilia)*; Stefano Pini (University of Modena and Reggio Emilia); Filippo Grazioli (University of Modena and Reggio Emilia); ROBERTO VEZZANI (University of Modena and Reggio Emilia, Italy); Rita Cucchiara (University of Modena and Reggio Emilia)

Mirror 1 [PDF]
Mirror 2 [PDF]
193. Sign Language Production using Neural Machine Translation and Generative Adversarial Networks
Stephanie M Stoll (Centre for Vision, Speech and Signal Processing)*; Necati Cihan Camgoz (University of Surrey); Simon Hadfield (University of Surrey); Richard Bowden (University of Surrey)

Mirror 1 [PDF]
Mirror 2 [PDF]
194. CU-Net: Coupled U-Nets
Zhiqiang Tang (Rutgers)*; Xi Peng (Rutgers University); Shijie Geng (Rutgers); Yizhe Zhu (Rutgers); Dimitris Metaxas (Rutgers)

Mirror 1 [PDF]
Mirror 2 [PDF]
195 - 199 Correspond to Thursday Orals 6
195. End-to-end Image Captioning Exploits Multimodal Distributional Similarity
Pranava Madhyastha (University of Sheffield)*; Josiah Wang (University of Sheffield); Lucia Specia (University of Sheffield)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
196. Boosting up Scene Text Detectors with Guided CNN
Xiaoyu Yue (SenseTime)*; Zhanghui Kuang (Sensetime Ltd.); Zhaoyang Zhang (Sensetime Ltd.); Zhenfang Chen (The university of Hong Kong); Pan He (University of Florida); Yu Qiao (Multimedia Laboratory, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences); Wei Zhang (SenseTime Research)

Mirror 1 [PDF]
Mirror 2 [PDF]
197. Y-Net: A deep Convolutional Neural Network to Polyp Detection
"Ahmed Kedir Mohammed (NTNU)*; Sule Yildirim-Yayilgan (NTNU); Ivar Farup (NTNU); Marius Pedersen (NTNU, Gjovik, Norway); Øistein Hovde (University of Oslo)"

Mirror 1 [PDF]
Mirror 2 [PDF]
198. Guitar Music Transcription from Silent Video
Shir Goldstein (IDC)*; Yael Moses (IDC, Israel)

Mirror 1 [PDF] [SUPP] [Video-1] [Video-2]
Mirror 2 [PDF] [SUPP] [Video-1] [Video-2]
199. Image Retrieval with Mixed Initiative and Multimodal Feedback
Nils Murrugarra-Llerena (University of Pittsburgh)*; Adriana Kovashka (University of Pittsburgh)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]

200. Human Activity Recognition with Pose-driven Attention to RGB
Fabien Baradel (LIRIS)*; Christian Wolf (INSA Lyon); Julien Mille (INSA Centre Val de Loire)

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
201. Generating Photorealistic Facial Expressions in Dyadic Interactions
Yuchi Huang (ACT)*; Saad Khan (ACTNext ACT Inc)

Mirror 1 [PDF]
Mirror 2 [PDF]
202. An Efficient End-to-End Neural Model for Handwritten Text Recognition
Arindam Chowdhury (Innovation Labs, Tata Consultancy Services Limited)*; Lovekesh Vig (Innovation Labs, Tata Consultancy Services Limited)

Mirror 1 [PDF]
Mirror 2 [PDF]
203. Online Multi-Object Tracking with Structural Invariance Constraint
Xiao Zhou (Xi'an Jiaotong University); Peilin Jiang (Xi'an Jiaotong Univerity)*; Zhao Wei (Xi'an Jiaotong University); Hang Dong (Xi’an Jiaotong University); Fei Wang (Xi'an Jiaotong University)

Mirror 1 [PDF]
Mirror 2 [PDF]
204. Self-attention Learning for Person Re-identification
Minyue Jiang (Northwestern Polytechnical University); Yuan Yuan ( Northwestern Polytechnical University); Qi Wang (Northwestern Polytechnical University)*

Mirror 1 [PDF]
Mirror 2 [PDF]
205. Improving Fast Segmentation With Teacher-Student Learning
Jiafeng Xie (Sun Yat-sen University); Bing Shuai (Nanyang Technological University); Jian-Fang HU (Sun Yat-sen University)*; Jingyang Lin (Sun Yat-sen University); WEI-SHI ZHENG (Sun Yat-sen University, China)

Mirror 1 [PDF]
Mirror 2 [PDF]
206. Asymmetric Spatio-Temporal Embeddings for Large-Scale Image-to-Video Retrieval
Noa Garcia (Aston University)*; George Vogiatzis (Aston University)

Mirror 1 [PDF]
Mirror 2 [PDF]
207. Adaptive Context-aware Reinforced Agent for Handwritten Text Recognition
Liangke Gui (Carnegie Mellon University)*; XIAODAN LIANG (Carnegie Mellon University); Xiaojun Chang (Carnegie Mellon University); Alexander Hauptmann (Carnegie Mellon University)

Mirror 1 [PDF]
Mirror 2 [PDF]
208. Attentional Alignment Networks
Lei Yue (Beihang University)*; Xin Miao (The University of Texas at Arlington); Pengbo Wang (Shanghai Jiao Tong University); Baochang Zhang (Beihang University); Xiantong Zhen (Beihang University); Xianbin Cao (Beihang University, China)

Mirror 1 [PDF]
Mirror 2 [PDF]
209. Regional Attention Based Deep Feature for Image Retrieval
Jaeyoon Kim (KAIST); Sungeui Yoon (KAIST)*

Mirror 1 [PDF]
Mirror 2 [PDF]
210. Learning and Thinking Strategy for Training Sequence Generation Models
Yu Li (Institute of Computing Technology, Chinese Academy of Sciences); Sheng Tang (Institute of Computing Technology, Chinese Academy of Sciences)*; Min Lin (Qihoo/360); junbo guo (ICT); Jintao Li (Institute of Computing Technology, Chinese Academy of Sciences); Shuicheng Yan (Qihoo/360)

Mirror 1 [PDF]
Mirror 2 [PDF]
211. A Deep Framework for Automatic Annotation with Application to Retail Warehouses
Kanika Mahajan (Tata Consultancy Services); ANIMA MAJUMDER (Tata Consultancy Services)*; Harika Nanduri (Tata Consultancy Services); Swagat Kumar (TCS Innovation Lab)

Mirror 1 [PDF]
Mirror 2 [PDF]
212. Iteratively Trained Interactive Segmentation
Sabarinath Mahadevan (RWTH Aachen University)*; Paul Voigtlaender (RWTH Aachen University); Bastian Leibe (RWTH Aachen University-)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
213. Feature Contraction: New ConvNet Regularization in Image Classification
Vladimir Li (KTH Royal Institute of Technology)*; Atsuto Maki (KTH Royal Institute of Technology)

Mirror 1 [PDF]
Mirror 2 [PDF]
214. Deep Attentional Structured Representation Learning for Visual Recognition
Krishna Kanth Nakka (EPFL)*; Mathieu Salzmann (EPFL)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
215. Ellipse Detection on Images Using Conic Power of Two Points
Min Liu (Purdue University); BODI Yuan (UC Berkeley)*; Jing Bai (Beifang University of Nationalities)

Mirror 1 [PDF]
Mirror 2 [PDF]
216. Parsing Pose of People with Interaction
"Serim Ryou (California Institute of Technology)*; Pietro Perona (California Institute of Technology)"

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
217. A Highly Accurate Feature Fusion Network For Vehicle Detection In Surveillance Scenarios
"Jianqiang Wang (THU)*; Ya-Li Li (THU); Shengjin Wang (THU); "

Mirror 1 [PDF]
Mirror 2 [PDF]
218. Structure Aligning Discriminative Latent Embedding for Zero-Shot Learning
Omkar Anil Gune (Indian Institute of Technology Bombay)*; Biplab Banerjee (Indian Institute of Technology, Bombay); Subhasis Chaudhuri (Indian Institute of Technology Bombay)

Mirror 1 [PDF]
Mirror 2 [PDF]
219. ROI-wise Reverse Reweighting Network for Road Marking Detection
Xiaoqiang Zhang (Northwestern Polytechnical University); Yuan Yuan (Northwestern Polytechnical University); Qi Wang (Northwestern Polytechnical University)*

Mirror 1 [PDF]
Mirror 2 [PDF]
220. MBLLEN: Low-Light Image/Video Enhancement Using CNNs
Feifan Lv (Beihang University); Feng Lu (Beihang University)*; Jianhua Wu (Panasonic Singapore Laboratory); Chongsoon Lim (Panasonic Singapore Laboratory)

Mirror 1 [PDF]
Mirror 2 [PDF]
221. Hierachical Image Link Selection Scheme for Duplicate Structure Disambiguation
Fan Wang (Stony Brook University)*; Aditi Nayak (Stony Brook University); Yogesh Agrawal (Stony Brook University); Roy Shilkrot (Stony Brook University)

Mirror 1 [PDF]
Mirror 2 [PDF]
222. Single Image Super-Resolution via Squeeze and Excitation Network
Tao Jiang (Shaanxi Normal University); yu zhang (Shaanxi normal university)*; Xiaojun Wu (Shaanxi Normal University); Yuan Rao (xi'an Jiaotong university); Mingquan Zhou (Beijing Normal University)

Mirror 1 [PDF]
Mirror 2 [PDF]
223. WebCaricature: a benchmark for caricature recognition
Jing Huo (Nanjing University)*; Wenbin Li (Nanjing University); Yinghuan Shi (Nanjing University); Yang Gao (Nanjing University); Hujun Yin (University of Manchester )

Mirror 1 [PDF]
Mirror 2 [PDF]
224. Resembled Generative Adversarial Networks: Two Domains with Similar Attributes
Duhyeon Bang (Yonsei university); Hyunjung Shim (Yonsei University)*

Mirror 1 [PDF]
Mirror 2 [PDF]
225. Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation
Chengyang Li (Zhejiang University)*; Dan Song (Zhejiang University); Ruofeng Tong (Zhejiang University); Min Tang (Zhejiang University)

Mirror 1 [PDF]
Mirror 2 [PDF]
226. Identity-based Adversarial Training of Deep CNNs for Facial Action Unit Recognition
Zheng Zhang (University of Binghamtom)*; Shuangfei Zhai (Binghamton University); Lijun Yin (State University of New York at Binghamton)

Mirror 1 [PDF]
Mirror 2 [PDF]
227. A Fine-to-Coarse Convolutional Neural Network for 3D Human Action Recognition
Thao M. Le (Tokyo Institute of Technology)*; Nakamasa Inoue (Tokyo Institute of Technology); Koichi Shinoda (Tokyo Institute of Technology)

Mirror 1 [PDF]
Mirror 2 [PDF]
228. Dense Correspondence of Cone-Beam Computed Tomography Images Using Oblique Clustering Forest
Diya Sun (Peking University); Yuru Pei (Peking University)*; Yuke Guo (Luoyang Institute of Science and Technology); Gengyu Ma (Usens Inc); Tianmin Xu (Peking University); Hongbin Zha (Peking University, China)

Mirror 1 [PDF]
Mirror 2 [PDF]
229. Attention is All We Need: Nailing Down Object-centric Attention for Egocentric Activity Recognition
Swathikiran Sudhakaran (Fondazione Bruno Kessler, Italy); Oswald Lanz (Fondazione Bruno Kessler, Italy)*

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
230. Structure-Aware 3D Shape Synthesis from Single-View Images
Xuyang Hu (Anhui University); Fan Zhu (the inception institute of artificial intelligence )*; Li Liu (the inception institute of artificial intelligence); Jin Xie (Nanjing University of Science and Technology); Jun Tang (Anhui University); Nian Wang (Anhui University); Fumin Shen (UESTC); Ling Shao (Inception Institute of Artificial Intelligence)

Mirror 1 [PDF]
Mirror 2 [PDF]
231. Robust Adversarial Perturbation on Deep Proposal-based Models
Yuezun Li (SUNY, albany)*; Daniel Tian (Berkshire School); Ming-Ching Chang (Albany University); Xiao Bian (GE Global Research); Siwei Lyu (University at Albany)

Mirror 1 [PDF]
Mirror 2 [PDF]
232. Compact Neural Networks based on the Multiscale Entanglement Renormalization Ansatz
"Andrew Hallam (University College London)*; Edward Grant (University College London); Vid Stojevic (University College London); Simone Severini (University College London); Andrew G. Green (University College London)"

Mirror 1 [PDF]
Mirror 2 [PDF]
233. Joint Action Unit localisation and intensity estimation through heatmap regression
Enrique Sánchez-Lozano (University of Nottingham)*; Georgios Tzimiropoulos (University of Nottingham); Michel Valstar (University of Nottingham)

Mirror 1 [PDF]
Mirror 2 [PDF]
234. Multiplicative vs. Additive Half-Quadratic Minimization for Robust Cost Optimization
Christopher Zach (Toshiba Research)*; Guillaume M Bourmaud (University of Bordeaux)

Mirror 1 [PDF]
Mirror 2 [PDF]
235. A Differential Approach for Gaze Estimation with Calibration
Gang Liu (Idiap Research Institute)*; Yu Yu (Idiap, and EPFL); Kenneth Alberto Funes Mora (Eyeware); JEAN-MARC ODOBEZ (IDIAP/EPFL, SWITZERLAND)

Mirror 1 [PDF]
Mirror 2 [PDF]
236. SAM-RCNN: Scale-Aware Multi-Resolution Multi-Channel Pedestrian Detection
Tianrui Liu (Imperial College London)*; Mohamed ElMikaty (Imperial College London); Tania Stathaki (n/a)

Mirror 1 [PDF]
Mirror 2 [PDF]
237. Understanding Deep Architectures by Visual Summaries
Marco Godi (University of Verona)*; Marco Carletti (University of Verona); Maya Aghaei (Istituto Italiano di Tecnologia); Francesco Giuliari (University of Verona); Marco Cristani (University of Verona)

Mirror 1 [PDF]
Mirror 2 [PDF]
238. A Hybrid Probabilistic Model for Camera Relocalization
Ming Cai (The University of Adelaide)*; Chunhua Shen (University of Adelaide); Ian Reid ("University of Adelaide, Australia")

Mirror 1 [PDF]
Mirror 2 [PDF]
239. Action Recognition with the Augmented MoCap Data using Neural Data Translation
Shih-Yao Lin (Tencent America LLC)*; Yen-Yu Lin (Academia Sinica)

Mirror 1 [PDF]
Mirror 2 [PDF]
240. StitchAD-GAN for Synthesizing Apparent Diffusion Coefficient Images of Clinically Significant Prostate Cancer
Zhiwei Wang (Huazhong University of Science and Technology); Yi Lin (Huazhong University of Science and Technology); Chunyuan Liao (Hiscene Technology); Kwang-Ting Cheng (Hong Kong University of Science and Technology); Xin Yang (Huazhong University of Science and Technology)*

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
241. Long-term object tracking with a moving event camera
Bharath Ramesh (National University of Singapore)*; Shihao Zhang (NUS); Zhi Wei Lee (NUS); Zhi Gao (NUS); Garrick Orchard (NUS); Cheng Xiang (National University of Singapore)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
242. Multi-Scale Recurrent Tracking via Pyramid Recurrent Network and Optical Flow
Ding Ma (Harbin Institute of Technology)*; Wei Bu (Harbin Institute of Technology); XIANGQIAN WU (Harbin Institute of Technology, China)

Mirror 1 [PDF]
Mirror 2 [PDF]
243. Strong Baseline for Single Image Dehazing with Deep Features and Instance Normalization
Zheng Xu (Univ. of Maryland)*; Xitong Yang (University of Maryland); Xue Li (Facebook); Xiaoshuai Sun (Harbin Institute of Technology)

Mirror 1 [PDF]
Mirror 2 [PDF]
244. Learning Regularization Weight for CRF Optimization
Jiaxiao Wu (University of Western Ontario); Olga Veksler (University of Western Ontario)*

Mirror 1 [PDF]
Mirror 2 [PDF]
245. Automatic X-ray Scattering Image Annotation via Double-View Fourier-Bessel Convolutional Networks
Ziqiao Guan (Stony Brook University)*; Hong Qin (Stony Brook University); Kevin Yager (Brookhaven National Laboratory); Youngwoo Choo (Yale University); Dantong Yu (New Jersey Institute of Technology)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
246. Semantics Meet Saliency: Exploring Domain Affinity and Models for Dual-Task Prediction
Md Amirul Islam (University of Manitoba)*; Mahmoud Kalash (University of Manitoba); Neil D. B. Bruce (Ryerson University)

Mirror 1 [PDF]
Mirror 2 [PDF]
247. Adaptive Appearance Rendering
Mengyao Zhai (Simon Fraser University)*; Ruizhi Deng (Simon Fraser University); Jiacheng Chen (Simon Fraser University); Lei Chen (Simon Fraser Univeristy); Zhiwei Deng (Simon Fraser University); Greg Mori (Simon Fraser University)

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
248. Network Decoupling: From Regular to Depthwise Separable Convolutions
Jianbo Guo (Tsinghua University)*; Yuxi Li (Shanghai Jiao Tong University); Weiyao Lin (Shanghai Jiaotong University); Yurong Chen (Intel Labs China); Jianguo Li (Intel Labs)

Mirror 1 [PDF]
Mirror 2 [PDF]
249. BUAA-PRO: A Tracking Dataset with Pixel-Level Annotation
Annan Li (Beijing University of Aeronautics and Astronautics)*; Zhiyuan Chen (Beijing University of Aeronautics and Astronautics); Yunhong Wang (State Key Laboratory of Virtual Reality Technology and System, Beihang University, Beijing 100191, China)

Mirror 1 [PDF]
Mirror 2 [PDF]
250. Reciprocal Attention Fusion for Visual Question Answering
Moshiur R Farazi (Australian National University (ANU))*; Salman Khan (Australian National University (ANU))

Mirror 1 [PDF]
Mirror 2 [PDF]
251. Recurrent CNN for 3D Gaze Estimation using Appearance and Shape Cues
Cristina Palmero (Universitat de Barcelona)*; Javier Selva (Universitat de Barcelona); Mohammad Ali Bagheri (University of Calgary); Sergio Escalera (Computer Vision Center (UAB) & University of Barcelona,)

Mirror 1 [PDF]
Mirror 2 [PDF]
252. Active Learning from Noisy Tagged Images
Ehsan M Abbasnejad (Adelaide)*; Anthony Dick (University of Adelaide, Australia); Qinfeng Shi (University of Adelaide); Anton Van Den Hengel (University of Adelaide)

Mirror 1 [PDF]
Mirror 2 [PDF]
253. STDnet: A ConvNet for Small Target Detection
Brais Bosquet (University of Santiago de Compostela)*; Manuel Mucientes (Universidade de Santiago de Compostela); Victor Brea (University of Santiago de Compostela, Spain)

Mirror 1 [PDF]
Mirror 2 [PDF]
254. Learning Human Poses from Actions
Aditya Arun (IIIT Hyderabad)*; C.V. Jawahar (IIIT-Hyderabad); M. Pawan Kumar (University of Oxford)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
255. 3D Motion Segmentation of Articulated Rigid Bodies based on RGB-D Data
"Urbano Miguel Nunes (Imperial College London)*; Yiannis Demiris (Imperial College London)"

Mirror 1 [PDF] [SUPP] [Video]
Mirror 2 [PDF] [SUPP] [Video]
256. Deep Evolutionary 3D Diffusion Heat Maps for Large-pose Face Alignment
Bin Sun (Northeastern University); Ming Shao (University of Massachusetts Dartmouth); Siyu Xia (Southeast University, China)*; YUN FU (Northeastern University)

Mirror 1 [PDF]
Mirror 2 [PDF]
257. Iterative Deep Learning for Road Topology Extraction
Carles Ventura (Universitat Oberta de Catalunya)*; Jordi Pont-Tuset (Eidgenössiche Technische Hochschule Zürich); Sergi Caelles (Eidgenössiche Technische Hochschule Zürich); Kevis-Kokitsi Maninis (Eidgenössiche Technische Hochschule Zürich); Luc Van Gool (ETH Zurich)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
258. Multi-phase Volume Segmentation with Tetrahedral Mesh
"Tuan T. Nguyen (Techinical University of Denmark)*; Vedrana A. Dahl (Technical University of Denmark); J. Andreas Bærentzen (Techinical University of Denmark); Camilla H. Trinderup (Techinical University of Denmark)"

Mirror 1 [PDF]
Mirror 2 [PDF]
259. AlphaGAN: Generative adversarial networks for natural image matting
Sebastian Lutz (Trinity College Dublin)*; Konstantinos Amplianitis (Trinity College Dublin); Aljosa Smolic (Trinity College Dublin)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
260. Actor-Action Semantic Segmentation with Region Masks
Kang Dang (Nanyang Technological University)*; CHUNLUAN ZHOU (Nanyang Technological University); Zhigang Tu (Wuhan University); Michael Hoy (Nanyang Technological University); Justin Dauwels (Nanyang Technological University); Junsong Yuan ("State University of New York at Buffalo, USA")

Mirror 1 [PDF]
Mirror 2 [PDF]
261. JointFlow: Temporal Flow Fields for Multi Person Pose Estimation
Andreas Doering (University of Bonn)*; Umar Iqbal (University of Bonn); Jurgen Gall (University of Bonn)

Mirror 1 [PDF] [SUPP] [Video-1] [Video-2]
Mirror 2 [PDF] [SUPP] [Video-1] [Video-2]
262. Learning Short-Cut Connections for Object Counting
Daniel Oñoro (NEC Lab Europe)*; Roberto Javier Lopez-Sastre (University of Alcala); Mathias Niepert (NEC Laboratories Europe)

Mirror 1 [PDF]
Mirror 2 [PDF]
263. Convolutional Simplex Projection Network for Weakly Supervised Semantic Segmentation
Rania Briq (The University of Bonn)*; Michael Moeller (University of Siegen); Jürgen Gall (University of Bonn)

Mirror 1 [PDF]
Mirror 2 [PDF]
264. Deep Domain Adaptation in Action Space
Arshad Jamal (IIT Kanpur)*; Vinay P Namboodiri (IIT Kanpur); Dipti Deodhare (CAIR, DRDO); K. S. Venkatesh (IIT Kanpur)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
265. A New Benchmark and Progress Toward Improved Weakly Supervised Learning
"Jason Ramapuram (University of Geneva); Russ Webb (Apple)*"

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
266. Recurrent Transformer Network for Remote Sensing Scene Categorisation
Zan Chen (Xi'an Jiaotong University); Shidong Wang (University of East Anglia); Xingsong Hou (Xi'an Jiaotong University)*; Ling Shao (Inception Institute of Artificial Intelligence)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
267. Deep Segmentation and Registration in X-Ray Angiography Video
Athanasios Vlontzos (Imperial College London)*; Krystian Mikolajczyk (Imperial College London)

Mirror 1 [PDF]
Mirror 2 [PDF]
268. Instance Segmentation of Fibers from Low Resolution CT Scans via 3D Deep Embedding Learning
Tomasz K Konopczynski (Heidelberg University)*; Thorben Kröger (Volume Graphics); Lei Zheng (Heidelberg University); Jürgen Hesser (Heidelberg University)

Mirror 1 [PDF]
Mirror 2 [PDF]
269. Human Motion Parsing by Hierarchical Dynamic Clustering
Yan Zhang (Institute of Neural Information Processing, Ulm University)*; Siyu Tang (MPI for Intelligent Systems); He Sun (School of Informatics, The University of Edinburgh); Heiko Neumann (Ulm University)

Mirror 1 [PDF]
Mirror 2 [PDF]
270. Part-based Graph Convolutional Network for Action Recognition
Kalpit C Thakkar (International Institute of Information Technology, Hyderabad)*; P. J. Narayanan (IIIT-Hyderabad)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
271. Multi-task Learning for Macromolecule Classification, Segmentation and Coarse Structural Recovery in Cryo-Tomography
Chang Liu (Carnegie Mellon University); Xiangrui Zeng (Carnegie Mellon University); Kaiwen Wang (Carnegie Mellon University); Qiang Guo (Max Planck Institute of Biochemistry); Min Xu (Carnegie Mellon University)*

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
272. Beef Cattle Instance Segmentation Using Fully Convolutional Neural Network
"Aram Ter-Sarkisov (Dublin Institute of Technology)*; John Kelleher (Dublin Institute of Technology); Bernadette Earley (TEAGASC); Michael Keane (TEAGASC); Robert Ross (Dublin Institute of Technology)"

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
273. Region-Object Relevance-Guided Visual Relationship Detection
Yusuke Goutsu (National Institute of Informatics)*

Mirror 1 [PDF]
Mirror 2 [PDF]
274. Learning Finer-class Networks for Universal Representations
Julien Girard (CEA); Youssef Tamaazousti (CEA LIST)*; Herve Le Borgne (CEA LIST); Céline Hudelot (CentraleSupélec)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
275. Mining for meaning: from vision to language through multiple networks consensus
Iulia Duta (Bitdefender)*; Andrei L Nicolicioiu (Bitdefender); Simion-Vlad Bogolin (Institute of Mathematics of the Romanian Academy); Marius Leordeanu (Institute of Mathematics of the Romanian Academy)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
276. Self-Paced Learning with Adaptive Deep Visual Embeddings
Vithursan Thangarasa (University of Guelph)*; Graham Taylor (University of Guelph)

Mirror 1 [PDF]
Mirror 2 [PDF]
277. Robust 6D Object Pose Estimation with Stochastic Congruent Sets
Chaitanya Mitash (Rutgers University)*; Abdeslam Boularias (Rutgers University); Kostas Bekris (Rutgers University)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
278. Neuro-IoU: Learning a Surrogate Loss for Semantic Segmentation
Nagendar G (IIIT Hyderabad)*; Digvijay Singh (IIIT Hyderabad); Vineeth N Balasubramanian (IIT Hyderabad); C.V. Jawahar (IIIT-Hyderabad)

Mirror 1 [PDF]
Mirror 2 [PDF]
279. Position-Squeeze and Excitation Block for Facial Attribute Analysis
Yan Zhang (East China Normal University); Wanxia Shen (East China Normal University); Li Sun (East China Normal University)*; Qingli Li (East China Normal University)

Mirror 1 [PDF]
Mirror 2 [PDF]
280. Semantic Iterative Closest Point through Expectation-Maximization
Steven Parkison (Univ. of Michigan)*; Lu Gan (Univ. of Michigan); Maani Ghaffari Jadidi (Univ. of Michigan); Dr.Ryan M Eustice (University of Michigan)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
281. SF-Net: Learning Scene Flow from RGB-D Images with CNNs
Yi-Ling Qiao (College students); Lin Gao (The Chinese academy of sciences institute of computing technology)*; Yukun Lai (Cardiff University); Fang-Lue Zhang (School of Engineering and Computer Science, Victoria University of Wellington); Ming-Ze Yuan (The Chinese academy of sciences institute of computing technology); Shi-Hong Xia (The Chinese academy of sciences institute of computing technology)

Mirror 1 [PDF]
Mirror 2 [PDF]
282. Functionally Modular and Interpretable Temporal Filtering for Robust Segmentation
Jörg Wagner (Robert Bosch GmbH)*; Volker Fischer (Robert Bosch GmbH); Michael Herman (Robert Bosch GmbH); Sven Prof. Behnke (University of Bonn)

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
283. Deep Facial Attribute Detection in the Wild: From General to Specific
Yuechuan Sun (University of Science and Technology of China); Jun Yu (University of Science and Technology of China)*

Mirror 1 [PDF]
Mirror 2 [PDF]
284. Accurate Eye Center Localization via Hierarchical Adaptive Convolution
Haibin Cai (University of portsmouth)*; Bangli Liu (University of portsmouth); Zhaojie Ju (University of Portsmouth); Serge Thill (University of Plymouth); Tony Belpaeme (Ghent University); Bram Vanderborght (VUB); Honghai Liu (University of Portsmouth)

Mirror 1 [PDF]
Mirror 2 [PDF]
285. Pyramid Attention Network for Semantic Segmentation
Hanchao Li (Beijing Institute of Technology)*; pengfei xiong (megvii); Jie An (Peking University); Lingxue Wang (Beijing Institute of Technology)

Mirror 1 [PDF]
Mirror 2 [PDF]
286. Deep Textured 3D Reconstruction of Human Bodies
Abbhinav Venkat (IIIT Hyderabad)*; Sai Sagar (IIIT Hyderabad); Avinash Sharma (CVIT, IIIT-Hyderabad)

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
287. Fast-BoW: Scaling Bag-of-Visual-Words Generation
Dinesh Singh (IIT Hyderabad)*; Abhijeet Bhure (IIT Hyderabad); Sumit Mamtani (IIT Hyderabad); C . Krishna Mohan (IIT Hyderabad)

Mirror 1 [PDF]
Mirror 2 [PDF]
288. Query-Conditioned Three-Player Adversarial Network for Video Summarization
Yujia Zhang (Institue of Automation, Chinese Academy of Sciences.)*; Michael C. Kampffmeyer (Universitet i Tromsø); Xiaodan Liang (Carnegie Mellon University); Min Tan (Institiute of Automation, Chinese academy of sciences); Eric Xing (CMU)

Mirror 1 [PDF]
Mirror 2 [PDF]
289. Structure-Aware 3D Hourglass Network for Hand Pose Estimation from Single Depth Image
Fuyang Huang (The Chinese University of Hong Kong)*; Ailing Zeng (The Chinese University of Hong Kong); Minhao Liu (The Chinese University of Hong Kong); Jing Qin (The Hong Kong Polytechnic University); Qiang Xu (The Chinese University of Hong Kong)

Mirror 1 [PDF]
Mirror 2 [PDF]
290. Chinese Handwriting Imitation with Hierarchical Generative Adversarial Network
Jie Chang (Shanghai Jiao Tong University)*; yujun gu (Shanghai Jiaotong University); Ya Zhang (Cooperative Medianet Innovation Center, Shang hai Jiao Tong University); Yan-Feng Wang (Shanghai Jiao Tong University)

Mirror 1 [PDF]
Mirror 2 [PDF]
291. Deep Learning intra-image and inter-images features for Co-saliency detection
min li (Shanxi Normal University); Shizhong Dong (Shenzhen Institutes of Advanced Technology); kun zhang (whu); Zhifan Gao (University of Western Ontario); Xi Wu (Chengdu University of Information Technology); heye zhang (Shenzhen Institutes of Advanced Technology)*; Guang Yang (Imperial College London); Shuo Li (University of Western Ontario)

Mirror 1 [PDF]
Mirror 2 [PDF]
292. Learning Generic Diffusion Processes for Image Restoration
Peng Qiao (NUDT)*; yong dou (National Laboratory for Parallel and Distributed Processing, National University of Defense Technology,Changsha,Hunan); Yunjin Chen (ULSee Inc.); Wensen Feng (College of Computer Science & Software Engineering, Shenzhen University)

Mirror 1 [PDF]
Mirror 2 [PDF]
16:15 - 16:45 Tea Break, Students Union
16:45 - 18:30 Orals 4, Students Union: Video, Motion and Actions
Chair: Yael Moses
293. S3D: Single Shot multi-Span Detector via Fully 3D Convolutional Networks
Da Zhang*, UC Santa Barbara; Xiyang Dai, UMD; Xin Wang, University of California, Santa Barbara; Yuan-Fang Wang, UC Santa Barbara

Mirror 1 [PDF]
Mirror 2 [PDF]
294. Budget-Aware Activity Detection with A Recurrent Policy Network
Behrooz Mahasseni, Apple; Xiaodong Yang*, NVIDIA; Pavlo Molchanov, NVIDIA; Kautz Jan, NVIDIA

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
295. From Coarse Attention to Fine-Grained Gaze: A Two-stage 3D Fully Convolutional Network for Predicting Eye Gaze in First Person Video
Zehua Zhang*, Indiana University; David Crandall, Indiana University; Chen Yu, Indiana University; Sven Bambach, Indiana University

Mirror 1 [PDF]
Mirror 2 [PDF]
296. LikeNet: A Siamese Motion Estimation Network Trained in an Unsupervised Way
Aria Ahmadi*, Queen Mary University of London; Marras Ioannis, Queen Mary University of London; Ioannis Patras, Queen Mary University of London

Mirror 1 [PDF]
Mirror 2 [PDF]
297. Learning Human Optical Flow
Anurag Ranjan*, MPI for Intelligent Systems; Javier Romero, MPI-IS; Michael Black, Brown University

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
298. Video Summarisation by Classification with Deep Reinforcement Learning
Kaiyang Zhou*, Queen Mary University of London, UK; Tao Xiang, Queen Mary, University of London, UK; ANDREA CAVALLARO, Queen Mary University of London, UK

Mirror 1 [PDF]
Mirror 2 [PDF]
299. QuaterNet: A Quaternion-based Recurrent Model for Human Motion
Dario Pavllo*, Facebook; David Grangier, Facebook; Michael Auli, Facebook

Mirror 1 [PDF] [Video]
Mirror 2 [PDF] [Video]
19:00 - 21:30 Banquet, Civic Centre
Thursday 6th September
7:30 - 7:45 Registration, Students Union
7:45 - 8:30 Coffee & Pastry, Students Union
8:30 - 10:00 Orals 5, Students Union: Low Level Vision and Computational Photography
Chair: Peter Hall
300. It's all Relative: Monocular 3D Human Pose Estimation from Weakly Supervised Data
Matteo Ronchi*, California Institute of Technology; Oisin Mac Aodha, Caltech; Robert Eng, Caltech; Pietro Perona, CALTECH, USA

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
301. 3D Hand Pose Estimation using Simulation and Partial-Supervision with a Shared Latent Space
Masoud Abdi*, Institute for Intelligent Systems Research and Innovation - Deakin University; Ehsan Abbasnejad, Adelaide; Chee Peng Lim, Deakin University; Saeid Nahavandi, Institute for Intelligent Systems Research and Innovation (IISRI)/Deakin University

Mirror 1 [PDF]
Mirror 2 [PDF]
302. Self-supervised learning of a facial attribute embedding from video
A Koepke*, University of Oxford; Olivia Wiles, University of Oxford; Andrew Zisserman, University of Oxford

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
303. Face Verification from Depth using Privileged Information
Guido Borghi*, University of Modena and Reggio Emilia; Stefano Pini, University of Modena and Reggio Emilia; Filippo Grazioli, University of Modena and Reggio Emilia; ROBERTO VEZZANI, University of Modena and Reggio Emilia, Italy; Rita Cucchiara, University of Modena and Reggio Emilia

Mirror 1 [PDF]
Mirror 2 [PDF]
304. Sign Language Production using Neural Machine Translation and Generative Adversarial Networks
Stephanie Stoll*, Centre for Vision, Speech and Signal Processing; Necati Cihan Camgoz, University of Surrey; Simon Hadfield, University of Surrey; Richard Bowden, University of Surrey

Mirror 1 [PDF]
Mirror 2 [PDF]
305. CU-Net: Coupled U-Nets
Zhiqiang Tang*, Rutgers; Xi Peng, Rutgers University; Shijie Geng, Rutgers; Yizhe Zhu, Rutgers; Dimitris Metaxas, Rutgers

Mirror 1 [PDF]
Mirror 2 [PDF]
10:00 - 10:45 Tea Break, Students Union
10:45 - 12:00 Orals 6, Students Union: Computer Vision Applications
Chair: Sotirios Tsaftaris
306 End-to-end Image Captioning Exploits Distributional Similarity in Multimodal Space
Pranava Madhyastha*, University of Sheffield; Josiah Wang, University of Sheffield; Lucia Specia, University of Sheffield

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
307 Boosting up Scene Text Detectors with Guided CNN
Xiaoyu Yue*, SenseTime; Zhanghui Kuang, Sensetime Ltd.; Zhaoyang Zhang, Sensetime Ltd.; Zhenfang Chen, The university of Hong Kong; Pan He, University of Florida; Yu Qiao, Multimedia Laboratory, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Wei Zhang, SenseTime Research

Mirror 1 [PDF]
Mirror 2 [PDF]
308 Y-Net: A deep Convolutional Neural Network for Polyp Detection
Ahmed Kedir Mohammed*, NTNU; Sule Yildirim-Yayilgan, NTNU; Marius Pedersen, NTNU, Gjovik, Norway; Ivar Farup, NTNU; Øistein Hovde, University of Oslo

Mirror 1 [PDF]
Mirror 2 [PDF]
309 Guitar Music Transcription from Silent Video
Shir Goldstein*, IDC; Yael Moses, IDC, Israel

Mirror 1 [PDF] [SUPP] [Video-1] [Video-2]
Mirror 2 [PDF] [SUPP] [Video-1] [Video-2]
310 Image Retrieval with Mixed Initiative and Multimodal Feedback
Nils Murrugarra-Llerena*, University of Pittsburgh; Adriana Kovashka, University of Pittsburgh

Mirror 1 [PDF] [SUPP]
Mirror 2 [PDF] [SUPP]
12:00 - 13:00 Simple Lunch Bag, Students Union
13:00 - 14:00 Keynote 3, Students Union
Learning Along the Edge of Deep Networks.
Rama Chellappa (University of Maryland)
Chair: TK Kim
14:00 - 15:45 Workshop Part 1, Students Union
15:45 - 16:15 Tea Break, Students Union
16:15 - 18:00 Workshop Part 2, Students Union
Workshops: Thursday 6th September
IAHFAR 2018: Image Analysis for Human Facial and Activity Recognition
Orals:
311. Graph-based Correlated Topic Model for Motion Patterns Analysis in Crowded Scenes from Tracklets
Manal AlGhamdi*, Umm AlQura University; Yoshihiko Gotoh, University of Sheffield, United Kingdom

Mirror 1 [PDF]
Mirror 2 [PDF]
312. Online Action Recognition based on Skeleton Motion Distribution
Bangli Liu, University of portsmouth; Zhaojie Ju, University of Portsmouth; Naoyuki Kubota, Tokyo Metropolitan University; Honghai Liu*, University of Portsmouth

Mirror 1 [PDF]
Mirror 2 [PDF]
313. Git Loss for Deep Face Recognition
Ignazio Gallo*, University of Insubria, Department of Theoretical and Applied Sciences (DiSTA); Shah Nawaz, University of Insubria; Alessandro Calefati, University of Insubria, Department of Theoretical and Applied Sciences (DiSTA); Muhammad Kamran Janjua, National University of Sciences and Technology

Mirror 1 [PDF]
Mirror 2 [PDF]
314. Bi-stream Region Ensemble Network: Promoting Accuracy in Fingertip Localization from Stereo Images
Cairong Zhang, Tsinghua University; Guijin Wang*, Tsinghua University; Xinghao Chen, Tsinghua University; huazhong yang, tsinghua university

Mirror 1 [PDF]
Mirror 2 [PDF]
315. Practical Action Recognition with Manifold Regularized Sparse Representations
Lining Zhang*, University of Portsmouth; Rinat Khusainov, Portsmouth University; John chiverton, University of Portsmouth

Mirror 1 [PDF]
Mirror 2 [PDF]
316. CAKE: a Compact and Accurate K-dimensional representation of Emotion
Corentin Kervadec, Orange Labs; Valentin Vielzeuf*, Orange Labs / University of Caen; Stephane Pateux, Orange Labs; Alexis Lechervy, University of Caen; Frederic Jurie, University of Caen

Mirror 1 [PDF]
Mirror 2 [PDF]
Posters:
317. Feature Selection Mechanism in CNNs for Facial Expression Recognition
Shuwen Zhao, Zhejiang University of Technology; Haibin Cai, University of portsmouth; Honghai Liu, University of Portsmouth; Jianhua Zhang*, Zhejiang University of Technology; Shengyong Chen, Tianjin University of Technology

Mirror 1 [PDF]
Mirror 2 [PDF]
318. A Deep Variational Autoencoder Approach for Robust Facial Symmetrization
Ting Wang, Shandong University of Science and Technology; Shu Zhang*, Ocean University of China; Junyu Dong, Ocean University of China; Yongquan Liang, Shandong University of Science and Technology

Mirror 1 [PDF]
Mirror 2 [PDF]
319. Palmprint Recognition System with Double-assistant-point on iOS Mobile Devices
Lu Leng*, Nanchang Hangkong University

Mirror 1 [PDF]
Mirror 2 [PDF]
320. Person Part Segmentation based on Weak Supervision
Yalong Jiang*, The Hong Kong Polytechnic University; Zheru Chi, The Hong Kong Polytechnic University

Mirror 1 [PDF]
Mirror 2 [PDF]
321. Saliency-Informed Spatio-Temporal Vector of Locally Aggregated Descriptors and Fisher Vectors for Visual Action Recognition
Zheming Zuo, Northumbria University; Daniel Organisciak, Northumbria University; Hubert P. H. Shum, Northumbria University; Longzhi Yang*, Northumbria

Mirror 1 [PDF]
Mirror 2 [PDF]
CVPPP 2018: Computer Vision Problems in Plant Phenotyping
CVPPP 2018 Editorial [PDF]
Orals:
322. A New 4D-RGB Mapping Technique for Field-Based High-Throughput Phenotyping
Ali Shafiekhani (University of Missouri-Columbia)*; Felix B. Fritschi (University of Missouri-Columbia); Guilherme DeSouza (University of Missouri)

Mirror 1 [PDF]
Mirror 2 [PDF]
323. Low-cost vision machine for high-throughput automated monitoring of heterotrophic seedling growth on wet paper support
Pejman Rasti (University of Angers)*; Didier Demilly (Station Nationale d’Essais de Semences (SNES - GEVES)); Landry Benoit (University of Angers); Etienne Belin (University of Angers); Sylvie DUCOURNAU (Station Nationale d’Essais de Semences (SNES - GEVES)); Francois CHAPEAU-BLONDEAU (University of Angers); David ROUSSEAU (Université d'Angers)

Mirror 1 [PDF]
Mirror 2 [PDF]
324. Data Augmentation using Conditional Generative Adversarial Networks for Leaf Counting in Arabidopsis Plants
Yezi Zhu (Eindhoven University of Technology)*; Marc Aoun (Signify); Marcel Krijn (Signify); Joaquin Vanschoren (Eindhoven University of Technology)

Mirror 1 [PDF]
Mirror 2 [PDF]
325. Root Gap Correction with a Deep Inpainting Model
Hao Chen (The University of Edinburgh)*; Mario Valerio Giuffrida (University of Edinburgh); Sotirios Tsaftaris (The University of Edinburgh); Peter Doerner (University of Edinburgh)

Mirror 1 [PDF]
Mirror 2 [PDF]
326. Towards Low-Cost Image-based Plant Phenotyping using Reduced-Parameter CNN
John Atanbori (University of Nottingham)*; Feng Chen (University of Nottingham); Andrew P French (University of Nottingham); Tony Pridmore (University of Nottingham)

Mirror 1 [PDF]
Mirror 2 [PDF]
327. Deep Leaf Segmentation Using Synthetic Data
Daniel C Ward (CSIRO); Peyman Moghadam (CSIRO)*; Nicolas Hudson (CSIRO)

Mirror 1 [PDF]
Mirror 2 [PDF]
328. Leaf counting: Multiple scale regression and detection using deep CNNs
Yotam Itzhaky (Ben Gurion University of the Negev); guy farjon (Ben Gurion University)*; Faina Khoroshevsky (Ben-Gurion University of the Negev); Alon Shpigler (Ben Gurion University); Aharon Bar-Hillel ()

Mirror 1 [PDF]
Mirror 2 [PDF]
Posters:
329. Instance segmentation for assessment of plant growth dynamics in artificial soilless conditions
Dmitrii G Shadrin (Skolkovo institute of Science and Technology)*; Victor Kulikov (Skoltech); Maxim Fedorov (Skolkovo Institute of Science and Technology)

Mirror 1 [PDF]
Mirror 2 [PDF]
330. What’s That Plant? WTPlant is a Deep Learning System to Identify Plants in Natural Images
Jonas Krause (University of Hawaii at Manoa)*; Gavin Sugita (University of Hawaii at Manoa); Kyungim Baek (University of Hawaii at Manoa); Lipyeow Lim (University of Hawaii at Manoa)

Mirror 1 [PDF]
Mirror 2 [PDF]
331. Soybean Leaf Coverage Estimation for Field-Phenotyping
Kevin Keller (ETHZ); Raghav Khanna (ETH Zurich); Norbert Kirchgessner (ETH Zurich); Roland Siegwrat (ETH Zürich Autonomous Systems Lab); Achim Walter (ETZ Zurich); Helge Aasen (ETH Zurich)*

Mirror 1 [PDF]
Mirror 2 [PDF]
VIBE 2018: Vision for Interaction and Behaviour undErstanding
332. AHA-3D: A Labelled Dataset for Senior Fitness Exercise Recognition and Segmentation from 3D Skeletal Data
João Antunes (Carnegie Mellon University); Alexandre Bernardino (Instituto Superior Técnico Lisboa); Asim Smailagic (Carnegie Mellon University); Daniel Siewiorek (Carnegie Mellon University)
[PDF]
333. Unsupervised Speaker Cue Usage Detection in Public Speaking Videos
Anshul Gupta (Multimodal Perception Lab); Dinesh Babu Jayagopi (Multimodal Perception Lab);
[PDF]
334. Tactile Logging for Understanding Plausible Tool Use Based on Human Demonstration
Shuichi Akizuki ( Keio University); Yoshimitsu Aoki (Keio University);
[PDF]
335. Online Multiple View Tracking: Targets Association Across Cameras
Quoc Cuong LE (LIFAT, University of Tours); Donatello Conte ( LIFAT, University of Tours); Moncef Hidane (Computer Science Department INSA Centre Val de Loire);
[PDF]
Copyright ©2017-2018. All Rights Reserved. Contents provided by BMVC2018
^ Back to Top