-1-1012345678910
Monday 7th September : Oral Session 1: Looking at People
0
[905]
Is Face Recognition Sexist? No, Gendered Hairstyles and Biology Are
Vítor Albiero and Kevin Bowyer
Paper  Oral Session 1  Poster Session 1
1
[66]
SIA-GCN: A Spatial Information Aware Graph Neural Network with 2D Convolutions for Hand Pose Estimation
Deying Kong, Haoyu Ma and Xiaohui Xie
Paper  Oral Session 1  Poster Session 1
2
[242]
Explicit Knowledge Distillation for 3D Hand Pose Estimation from Monocular RGB
Yumeng Zhang, Li Chen, Yufeng Liu, Wen Zheng and JunHai Yong
Paper  Supplemental  Oral Session 1  Poster Session 1
3
[266]
Text Attribute Aggregation and Visual Feature Decomposition for Person Search
Sara Iodice and Krystian Mikolajczyk
Paper  Code  Oral Session 1  Poster Session 1
Monday 7th September : Oral Session 2: Cross Modality and Weak Supervision
4
[102]
Cross-Modal Hierarchical Modelling for Fine-Grained Sketch Based Image Retrieval
Aneeshan Sain, Ayan Kumar Bhunia, Yongxin Yang, Tao Xiang and Yi-Zhe Song
Paper  Oral Session 2  Poster Session 1
5
[423]
WAMDA: Weighted Alignment of Sources for Multi-source Domain Adaptation
Surbhi Aggarwal, Jogendra Nath Kundu, Venkatesh Babu Radhakrishnan and Anirban Chakraborty
Paper  Supplemental  Oral Session 2  Poster Session 1
6
[566]
Advancing weakly supervised cross-domain alignment with optimal transport
Siyang Yuan, Ke Bai, Liqun Chen, Yizhe Zhang, Chenyang Tao, Chunyuan Li, Guoyin Wang, Ricardo Henao and Lawrence Carin Duke
Paper  Supplemental  Oral Session 2  Poster Session 1
7
[430]
Weakly-supervised Salient Instance Detection
Xin Tian, Ke Xu, Xin Yang, Baocai Yin and Rynson Lau
Paper  Supplemental  Oral Session 2  Poster Session 1
Monday 7th September : Poster Session 1
8
[324]
Semantic Estimation of 3D Body Shape and Pose using Minimal Cameras
Andrew Gilbert, Matthew Trumble, Adrian Hilton and John Collomosse
Paper  Poster Session 1
9
[330]
Weakly Supervised Generative Network for Multiple 3D Human Pose Hypotheses
Chen Li and Gim Hee Lee
Paper  Code  Poster Session 1
10
[436]
Determinantal Point Process as an alternative to NMS
Samik Some, Mithun Gupta and Vinay Namboodiri
Paper  Code  Poster Session 1
11
[16]
CornerNet-Lite: Efficient Keypoint based Object Detection
Hei Law, Yun Teng, Olga Russakovsky and Jia Deng
Paper  Code  Poster Session 1
12
[126]
High-speed Light-weight CNN Inference via Strided Convolutions on a Pixel Processor Array
Yanan Liu, Laurie Bose, Jianing Chen, Stephen Carey, Piotr Dudek and Walterio Mayol-Cuevas
Paper  Code  Poster Session 1
13
[815]
Text and Style Conditioned GAN for the Generation of Offline-Handwriting Lines
Brian Davis, Bryan Morse, Brian Price, Chris Tensmeyer, Curtis Wigington and Rajiv Jain
Paper  Supplemental  Poster Session 1
14
[367]
Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization
Yu-Ting Chang, Qiaosong Wang, Wei-Chih Hung, Robinson Piramuthu, Yi-Hsuan Tsai and Ming-Hsuan Yang
Paper  Supplemental  Poster Session 1
15
[193]
FairFaceGAN: Fairness-aware Facial Image-to-Image Translation
Sunhee Hwang, Sungho Park, Dohyung Kim, Mirae Do and Hyeran Byun
Paper  Supplemental  Poster Session 1
16
[243]
Annealing Genetic GAN for Minority Oversampling
Jingyu Hao, Chengjia Wang, Heye Zhang and Guang Yang
Paper  Code  Poster Session 1
17
[754]
Accurate Parts Visualization for Explaining CNN Reasoning via Semantic Segmentation
Ren Harada, Antonio Tejero-de-Pablos and Tatsuya Harada
Paper  Poster Session 1
18
[906]
Intrinsic Decomposition of Document Images In-the-Wild
Sagnik Das, Hassan Sial, Ke Ma, Ramón Baldrich, Maria Vanrell and Dimitris Samaras
Paper  Code  Poster Session 1
19
[264]
Object Detection as a Positive-Unlabeled Problem
Yuewei Yang, Kevin Liang and Lawrence Carin Duke
Paper  Supplemental  Poster Session 1
20
[570]
First-Person View Hand Segmentation of Multi-Modal Hand Activity Video Dataset
Sangpil Kim, Hyung-gun Chi, Xiao Hu, Anirudh Vegesana and Karthik Ramani
Paper  Supplemental  Poster Session 1
21
[445]
Physics-informed detection and segmentation of type II solar radio bursts
Joseph Jenkins, Adeline Paiement, Jean Aboudarham and Xavier Bonnin
Paper  Supplemental  Poster Session 1
22
[481]
Learning 3D Global Human Motion Estimation from Unpaired, Disjoint Datasets
Julian Habekost, Takaaki Shiratori, Yuting Ye and Taku Komura
Paper  Supplemental  Poster Session 1
23
[186]
Adaptation Across Extreme Variations using Unlabeled Bridges
Shuyang Dai, Kihyuk Sohn, Yi-Hsuan Tsai, Lawrence Carin Duke and Manmohan Chandraker
Paper  Supplemental  Poster Session 1
24
[662]
Lifted Regression/Reconstruction Networks
Rasmus Høier and Christopher Zach
Paper  Supplemental  Poster Session 1
25
[789]
LiPo-LCD: Combining Lines and Points for Appearance-based Loop Closure Detection
Joan Pep Company-Corcoles, Emilio Garcia-Fidalgo and Alberto Ortiz
Paper  Poster Session 1
26
[383]
Stratified Autocalibration of Cameras with Euclidean Image Plane
Devesh Adlakha, Adlane Habed, Fabio Morbidi, Cedric Demonceaux and Michel de Mathelin
Paper  Supplemental  Poster Session 1
27
[261]
Bias-Awareness for Zero-Shot Learning the Seen and Unseen
William Thong and Cees Snoek
Paper  Code  Poster Session 1
28
[129]
ASAP-Net: Attention and Structure Aware Point Cloud Sequence Segmentation
Hanwen Cao, Yongyi Lu, Bo Pang, Cewu Lu, Alan Yuille and Gongshen Liu
Paper  Code  Poster Session 1
29
[166]
Unsupervised Domain Adaptation for Spatio-Temporal Action Localization
Nakul Agarwal, Yi-Ting Chen, Behzad Dariush and Ming-Hsuan Yang
Paper  Supplemental  Poster Session 1
30
[680]
Semi-supervised semantic segmentation needs strong, varied perturbations
Geoffrey French, Samuli Laine, Timo Aila, Michal Mackiewicz and Graham Finlayson
Paper  Supplemental  Code  Poster Session 1
31
[528]
Inpainting Networks Learn to Separate Cells in Microscopy Images
Steffen Wolf, Fred Hamprecht and Jan Funke
Paper  Supplemental  Poster Session 1
32
[99]
Adversarial Color Enhancement: Generating Unrestricted Adversarial Images by Optimizing a Color Filter
Zhengyu Zhao, Zhuoran Liu and Martha Larson
Paper  Code  Poster Session 1
33
[82]
Cross-dataset Color Constancy Revisited Using Sensor-to-Sensor Transfer
Samu Koskinen, Dan Yang and Joni-Kristian Kamarainen
Paper  Poster Session 1
34
[448]
SD-MTCNN: Self-Distilled Multi-Task CNN
Ankit Jha, Awanish Kumar, Biplab Banerjee and Vinay Namboodiri
Paper  Supplemental  Poster Session 1
35
[176]
The Resistance to Label Noise in K-NN and DNN Depends on its Concentration
Amnon Drory, Oria Ratzon, Shai Avidan and Raja Giryes
Paper  Supplemental  Code  Poster Session 1
36
[279]
Anti-Litter Surveillance based on Person Understanding via Multi-Task Learning
Kangmin Bae, Kimin Yun, Hyung-Il Kim, Youngwan Lee and Jongyoul Park
Paper  Poster Session 1
37
[877]
Two-Stream Spatiotemporal Compositional Attention Network for VideoQA
Taiki Miyanishi, Takuya Maekawa and Motoaki Kawanabe
Paper  Poster Session 1
38
[907]
WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose
Yijun Zhou and James Gregson
Paper  Supplemental  Code  Poster Session 1
39
[53]
A Spherical Approach to Planar Semantic Segmentation
Chao Zhang, Sen He and Stephan Liwicki
Paper  Supplemental  Poster Session 1
40
[161]
Visualizing point cloud classifiers by curvature smoothing
Chen Ziwen, Wenxuan Wu, Zhongang Qi and Li Fuxin
Paper  Supplemental  Code  Poster Session 1
41
[743]
Initial Classifier Weights Replay for Memoryless Class Incremental Learning
Eden Belouadah, Adrian Popescu and Ioannis Kanellos
Paper  Supplemental  Code  Poster Session 1
42
[43]
Seeing wake words: Audio-visual Keyword Spotting
Liliane Momeni, Triantafyllos Afouras, Themos Stafylakis, Samuel Albanie and Andrew Zisserman
Paper  Code  Poster Session 1
43
[221]
Unsupervised Domain Adaptation by Uncertain Feature Alignment
Tobias Ringwald and Rainer Stiefelhagen
Paper  Supplemental  Code  Poster Session 1
44
[901]
Bayesian Geodesic Regression on Riemannian Manifolds
Youshan Zhang
Paper  Poster Session 1
45
[550]
High-order Graph Convolutional Networks for 3D Human Pose Estimation
Zhiming Zou, Kenkun Liu, Le Wang and Wei Tang
Paper  Poster Session 1
46
[174]
Boosting Image and Video Compression via Learning Latent Residual Patterns
Yen-Chung Chen, Keng-Jui Chang, Yi-Hsuan Tsai and Wei-Chen Chiu
Paper  Poster Session 1
47
[356]
Conditional Attention for Content-based Image Retrieval
Zechao Hu and Adrian Bors
Paper  Poster Session 1
48
[113]
STQ-Nets: Unifying Network Binarization and Structured Pruning
Aurobindo Munagala, Ameya Prabhu and Anoop Namboodiri
Paper  Poster Session 1
49
[561]
Attribute Adaptive Margin Softmax Loss using Privileged Information
Seyed mehdi Iranmanesh, Ali Dabouei and Nasser Nasrabadi
Paper  Poster Session 1
50
[187]
Attentive Action and Context Factorization
Yang Wang, Vinh Tran, Gedas Bertasius, Lorenzo Torresani and Minh Hoai Nguyen
Paper  Poster Session 1
Tuesday 8th September : Oral Session 3: Segmentation
51
[694]
Fast Convex Relaxations using Graph Discretizations
Jonas Geiping, Fjedor Gaede, Hartmut Bauermeister and Michael Moeller
Paper  Oral Session 3  Poster Session 2
52
[614]
Feature Binding with Category-Dependant MixUp for Semantic Segmentation and Adversarial Robustness
Md Amirul Islam, Matthew Kowal, Konstantinos Derpanis and Neil D. B. Bruce
Paper  Oral Session 3  Poster Session 2
53
[184]
Bipartite Conditional Random Fields for Panoptic Segmentation
Sadeep Jayasumana, Kanchana Ranasinghe, Sahan Liyanaarachchi, Bethmage Mayuka Jayawardhana, Harsha Ranasinghe and Sina Samangooei
Paper  Supplemental  Code  Oral Session 3  Poster Session 2
54
[547]
Delving Deeper into Anti-aliasing in ConvNets
Xueyan Zou, Fanyi Xiao, Zhiding Yu and Yong Jae Lee
Paper  Code  Oral Session 3  Poster Session 2
Tuesday 8th September : Oral Session 4: Shape-from-X / 3D Reconstruction
55
[277]
A CNN Based Approach for the Near-Field Photometric Stereo Problem
Fotios Logothetis, Ignas Budvytis, Roberto Mecca and Roberto Cipolla
Paper  Oral Session 4  Poster Session 2
56
[122]
DESC: Domain Adaptation for Depth Estimation via Semantic Consistency
Adrian Lopez-Rodriguez and Krystian Mikolajczyk
Paper  Code  Oral Session 4  Poster Session 2
57
[421]
Visibility-aware Multi-view Stereo Network
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo and Tian Fang
Paper  Supplemental  Code  Oral Session 4  Poster Session 2
58
[473]
Pano2Scene: 3D Indoor Semantic Scene Reconstruction from a Single Indoor Panorama Image
Wei Zeng, Sezer Karaoglu and Theo Gevers
Paper  Oral Session 4  Poster Session 2
59
[28]
Neighbourhood-Insensitive Point Cloud Normal Estimation Network
Zirui Wang and Victor Prisacariu
Paper  Supplemental  Code  Oral Session 4  Poster Session 2
Tuesday 8th September : Poster Session 2
60
[453]
Domain Adaptation Regularization for Spectral Pruning
Laurent Dillard, Yosuke Shinya and Taiji Suzuki
Paper  Supplemental  Poster Session 2
61
[328]
Deep Metric Learning Meets Deep Clustering: An Novel Unsupervised Approach for Feature Embedding
Binh Nguyen, Binh Nguyen, Gustavo Carneiro, Erman Tjiputra, Quang Tran and Thanh-Toan Do
Paper  Code  Poster Session 2
62
[443]
A Simple and Scalable Shape Representation for 3D Reconstruction.
Mateusz Michalkiewicz, Eugene Belilovsky, Mahsa Baktashmotlagh and Anders Eriksson
Paper  Supplemental  Poster Session 2
63
[282]
Non-Probabilistic Cosine Similarity Loss for Few-Shot Image Classification
Joonhyuk Kim, Inug Yoon, Gyeong-Moon Park and Jong-Hwan Kim
Paper  Supplemental  Poster Session 2
64
[59]
Improved Trainable Calibration Method for Neural Networks
Gongbo Liang, Yu Zhang, Xiaoqing Wang and Nathan Jacobs
Paper  Supplemental  Poster Session 2
65
[864]
Towards a Hypothesis on Visual Transformation based Self-Supervision
Dipan Pal, Sreena Nallamothu and Marios Savvides
Paper  Supplemental  Poster Session 2
66
[274]
Pose Proposal Critic: Robust Pose Refinement by Learning Reprojection Errors
Lucas Brynte and Fredrik Kahl
Paper  Supplemental  Poster Session 2
67
[673]
Zero-Shot Domain Generalization
Udit Maniyar, Joseph K J, Aniket Anand Deshmukh, Urun Dogan and Vineeth N Balasubramanian
Paper  Supplemental  Code  Poster Session 2
68
[359]
Automated Search for Resource-Efficient Branched Multi-Task Networks
David Brüggemann, Menelaos Kanakis, Stamatios Georgoulis and Luc Van Gool
Paper  Supplemental  Code  Poster Session 2
69
[42]
Meta-RetinaNet for Few-shot Object Detection
Shaoqi Li, Wenfeng Song, Shuai Li, Aimin Hao and Hong Qin
Paper  Poster Session 2
70
[479]
Making L-BFGS Work with Industrial-Strength Nets
Abhay Yadav, Tom Goldstein and David Jacobs
Paper  Supplemental  Poster Session 2
71
[581]
Rethinking Curriculum Learning with Incremental Labels and Adaptive Compensation
Madan Ravi Ganesh and Jason Corso
Paper  Supplemental  Poster Session 2
72
[783]
Not all points are created equal - an anisotropic cost function for facial landmark location
Farshid Rayhan, Aphrodite Galata and Timothy Cootes
Paper  Supplemental  Code  Poster Session 2
73
[220]
Relational Generalized Few-Shot Learning
Xiahan Shi, Leonard Salewski, Martin Schiegg and Max Welling
Paper  Supplemental  Poster Session 2
74
[306]
Uncovering Hidden Challenges in Query-Based Video Moment Retrieval
Mayu Otani, Yuta Nakashima, Esa Rahtu and Janne Heikkila
Paper  Supplemental  Code  Poster Session 2
75
[9]
ViewSynth: Learning Local Features from Depth using View Synthesis
Jisan Mahmud, Rajat Vikram Singh, Peri Akiva, Spondon Kundu, Kuan-Chuan Peng and Jan-Michael Frahm
Paper  Supplemental  Poster Session 2
76
[316]
Domain Adaptation of Learned Featuresfor Visual Localization
Sungyong Baik, Hyo Jin Kim, Tianwei Shen, Eddy Ilg, Kyoung Mu Lee and Christopher Sweeney
Paper  Supplemental  Poster Session 2
77
[234]
Mid-level Fusion for End-to-End Temporal Activity Detection in Untrimmed Video
Md Atiqur Rahman and Robert Laganiere
Paper  Poster Session 2
78
[634]
Neural Network Quantization with Scale-Adjusted Training
Qing Jin, Linjie Yang, Zhenyu Liao and Xiaoning Qian
Paper  Supplemental  Poster Session 2
79
[213]
Branched Multi-Task Networks: Deciding what layers to share
Simon Vandenhende, Stamatios Georgoulis, Luc Van Gool and Bert De Brabandere
Paper  Supplemental  Poster Session 2
80
[534]
Anchor-free Small-scale Multispectral Pedestrian Detection
Alexander Wolpert, Michael Teutsch, Saquib Sarfraz and Rainer Stiefelhagen
Paper  Supplemental  Code  Poster Session 2
81
[413]
PMD-Net: Privileged Modality Distillation Network for 3D Hand Pose Estimation from a Single RGB Image
Kewen Wang and Xilin Chen
Paper  Poster Session 2
82
[979]
Learning to Abstract and Predict Human Actions
Romero Morais, Vuong Le, Truyen Tran and Svetha Venkatesh
Paper  Supplemental  Code  Poster Session 2
83
[275]
Superpixel Masking and Inpainting for Self-Supervised Anomaly Detection
Zhenyu Li, Ning Li, Kaitao Jiang, Zhiheng Ma, Xing Wei, Xiaopeng Hong and Yihong Gong
Paper  Poster Session 2
84
[772]
From Saturation to Zero-Shot Visual Relationship Detection Using Local Context
Nikolaos Gkanatsios, Vassilis Pitsikalis and Petros Maragos
Paper  Code  Poster Session 2
85
[440]
Align-and-Attend Network for Globally and Locally Coherent Video Inpainting
Sanghyun Woo, Dahun Kim, KwanYong Park, Joon-Young Lee and In So Kweon
Paper  Supplemental  Poster Session 2
86
[890]
E2ETag: An End-to-End Trainable Method for Generating and Detecting Fiducial Markers
John Peace, Eric Psota, Yanfeng Liu and Lance Pérez
Paper  Supplemental  Supplemental  Code  Poster Session 2
87
[369]
Semantically Adaptive Image-to-image Translation for Domain Adaptation of Semantic Segmentation
Luigi Musto and Andrea Zinelli
Paper  Supplemental  Poster Session 2
88
[149]
Inducing Predictive Uncertainty Estimation for Face Verification
Weidi Xie, Jeffrey Byrne (STR, Visym Labs) and Andrew Zisserman
Paper  Poster Session 2
89
[796]
Synchronous Bidirectional Learning for Multilingual Lip Reading
Mingshuang Luo, Shuang Yang, Xilin Chen, Zitao Liu and Shiguang Shan
Paper  Poster Session 2
90
[928]
Mish: A Self Regularized Non-Monotonic Activation Function
Diganta Misra
Paper  Code  Poster Session 2
91
[702]
Two-in-One Refinement for Interactive Segmentation
Soumajit Majumder, Abhinav Rai, Ansh Khurana and Angela Yao
Paper  Poster Session 2
92
[816]
LaDDer: Latent Data Distribution Modelling with a Generative Prior
Shuyu Lin and Ronald Clark
Paper  Supplemental  Code  Poster Session 2
93
[817]
Paying more Attention to Snapshots of Iterative Pruning: Improving Model Compression via Ensemble Distillation
Duong Le, Nhan Vo and Nam Thoai
Paper  Supplemental  Code  Poster Session 2
94
[209]
When Humans Meet Machines: Towards Efficient Segmentation Networks
Peike Li, Xuanyi Dong, Xin Yu and Yi Yang
Paper  Supplemental  Poster Session 2
95
[145]
Towards Fast and Light-Weight Restoration of Dark Images
Mohit Lamba, Atul Balaji and Kaushik Mitra
Paper  Supplemental  Code  Poster Session 2
96
[656]
Contrastively-reinforced Attention Convolutional Neural Network for Fine-grained Image Recognition
Dichao Liu, Yu Wang, Jien Kato and Kenji Mase
Paper  Supplemental  Poster Session 2
97
[31]
Semi-supervised Active Learning for Instance Segmentation via Scoring Predictions
Jun Wang, Shaoguo Wen, Jianghua Yu, Kaixing Chen, Xin Zhou, Peng Gao, Guotong Xie and Changsheng Li
Paper  Supplemental  Poster Session 2
98
[863]
Learning Non-Parametric Invariances from Data with Permanent Random Connectomes
Dipan Pal, Akshay Chawla and Marios Savvides
Paper  Supplemental  Poster Session 2
Wednesday 9th September : Oral Session 5: Computational Photography
99
[96]
EPI-based Oriented Relation Networks for Light Field Depth Estimation
Kunyuan Li, Jun Zhang, Rui Sun, Xudong Zhang and Jun Gao
Paper  Code  Oral Session 5  Poster Session 3
100
[160]
Deep Sparse Light Field Refocusing
Shachar Ben Dayan, David Mendlovic and Raja Giryes
Paper  Supplemental  Oral Session 5  Poster Session 3
101
[366]
High-speed event-based camera tracking
William Chamorro, Juan Andrade-Cetto and Joan Solà
Paper  Supplemental  Oral Session 5  Poster Session 3
102
[101]
Key-Nets: Optical Transformation Convolutional Networks for Privacy Preserving Vision Sensors
Jeffrey Byrne (STR, Visym Labs), Brian DeCann and Scott Bloom
Paper  Supplemental  Code  Oral Session 5  Poster Session 3
Wednesday 9th September : Oral Session 6: Zero/Few Shot Learning
103
[139]
BriNet: Towards Bridging the Intra-class and Inter-class Gaps in One-Shot Segmentation
Xianghui Yang, Bairun Wang, Xinchi Zhou, Kaige Chen, Shuai Yi, Wanli Ouyang and Luping Zhou
Paper  Code  Oral Session 6  Poster Session 3
104
[249]
Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge
He Huang, Wei Tang, Philip Yu, Yuanwei Chen, Wenhao Zheng and Qing-Guo Chen
Paper  Oral Session 6  Poster Session 3
105
[353]
Few-Shot Learning with Complex-valued Neural Networks
Zhen Liu, Baochang Zhang and Guodong Guo
Paper  Code  Oral Session 6  Poster Session 3
106
[688]
Marginalized Graph Attention Hashing for Zero-Shot Image Retrieval
Meixue Huang, Dayan Wu, Wanqian Zhang, Zhi Xiong, Bo Li and Weiping Wang
Paper  Oral Session 6  Poster Session 3
Wednesday 9th September : Poster Session 3
107
[51]
Novel View Synthesis from Single Images via Point Cloud Transformation
Hoang-An Le, Thomas Mensink, Partha Das and Theo Gevers
Paper  Code  Poster Session 3
108
[384]
Attribute-Guided Image Generation from Layout
Ke Ma, Bo Zhao and Leonid Sigal
Paper  Supplemental  Poster Session 3
109
[44]
An ETF view of Dropout regularization
Dor Bank and Raja Giryes
Paper  Supplemental  Code  Poster Session 3
110
[549]
Tripping through time: Efficient Localization of Activities in Videos
Meera Hahn, Asim Kadav, James Rehg and Hans Peter Graf
Paper  Supplemental  Poster Session 3
111
[226]
ALBA: Reinforcement Learning for Video Object Segmentation
Shreyank Gowda, Panagiotis Eustratiadis, Timothy Hospedales and Laura Sevilla-Lara
Paper  Poster Session 3
112
[151]
Explicit Residual Descent for 3D Human Pose Estimation from 2D Joint Locations
Yangyuxuan Kang, Anbang Yao, Shandong Wang, Ming Lu, Yurong Chen and Enhua Wu
Paper  Code  Poster Session 3
113
[223]
Adversarial Training for Multi-Channel Sign Language Production
Ben Saunders, Richard Bowden and Necati Cihan Camgoz
Paper  Supplemental  Poster Session 3
114
[10]
Importance of Self-Consistency in Active Learning for Semantic Segmentation
S. Alireza Golestaneh and Kris Kitani
Paper  Poster Session 3
115
[493]
AOL: Adaptive Online Learning for Human Trajectory Prediction in Dynamic Video Scenes
Manh Huynh and Gita Alaghband
Paper  Poster Session 3
116
[781]
MagnifierNet: Towards Semantic Adversary and Fusion for Person Re-identification
Yushi Lan, Yuan Liu, Xinchi Zhou, Tian Maoqing, Xuesen Zhang, Shuai Yi and Hongsheng Li
Paper  Code  Poster Session 3
117
[526]
RODEO: Replay for Online Object Detection
Manoj Acharya, Tyler Hayes and Christopher Kanan
Paper  Supplemental  Poster Session 3
118
[196]
What do CNNs gain by imitating the visual development of primate infants?
Shantanu Jaiswal, Dongkyu Choi and Basura Fernando
Paper  Supplemental  Poster Session 3
119
[222]
SOFA-Net: Second-Order and First-order Attention Network for Crowd Counting
Haoran Duan, Shidong Wang and Yu Guan
Paper  Poster Session 3
120
[238]
CoMoGCN: Coherent Motion Aware Trajectory Prediction with Graph Representation
Yuying Chen, Congcong LIU, Bertram Shi and Ming Liu
Paper  Supplemental  Poster Session 3
121
[451]
Class Interference Regularization
Bharti Munjal, Sikandar Amin and Fabio Galasso
Paper  Poster Session 3
122
[541]
Tackling the Unannotated: Scene Graph Generation with Bias-Reduced Models
Tzujui Wang, Selen Pehlivan and Jorma Laaksonen
Paper  Poster Session 3
123
[368]
Learning Gaussian Maps for Dense Object Detection
Sonaal Kant
Paper  Poster Session 3
124
[400]
From Quantized DNNs to Quantizable DNNs
Kunyuan Du, Ya Zhang and Haibing Guan
Paper  Poster Session 3
125
[33]
Revisiting Temporal Modeling for Video Super-resolution
Takashi Isobe, Fang Zhu and Shengjin Wang
Paper  Code  Poster Session 3
126
[375]
Learning to Adapt Multi-View Stereo by Self-Supervision
Arijit Mallick, Joerg Stueckler and Hendrik Lensch
Paper  Supplemental  Poster Session 3
127
[774]
Imitating Unknown Policies via Exploration
Nathan Gavenski, Juarez Monteiro, Roger Granada, Felipe Meneguzzi and Rodrigo Barros
Paper  Supplemental  Code  Poster Session 3
128
[401]
RankPose: Learning Generalised Feature with Rank Supervision for Head Pose Estimation
Donggen Dai, Wangkit Wong and Zhuojun Chen
Paper  Code  Poster Session 3
129
[131]
M2KD: Incremental Learning via Multi-model and Multi-level Knowledge Distillation
Peng Zhou, Long Mai, Jianming Zhang, Ning Xu, Zuxuan Wu and Larry Davis
Paper  Supplemental  Poster Session 3
130
[539]
RecSal : Deep Recursive Supervision for Visual Saliency Prediction
Oindrila Saha and Sandeep Mishra
Paper  Poster Session 3
131
[287]
6DoF Object Pose Estimation via Differentiable Proxy Voting Regularizer
Xin Yu, Zheyu Zhuang, Piotr Koniusz and HONGDONG LI
Paper  Supplemental  Poster Session 3
132
[90]
Transferring Pretrained Networks to Small Data via Category Decorrelation
Ying Jin, Zhangjie Cao, Mingsheng Long and Jianmin Wang
Paper  Poster Session 3
133
[167]
Integrating Long-Short Term Network for Efficient Video Object Segmentation
Jingjing Wang, Zhu Teng, Baopeng Zhang and Jianping Fan
Paper  Poster Session 3
134
[118]
Point Cloud Super Resolution with Adversarial Residual Graph Networks
Huikai Wu and Kaiqi Huang
Paper  Code  Poster Session 3
135
[476]
On Modality Bias in the TVQA Dataset
Thomas Winterbottom, Sarah Xiao, Alistair McLean and Noura Al Moubayed
Paper  Supplemental  Code  Poster Session 3
136
[191]
Residual Likelihood Forests
Yan Zuo and Tom Drummond
Paper  Poster Session 3
137
[1025]
DALE : Dark Region-Aware Low-light Image Enhancement
DoKyeong Kwon, Guisik Kim and Junseok Kwon
Paper  Poster Session 3
138
[899]
Constrained Video Face Clustering using1NN Relations
Vicky Kalogeiton and Andrew Zisserman
Paper  Code  Poster Session 3
139
[962]
Thoracic Disease Identification and Localization using Distance Learning and Region Verification
Cheng Zhang, Francine Chen and Yan-Ying Chen
Paper  Poster Session 3
140
[121]
Image Harmonization with Attention-based Deep Feature Modulation
Guoqing Hao, Satoshi Iizuka and Kazuhiro Fukui
Paper  Supplemental  Code  Poster Session 3
141
[303]
BCaR: Beginner Classifier as Regularization Towards Generalizable Re-ID
Masato Tamura and Tomoaki Yoshinaga
Paper  Code  Poster Session 3
142
[525]
Cascaded channel pruning using hierarchical self-distillation
Roy Miles and Krystian Mikolajczyk
Paper  Supplemental  Code  Poster Session 3
143
[406]
Loss Functions for Person Image Generation
Haoyue Shi, Le Wang, Wei Tang, Nanning Zheng and Gang Hua
Paper  Poster Session 3
144
[552]
Black Magic in Deep Learning: How Human Skill Impacts Network Training
Kanav Anand, Ziqi Wang, Marco Loog and Jan van Gemert
Paper  Supplemental  Poster Session 3
145
[859]
Adversarial Concurrent Training: Optimizing Robustness and Accuracy Trade-off of Deep Neural Networks
Elahe Arani, Fahad Sarfraz and Bahram Zonooz
Paper  Poster Session 3
146
[294]
3D-GMNet: Single-View 3D Shape Recovery as A Gaussian Mixture
Kohei Yamashita, Shohei Nobuhara and Ko Nishino
Paper  Supplemental  Poster Session 3
Thursday 10th September : Oral Session 7: Synthesis and Visualisation
147
[841]
Weakly Paired Multi-Domain Image Translation
Marc Yanlong Zhang, Zhiwu Huang, Danda Pani Paudel, Janine Thoma and Luc Van Gool
Paper  Supplemental  Oral Session 7  Poster Session 4
148
[689]
Bipartite Graph Reasoning GANs for Person Image Generation
Hao Tang, Song Bai, Philip Torr and Nicu Sebe
Paper  Code  Oral Session 7  Poster Session 4
149
[115]
Multimodal Image Translation with Stochastic Style Representations and Mutual Information Loss
Sanghyeon Na, Seungjoo Yoo and Jaegul Choo
Paper  Supplemental  Oral Session 7  Poster Session 4
150
[631]
Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs
Ruigang Fu, Qingyong Hu, Xiaohu Dong, Yulan Guo, Yinghui Gao and Biao Li
Paper  Supplemental  Code  Oral Session 7  Poster Session 4
151
[711]
SketchHealer: A Graph-to-Sequence Network for Recreating Partial Human Sketches
Guoyao Su, Yonggang Qi, Kaiyue Pang, Jie Yang and Yi-Zhe Song
Paper  Code  Oral Session 7  Poster Session 4
Thursday 10th September : Oral Session 8: Video
152
[6]
Attention Distillation for Learning Video Representations
Miao Liu, Xin Chen, Yun Zhang, Yin Li and James Rehg
Paper  Supplemental  Oral Session 8  Poster Session 4
153
[130]
Procedure Completion by Learning from Partial Summaries
Ehsan Elhamifar and Zwe Naing
Paper  Oral Session 8  Poster Session 4
154
[621]
Learning from Counting: Leveraging Temporal Classification for Weakly Supervised Object Localization and Detection
Chia-Yu Hsu and Wenwen Li
Paper  Oral Session 8  Poster Session 4
155
[638]
Video Region Annotation with Sparse Bounding Boxes
Yuzheng Xu, Yang Wu, Nur Sabrina binti Zuraimi, Shohei Nobuhara and Ko Nishino
Paper  Supplemental  Oral Session 8  Poster Session 4
Thursday 10th September : Poster Session 4
156
[618]
RNN-based Motion Prediction in Competitive Fencing Considering Interaction between Players
Yutaro Honda, Rei Kawakami and Takeshi Naemura
Paper  Poster Session 4
157
[14]
Localizing Novel Attended Objects in Egocentric Views
Shujon Naha, Md Reza, Chen Yu and David Crandall
Paper  Poster Session 4
158
[154]
How to Train Your Energy-Based Model for Regression
Fredrik Gustafsson, Martin Danelljan, Radu Timofte and Thomas Schön
Paper  Supplemental  Code  Poster Session 4
159
[977]
Robust Unsupervised Cleaning of Underwater Bathymetric Point Cloud Data
Cong Chen, Abel Gawel, Stephen Krauss, Yuliang Zou, Amos Abbott and Daniel Stilwell
Paper  Poster Session 4
160
[391]
Refinement of Boundary Regression Using Uncertainty in Temporal Action Localization
Yunze Chen, Mengjuan Chen, Rui Wu, Jiagang Zhu, Zheng Zhu and Qingyi Gu
Paper  Poster Session 4
161
[512]
Real-time screen reading: reducing domain shift for one-shot learning
James Charles, Stefano Bucciarelli and Roberto Cipolla
Paper  Supplemental  Supplemental  Poster Session 4
162
[86]
Learning-based Region Selection for End-to-End Gaze Estimation
Xucong Zhang, Yusuke Sugano, Andreas Bulling and Otmar Hilliges
Paper  Supplemental  Poster Session 4
163
[63]
Centroid Based Concept Learning for RGB-D Indoor Scene Classification
Ali Ayub and Alan Wagner
Paper  Supplemental  Code  Poster Session 4
164
[335]
Learning To Pay Attention To Mistakes
Moucheng Xu, Neil Oxtoby, Daniel Alexander and Joseph Jacob
Paper  Poster Session 4
165
[79]
On the Exploration of Incremental Learning for Fine-grained Image Retrieval
Wei Chen, Yu Liu, Weiping Wang, Tinne Tuytelaars, Erwin M. Bakker and Michael Lew
Paper  Supplemental  Poster Session 4
166
[395]
View-consistent 4D Light Field Depth Estimation
Numair Khan, Min H. Kim and James Tompkin
Paper  Supplemental  Code  Poster Session 4
167
[378]
Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation
Boris Knyazev, Harm De Vries, Cătălina Cangea, Graham Taylor, Aaron Courville and Eugene Belilovsky
Paper  Supplemental  Code  Poster Session 4
168
[410]
Sentence Guided Temporal Modulation for Dynamic Video Thumbnail Generation
Mrigank Rochan, Mahesh Kumar Krishna Reddy and Yang Wang
Paper  Poster Session 4
169
[81]
Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild
Akash Sengupta, Roberto Cipolla and Ignas Budvytis
Paper  Supplemental  Code  Poster Session 4
170
[578]
Learning Effectively from Noisy Supervision for Weakly Supervised Semantic Segmentation
Wenbin Xie, Qiaoqiao Wei, Zheng Li and Hui Zhang
Paper  Supplemental  Poster Session 4
171
[790]
MDA-Net: Memorable Domain Adaptation Network for Monocular Depth Estimation
Jing Zhu, Yunxiao Shi, Mengwei Ren and Yi Fang
Paper  Poster Session 4
172
[233]
Making a Case for 3D Convolutions for Object Segmentation in Videos
Sabarinath Mahadevan, Ali Athar, Aljosa Osep, Laura Leal-Taixé, Bastian Leibe and Sebastian Hennen
Paper  Supplemental  Code  Poster Session 4
173
[742]
Spatial Feedback Learning to Improve Semantic Segmentation in Hot Weather
Shyam Nandan Rai, Vineeth N Balasubramanian, Anbumani Subramanian and C.V. Jawahar
Paper  Supplemental  Code  Poster Session 4
174
[342]
Neighbours Matter: Image Captioning with Similar Images
Qingzhong Wang, Jiuniu Wang, Antoni Chan, Siyu Huang, Haoyi Xiong, Xingjian Li and Dejing Dou
Paper  Poster Session 4
175
[474]
The ADUULM-Dataset - a Semantic Segmentation Dataset for Sensor Fusion
Andreas Pfeuffer, Markus Schön, Ditzel Carsten and Klaus Dietmayer
Paper  Code  Poster Session 4
176
[725]
LSD_2 - Joint Denoising and Deblurring of Short and Long Exposure Images with CNNs
Janne Mustaniemi, Juho Kannala, Jiri Matas, Simo Särkkä and Janne Heikkila
Paper  Supplemental  Code  Poster Session 4
177
[737]
Reducing Label Noise in Anchor-Free Object Detection
Nermin Samet, Samet Hicsonmez and Emre Akbas
Paper  Code  Poster Session 4
178
[55]
Generative Appearance Flow: A Hybrid Approach for Outdoor View Synthesis
M. Usman Rafique, Hunter Blanton, Noah Snavely and Nathan Jacobs
Paper  Supplemental  Code  Poster Session 4
179
[744]
HASTE: multi-Hypothesis Asynchronous Speeded-up Tracking of Events
Ignacio Alzugaray and Margarita Chli
Paper  Supplemental  Poster Session 4
180
[452]
Towards Convolutional Neural Networks Compression via Global&Progressive Product Quantization
Weihan Chen, Peisong Wang and Jian Cheng
Paper  Poster Session 4
181
[975]
Unsupervised Monocular Depth Estimation with Multi-Baseline Stereo
Saad Imran, Muhammad Umar Karim Khan, Sikander Mukaram and Chong-Min Kyung
Paper  Supplemental  Code  Poster Session 4
182
[111]
A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer
Vladimir Iashin and Esa Rahtu
Paper  Supplemental  Code  Poster Session 4
183
[678]
Real-Time Semantic Segmentation via Multiply Spatial Fusion Network
Haiyang Si, Zhiqiang Zhang and Feng Lu
Paper  Poster Session 4
184
[918]
POMP: Pomcp-based Online Motion Planning for active visual search in indoor environments
Yiming Wang, Francesco Giuliari, Riccardo Berra, Alberto Castellini, Alessio Del Bue, Alessandro Farinelli, Marco Cristani and Francesco Setti
Paper  Poster Session 4
185
[257]
Robust Scene Text Recognition Through Adaptive Image Enhancement
Ye Qian, Yuyang Wang and Feng Su
Paper  Supplemental  Code  Poster Session 4
186
[211]
A Novel Baseline for Zero-shot Learning via Adversarial Visual-Semantic Embedding
Yu Liu and Tinne Tuytelaars
Paper  Supplemental  Code  Poster Session 4
187
[250]
BiHand: Recovering Hand Mesh with Multi-stage Bisected Hourglass Networks
Lixin Yang, Jiasen Li, Wenqiang Xu, Yiqun Diao and Cewu Lu
Paper  Code  Poster Session 4
188
[97]
N2NSkip: Learning Highly Sparse Networks using Neuron-to-Neuron Skip Connections
Arvind Subramaniam and Avinash Sharma
Paper  Poster Session 4
189
[46]
NTGAN: Learning Blind Image Denoising without Clean Reference
Rui Zhao, Daniel P.K. Lun and Kin-Man Lam
Paper  Supplemental  Poster Session 4
190
[532]
Robust Ensemble Model Training via Random Layer Sampling Against Adversarial Attack
Hakmin Lee, Hong Joo Lee, Seong Tae Kim and Yong Man Ro
Paper  Poster Session 4
191
[803]
Robust Image Matching By Dynamic Feature Selection
Hao Huang, Jianchun Chen, Xiang Li, Lingjing Wang and Yi Fang
Paper  Poster Session 4
192
[195]
Unified Representation Learning for Cross Model Compatibility
Chien-Yi Wang, Ya-Liang Chang, Shang-Ta Yang, Dong Chen and Shang-Hong Lai
Paper  Poster Session 4
193
[861]
Self-Supervised Learning for Facial Action Unit Recognition through Temporal Consistency
Liupei Lu, Leili Tavabi and Mohammad Soleymani
Paper  Supplemental  Code  Poster Session 4
194
[643]
Unsupervised and Semi-supervised Novelty Detection using Variational Autoencoders in Opportunistic Science Missions
Lorenzo Sintini and Lars Kunze
Paper  Poster Session 4
195
[822]
Large Scale Photometric Bundle Adjustment
Oliver J. Woodford and Edward Rosten
Paper  Poster Session 4