Time slot
Start time
Day 1 (Nov. 30)
Day 2 (Dec. 1)
Day 3 (Dec. 2)
10:00-12:00 Beijing
(-1 day) 18:00 PST
(-1 day) 21:00 EST
3:00 CET
11:00 JST
14:00-16:00 Beijing
(-1 day) 22:00 PST
1:00 EST
7:00 CET
15:00 JST
17:00-19:00 Beijing
1:00 PST
4:00 EST
10:00 CET
18:00 JST
21:00-23:00 Beijing
5:00 PST
8:00 EST
14:00 CET
22:00 JST


TitleAuthorsLive 1Live 2
Condensed Movies: Story Based Retrieval with Contextual EmbeddingsMax Bain (University of Oxford)*; Arsha Nagrani (Oxford University ); Andrew Brown (University of Oxford); Andrew Zisserman (University of Oxford)2-D3-B
Class-incremental Learning with Rectified Feature-Graph PreservationCheng-Hsun Lei (National Chiao Tung University); Yi-Hsin Chen (National Chiao Tung University); Wen-Hsiao Peng (National Chiao Tung University); Wei-Chen Chiu (National Chiao Tung University)*2-C3-A
Pre-training without Natural ImagesHirokatsu Kataoka (National Institute of Advanced Industrial Science and Technology (AIST))*; Kazushige Okayasu (National Institute of Advanced Industrial Science and Technology (AIST)); Asato Matsumoto (National Institute of Advanced Industrial Science and Technology (AIST)); Eisuke Yamagata (Tokyo Institute of Technology); Ryosuke Yamada (Tokyo Denki University); Nakamasa Inoue (Tokyo Institute of Technology); Akio Nakamura (Tokyo Denki University (TDU)); Yutaka Satoh (National Institute of Advanced Industrial Science and Technology (AIST))1-A3-B
In-sample Contrastive Learning and Consistent Attention for Weakly Supervised Object LocalizationMinsong Ki (Yonsei University)*; Youngjung Uh (Yonsei University); Wonyoung Lee (Yonsei University); Hyeran Byun (Yonsei University)1-A1-C
Fast and Differentiable Message Passing on Pairwise Markov Random FieldsZhiwei Xu (Australian National University)*; Thalaiyasingam Ajanthan (ANU); RICHARD HARTLEY (Australian National University, Australia)1-C2-A
Introspective Learning by Distilling Knowledge from Online Self-explanationJindong Gu (University of Munich)*; Zhiliang Wu (Siemens AG and Ludwig Maximilian University of Munich); Volker Tresp (Siemens AG and Ludwig Maximilian University of Munich )2-B2-D
Accurate and Efficient Single Image Super-Resolution with Matrix Channel Attention NetworkHailong Ma (Xiaomi); Xiangxiang Chu (Xiaomi); Bo Zhang (Xiaomi)*1-C3-A
Progressive Batching for Efficient Non-linear Least SquaresHuu Le (Chalmers University of Technology)*; Christopher Zach (Chalmers University); Edward Rosten (Snap Inc.); Oliver J. Woodford (Snap Inc)2-B3-D
Domain Adaptation Gaze Estimation by Embedding with Prediction ConsistencyZidong Guo (Xi’an Jiaotong university)*; Zejian Yuan (Xi‘an Jiaotong University); Chong Zhang (Tencent Robotics X); Wanchao Chi (Tencent Robotics X); Yonggen Ling (Tencent); shenghao zhang (Tencent)1-C3-A
DoFNet: Depth of Field Difference Learning for Detecting Image ForgeryYonghyun Jeong (Samsung SDS)*; Jongwon Choi (Chung-Ang University); Doyeon Kim (SamsungSDS); Sehyeon Park (Samsung SDS); Minki Hong (Samsung SDS); Changhyun Park (Samsung SDS); Seungjai Min (Samsung SDS); Youngjune Gwon (Samsung SDS)1-C3-A
Watch, read and lookup: learning to spot signs from multiple supervisorsLiliane Momeni (University of Oxford); Gul Varol (University of Oxford)*; Samuel Albanie (University of Oxford); Triantafyllos Afouras (University of Oxford); Andrew Zisserman (University of Oxford)3-B3-D
Patch SVDD: Patch-level SVDD for Anomaly Detection and SegmentationJihun Yi (Seoul National University); Sungroh Yoon (Seoul National University)*2-C3-A
Meta-Learning with Context-Agnostic InitialisationsToby Perrett (University of Bristol)*; Alessandro Masullo (University of Bristol); Tilo Burghardt (University of Bristol); Majid Mirmehdi (University of Bristol); Dima Damen (University of Bristol)1-B2-D
D2D: Keypoint Extraction with Describe to Detect ApproachYurun Tian (Imperial College London)*; Vassileios Balntas (Scape Technologies); Tony Ng (Imperial College London); Axel Barroso-Laguna (Imperial College London); Yiannis Demiris (Imperial College London); Krystian Mikolajczyk (Imperial College London)1-B3-D
Backbone Based Feature Enhancement for Object DetectionHaoqin Ji (Shenzhen University); Weizeng Lu (Shenzhen University); Linlin Shen (Shenzhen University)*1-A2-C
Part-aware Attention Network for Person Re-IdentificationWangmeng Xiang (The Hong Kong Polytechnic University); Jianqiang Huang (Damo Academy, Alibaba Group); Xian-Sheng Hua (Alibaba Group); Lei Zhang (“Hong Kong Polytechnic University, Hong Kong, China”)*1-A2-C
Class-Wise Difficulty-Balanced Loss for Solving Class-ImbalanceSaptarshi Sinha (Hitachi CRL)*; Hiroki Ohashi (Hitachi Ltd); Katsuyuki Nakamura (Hitachi Ltd.)2-A2-C
Visually Guided Sound Source Separation using Cascaded Opponent Filter NetworkLingyu Zhu (Tampere University)*; Esa Rahtu (Tampere University)1-B2-D
To Filter Prune, or to Layer Prune, That Is The QuestionSara Elkerdawy (University of Alberta)*; Mostafa Elhoushi (Huawei Technologies); Abhineet Singh (University of Alberta); Hong Zhang (University of Alberta); Nilanjan Ray (University of Alberta)1-D2-A
Descriptor-Free Multi-View Region Matching for Instance-Wise 3D ReconstructionTakuma Doi (Osaka University); Fumio Okura (Osaka University)*; Toshiki Nagahara (Osaka University); Yasuyuki Matsushita (Osaka University); Yasushi Yagi (Osaka University)2-A3-C
Long-Term Cloth-Changing Person Re-identificationXuelin Qian (Fudan University); Wenxuan Wang (Fudan University); Li Zhang (University of Oxford); Fangrui Zhu (Fudan University); Yanwei Fu (Fudan University)*; Tao Xiang (University of Surrey); Yu-Gang Jiang (Fudan University); Xiangyang Xue (Fudan University)1-D3-B
Dehazing Cost Volume for Deep Multi-view Stereo in Scattering MediaYuki Fujimura (Kyoto University)*; Motoharu Sonogashira (Kyoto University); Masaaki Iiyama (Kyoto University)2-A2-C
Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position EstimationPatrick Dendorfer (TUM)*; Aljosa Osep (TUM Munich); Laura Leal-Taixé (TUM)2-D3-B
RF-GAN: A Light and Reconfigurable Network for Unpaired Image-to-Image TranslationAli Koksal (Nanyang Technological University); Shijian Lu (Nanyang Technological University)*1-A1-C
Efficient Large-Scale Semantic Visual Localization in 2D MapsTomas Vojir (CMP CTU)*; Ignas Budvytis (Department of Engineering, University of Cambridge); Roberto Cipolla (University of Cambridge)1-B1-D
SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object DetectionKeren Ye (University of Pittsburgh)*; Adriana Kovashka (University of Pittsburgh); Mark Sandler (Google); Menglong Zhu (UPenn); Andrew Howard (Google); Marco Fornoni (Google)1-A3-D
DeepSEE: Deep Disentangled Semantic Explorative Extreme Super-ResolutionMarcel C. Bühler (ETH Zürich)*; Andrés Romero (ETH Zürich); Radu Timofte (ETH Zurich)2-B2-D
Learning 3D Face Reconstruction with a Pose Guidance NetworkPengpeng Liu (The Chinese University of Hong Kong)*; Xintong Han (Huya AI); Michael Lyu (The Chinese University of Hong Kong); Irwin King (The Chinese University of Hong Kong); Jia Xu (Huya AI)2-D3-B
Domain-transferred Face Augmentation NetworkHao-Chiang Shao (Fu Jen Catholic University); Kang-Yu Liu (National Tsing Hua University); Chia-Wen Lin (National Tsing Hua University)*; Jiwen Lu (Tsinghua University)2-A3-C
A Sparse Gaussian Approach to Region-Based 6DoF Object TrackingManuel Stoiber (German Aerospace Center (DLR))*; Martin Pfanne (German Aerospace Center); Klaus H. Strobl (DLR); Rudolph Triebel (German Aerospace Center (DLR)); Alin Albu-Schaeffer (Robotics and Mechatronics Center (RMC), German Aerospace Center (DLR))2-B3-D
Encode the Unseen: Predictive Video Hashing for Scalable Mid-Stream RetrievalTong Yu (University of Strasbourg)*; Nicolas Padoy (University of Strasbourg)1-B3-D
Image Inpainting with Onion ConvolutionsShant Navasardyan (Picsart Inc.)*; Marianna Ohanyan (Picsart Inc.)2-A3-C
In Defense of LSTMs for Addressing Multiple Instance Learning ProblemsKaili Wang (KU Leuven, UAntwerpen)*; Jose Oramas (UAntwerp, imec-IDLab); Tinne Tuytelaars (KU Leuven)3-B3-D
Sketch-to-Art: Synthesizing Stylized Art Images From SketchesBingchen Liu (Rutgers, The State University of New Jersey)*; Kunpeng Song (Rutgers University); Yizhe Zhu (Rutgers University ); Ahmed Elgammal (-)1-A1-B
FreezeNet: Full Performance by Reduced Storage CostsPaul Wimmer (Luebeck University / Robert Bosch GmbH)*; Jens Mehnert (Robert Bosch GmbH); Alexandru Condurache (Bosch)2-B3-D
Chromatic Aberration Correction Using Cross-Channel Prior in Shearlet DomainKunyi Li (Tsinghua University); Xin Jin (Tsinghua University)*2-A2-C
Project to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor DataAdrian Lopez-Rodriguez (Imperial College London)*; Benjamin Busam (Technical University of Munich); Krystian Mikolajczyk (Imperial College London)2-B2-D
An Efficient Group Feature Fusion Residual Network for Image Super-ResolutionPengcheng Lei (University of Shanghai for Science and Technology); Cong Liu (University of Shanghai for Science and Technology)*1-A3-C
Adversarial Image Composition with Auxiliary IlluminationFangneng Zhan (Nanyang Technological University); Shijian Lu (Nanyang Technological University)*; Changgong Zhang (Alibaba Group); Feiying Ma (Alibaba); Xuansong Xie (Alibaba)3-A3-C
Self-Supervised Multi-View Synchronization Learning for 3D Pose EstimationSimon Jenni (Universität Bern)*; Paolo Favaro (University of Bern)1-B1-D
Adversarial Refinement Network for Human Motion PredictionXianjin Chao (The City University of Hong Kong)*; Yanrui Bin (HUST); Wenqing Chu (Tencent); Xuan Cao (Tencent); Yanhao Ge (Tencent); Chengjie Wang (Tencent); Jilin Li (Tencent); Feiyue Huang (Tencent); Howard Leung (City University of Hong Kong)1-C2-A
3D Human Motion Estimation via Motion Compression and RefinementZhengyi Luo (Carnegie Mellon University)*; S. Alireza Golestaneh (Carnegie Mellon University); Kris M. Kitani (Carnegie Mellon University)1-A1-D
Lossless Image Compression Using a Multi-Scale Progressive Statistical ModelHonglei Zhang (Nokia Technologies)*; Francesco Cricri (Nokia Technologies); Hamed R. Tavakoli (Nokia Technologies); Nannan Zou (Tampere University); Emre Aksu (Nokia Technologies); Miska M. Hannuksela (Nokia Technologies)2-B3-D
A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddingsQi Li (Auburn University); Long Mai (Adobe Research); Michael A. Alcorn (Auburn University); Anh Nguyen (Auburn University)*1-D2-A
Dense Pixel-wise Micro-motion Estimation of Object Surface by using Low Dimensional Embedding of Laser Speckle PatternRyusuke Sagawa (“AIST, Japan”)*; Yusuke Higuchi (Kyushu University); Hiroshi Kawasaki (Kyushu univ.); Ryo Furukawa (Hiroshima city univ.); Takahiro Ito (AIST)1-A1-C
Learning More Accurate Features for Semantic Segmentation in CycleNetLinzi Qu (Xidian University)*; Lihuo He (Xidian University); JunJie Ke (Xidian University); Xinbo Gao (Xidian University); Wen Lu (Xidian University)2-C3-A
Deep Snapshot HDR Imaging Using Multi-Exposure Color Filter ArrayTakeru Suda (Tokyo Institute of Technology); Masayuki Tanaka (Tokyo Institute of Technology); Yusuke Monno (Tokyo Institute of Technology)*; Masatoshi Okutomi (Tokyo Institute of Technology)3-A3-C
A Benchmark and Baseline for Language-Driven Image EditingJing Shi (University of Rochester)*; Ning Xu (Adobe Research); Trung Bui (Adobe Research); Franck Dernoncourt (Adobe Research); Zheng Wen (DeepMind); Chenliang Xu (University of Rochester)1-D3-A
Bidirectional Pyramid Networks for Semantic SegmentationDong Nie (UNC)*; Jia Xue (Rutgers University); Xiaofeng Ren (Alibaba group)1-A3-B
Semantics through Time: Semi-supervised Segmentation of Aerial Videos with Iterative Label PropagationAlina Marcu (University “Politehnica” of Bucharest)*; Vlad Licaret (Autonomous Systems); Dragos Costea (University “Politehnica” of Bucharest); Marius Leordeanu (University “Politehnica” of Bucharest)3-B3-D
GAN-based Noise Model for Denoising Real ImagesLinh Duy Tran (Teikyo University)*; Son Minh Nguyen (Teikyo University); Masayuki Arai (Teikyo Univ.)1-D2-B
Mapping of Sparse 3D Data using Alternating ProjectionSiddhant Ranade (University of Utah); Xin Yu (University of Utah); Shantnu Kakkar (Trimble); Pedro Miraldo (Instituto Superior Técnico, Lisboa); Srikumar Ramalingam (University of Utah)*2-A2-D
FKAConv: Feature-Kernel Alignment for Point Cloud ConvolutionAlexandre Boulch (valeo.ai)*; Gilles Puy (Valeo); Renaud Marlet (Ecole des Ponts ParisTech)2-D3-B
Raw-Guided Enhancing Reprocess of Low-Light Image via Deep Exposure AdjustmentHaofeng Huang (Peking University)*; Wenhan Yang (Peking University); Yueyu Hu (Peking University); Jiaying Liu (Peking University)1-B1-D
Depth-Adapted CNN for RGB-D camerasZongwei WU (Univ. Bourgogne Franche-Comte, France)*; Guillaume Allibert (Université Côte d’Azur, CNRS, I3S, France ); Christophe Stolz (Univ. Bourgogne Franche-Comte, France); Cedric Demonceaux (Univ. Bourgogne Franche-Comte, France)1-D2-B
Sparse Convolutions on Continuous Domains for Point Cloud and Event Stream NetworksDominic Jack (Queensland University of Technology)*; Frederic Maire (Queensland University of Technology); SIMON DENMAN (Queensland University of Technology, Australia); Anders Eriksson (University of Queensland )1-C3-A
Unified Application of Style Transfer for Face Swapping and ReenactmentLe Minh Ngo (University of Amsterdam)*; Christian aan de Wiel (3DUniversum); Sezer Karaoglu (University of Amsterdam); Theo Gevers (University of Amsterdam)1-D2-B
Self-supervised Learning of Orc-Bert Augmentator for Recognizing Few-Shot Oracle CharactersWenhui Han (Fudan University); Xinlin Ren (Fudan University); Hangyu Lin (Fudan University); Yanwei Fu (Fudan University)*; Xiangyang Xue (Fudan University)1-A2-B
Generic Image Segmentation in Fully Convolutional Networks by Superpixel Merging MapJin-Yu Huang (National Taiwan University); Jian-Jiun Ding (National Taiwan University)*1-B3-D
EvolGAN: Evolutionary Generative Adversarial NetworksBaptiste Roziere (Facebook AI Research); Fabien Teytaud (Univ. Littoral Cote d’Opale); Vlad Hosu (University of Konstanz); Hanhe Lin (University of Konstanz); Jeremy Rapin (Facebook AI Research); Mariia Zameshina (Inria); Olivier Teytaud (Facebook)*2-D3-B
AFN: Attentional Feedback Network based 3D Terrain Super-ResolutionAshish Kubade (International Institute Of Information Technology, Hyderabad)*; Diptiben Patel (IIIT Hyderabad); Avinash Sharma (CVIT, IIIT-Hyderabad); K. S. Rajan (IIIT Hyderabad)2-C3-A
L2R GAN: LiDAR-to-Radar TranslationLeiChen Wang (Daimler AG)*; Bastian Goldluecke (University of Konstanz); Carsten Anklam (Daimler AG)2-D3-B
Webly Supervised Semantic Embeddings for Large Scale Zero-Shot LearningYannick Le Cacheux (CEA LIST)*; Adrian Popescu (CEA LIST); Herve Le Borgne (CEA LIST)1-B1-D


TitleAuthorsLive 1Live 2
Self-Guided Multiple Instance Learning for Weakly Supervised Thoracic Disease Classification and Localization in Chest RadiographsConstantin Seibold (Karlsruhe Institute of Technology)*; Jens Kleesiek (German Cancer Research Center); Heinz-Peter Schlemmer (German Cancer Research Center); Rainer Stiefelhagen (Karlsruhe Institute of Technology)2-D3-B
RealSmileNet: A Deep End-To-End Network for Spontaneous and Posed Smile RecognitionYan Yang (Australian National University)*; Md Zakir Hossain (The Australian National University ); Tom Gedeon (The Australian National University); Shafin Rahman (North South University)1-A3-C
Anatomy and Geometry Constrained One-Stage Framework for 3D Human Pose EstimationXin Cao (Shanghai JiaoTong University); Xu Zhao (Shanghai Jiao Tong University)*1-C2-A
Imbalance Robust Softmax for Deep Embedding LearningHao Zhu (Australian National University)*; Yang Yuan (AnyVision); Guosheng Hu (AnyVision); Xiang Wu (Reconova); Neil Robertson (Queen’s University Belfast)1-C3-A
IAFA: Instance-Aware Feature Aggregation for 3D Object Detection from a Single ImageDingfu Zhou (Baidu)*; Xibin Song (Baidu); Yuchao Dai (Northwestern Polytechnical University); Junbo Yin (Beijing Institute of Technology); Feixiang Lu (Baidu); Miao Liao (Baidu); Jin Fang (Baidu ); Liangjun Zhang (Baidu)1-A3-C
Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wildweijia wu (Zhejiang University)*; Ning Lu (Tencent Cloud Product Department); Enze Xie (The University of Hong Kong); Yuxing Wang (Zhejiang University); Wenwen Yu (Xuzhou Medical University); Cheng Yang (Zhejiang University); HONG ZHOU (Zhejiang University)1-A3-C
Play Fair: Frame Contributions in Video ModelsWill Price (University of Bristol)*; Dima Damen (University of Bristol)2-D3-B
Speech2Video Synthesis with 3D Skeleton Regularization and Expressive Body PosesMiao Liao (Baidu)*; Sibo Zhang (Baidu); Peng Wang (Baidu USA LLC.); Hao Zhu (Nanjing University); Xinxin Zuo (University of Kentucky); Ruigang Yang (University of Kentucky, USA)1-A3-B
Transforming Multi-Concept Attention into Video SummarizationYen-Ting Liu (National Taiwan University)*; Yu-Jhe Li (Carnegie Mellon University); Yu-Chiang Frank Wang (National Taiwan University)1-B3-D
3D Guided Weakly Supervised Semantic SegmentationWeixuan Sun (Australian National University, Data61 )*; Jing Zhang (Australian National University); Nick Barnes (ANU)3-A3-C
Visual Tracking by TridentAlign and Context EmbeddingJanghoon Choi (Seoul National University)*; Junseok Kwon (Chung-Ang Univ., Korea); Kyoung Mu Lee (Seoul National University)2-B3-D
Frequency Attention Network: Blind Noise Removal for Real ImagesHongcheng Mo (Shanghai Jiao Tong University); Jianfei Jiang (Shanghai Jiao Tong University); Qin Wang (Shanghai Jiao Tong University)*; Dong Yin (Fullhan); Pengyu Dong (Fullhan); Jingjun Tian (Fullhan)1-C3-A
Exploiting Transferable Knowledge for Fairness-aware Image Classificationsunhee hwang (Yonsei university)*; Sungho Park (Yonsei University); Pilhyeon Lee (Yonsei University); seogkyu jeon (Yonsei university); Dohyung Kim (Yonsei University); Hyeran Byun (Yonsei University)1-B3-D
Adversarial Semi-Supervised Multi-Domain TrackingKourosh Meshgi (RIKEN AIP)*; Maryam Sadat Mirzaei (Riken AIP / Kyoto University)3-B3-D
DeepVoxels++: Enhancing the Fidelity of Novel View Synthesis from 3D Voxel EmbeddingsTong He (UCLA)*; John Collomosse (Adobe Research); Hailin Jin (Adobe Research); Stefano Soatto (UCLA)1-A3-B
CPTNet: Cascade Pose Transform Network for Single Image Talking Head AnimationJiale Zhang (Huazhong University of Science and Technology); Ke Xian (Huazhong University of Science and Technology); Chengxin Liu (Huazhong University of Science and Technology)*; Yinpeng Chen (Huazhong University of Science and Technology); Zhiguo Cao (Huazhong Univ. of Sci.&Tech.); Weicai Zhong (Huawei CBG Consumer Cloud Service Big Data Platform Dept.)1-B1-D
Multi-View Consistency Loss for Improved Single-Image 3D Reconstruction of Clothed PeopleAkin Caliskan (Center for Vision Speech and Signal Processing – University of Surrey)*; Armin Mustafa (University of Surrey); Evren Imre (Vicon); Adrian Hilton (University of Surrey)2-B3-D
CLASS: Cross-Level Attention and Supervision for Salient Objects DetectionLv Tang (Nanjing University)*; Bo Li (Nanjing University)1-D2-B
MLIFeat: Multi-level information fusion based deep local featuresYuyang Zhang (Institute of Automation, Chinese Academy of Sciences; University of Chinese Academy of Sciences); Jinge Wang (Megvii); Shibiao Xu (Institute of Automation, Chinese Academy of Sciences)*; Xiao Liu (Megvii Inc); Xiaopeng Zhang (Institute of Automation, Chinese Academy of Sciences)1-A1-B
Multiple Exemplars-based Hallucination for Face Super-resolution and EditingKaili Wang (KU Leuven, UAntwerpen)*; Jose Oramas (UAntwerp, imec-IDLab); Tinne Tuytelaars (KU Leuven)2-B3-D
End-to-end Model-based Gait RecognitionXiang Li (Nanjing University of Science and Technology)*; Yasushi Makihara (“””Osaka University, Japan”””); Chi Xu (Nanjing University of Science and Technology); Yasushi Yagi (Osaka University); Shiqi Yu (Southern University of Science and Technology, China); Mingwu Ren (Nanjing University of Science and Technology)2-A2-C
Learning End-to-End Action Interaction by Paired-Embedding Data AugmentationZiyang Song (Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University.)*; Zejian Yuan (Xi‘an Jiaotong University); Chong Zhang (Tencent Robotics X); Wanchao Chi (Tencent Robotics X); Yonggen Ling (Tencent); Shenghao Zhang (Tencent)1-C3-A
Quantum Robust FittingTat-Jun Chin (University of Adelaide); David Suter (Edith Cowan University); Shin-Fang Ch’ng (The University of Adelaide)*; James Quach (The University of Adelaide)1-A2-C
Tracking-by-Trackers with a Distilled and Reinforced ModelMatteo Dunnhofer (University of Udine)*; Niki Martinel (University of Udine); CHRISTIAN MICHELONI (University of Udine, Italy)1-D2-B
Do We Need Sound for Sound Source Localization?Takashi Oya (Waseda University)*; Shohei Iwase (Waseda University ); Ryota Natsume (Waseda University); Takahiro Itazuri (Waseda University); Shugo Yamaguchi (Waseda University); Shigeo Morishima (Waseda Research Institute for Science and Engineering)1-A1-C
Adaptive Spatio-Temporal Regularized Correlation Filters for UAV-based TrackingLibin Xu (Shandong University of Technology); Qilei Li (Sichuan University); Jun Jiang ( Southwest Petroleum University;Sichuan University of Science & Engineering); Guofeng Zou (Shandong University of Technology); Zheng Liu (University of British Columbia); Mingliang Gao (Shandong University of Technology)*1-D2-B
Learning Global Pose Features in Graph Convolutional Networks for 3D Human Pose EstimationKenkun Liu ( University of Illinois at Chicago); Zhiming Zou (University of Illinois at Chicago); Wei Tang (University of Illinois at Chicago)*2-A3-C
Horizontal Flipping Assisted Disentangled Feature Learning for Semi-Supervised Person Re-IdentificationGehan Hao ( University of Electronic Science and Technology of China); Yang Yang (Institute of Automation, Chinese Academy of Sciences); Xue Zhou (University of Electronic Science and Technology of China)*; Guanan Wang (CASIA); Zhen Lei (NLPR, CASIA, China)1-C3-A
Unpaired Multimodal Facial Expression RecognitionBin Xia (University of Science and Technology of China); Shangfei Wang (University of Science and Technology of China)*2-A3-B
Dense Dual-Path Network for Real-time Semantic SegmentationXinneng Yang (Tongji University)*; Yan Wu (Tongji University); Junqiao Zhao (Tongji University); Feilin Liu (Tongji University)1-C3-A
Audiovisual Transformer with Instance Attention for Audio-Visual Event LocalizationYan-Bo Lin (National Taiwan University)*; Yu-Chiang Frank Wang (National Taiwan University)2-B3-D
Hyperparameter-Free Out-of-Distribution Detection Using Cosine SimilarityEngkarat Techapanurak (Tohoku University)*; Masanori Suganuma (RIKEN AIP / Tohoku University); Takayuki Okatani (Tohoku University/RIKEN AIP)2-A2-C
Towards Fast and Robust Adversarial Training for Image ClassificationErh-Chung Chen (National Tsing Hua University)*; Che-Rung Lee (National Tsing Hua University )1-D3-B
Utilizing Transfer Learning and a Customized Loss Function for Optic Disc Segmentation from Retinal ImagesAbdullah Sarhan (University of Calgary)*; Ali Al-Khaz’Aly (University of Calgary); Adam Gorner (University of Calgary); Andrew Swift (University of Calgary); Jon Rokne (University of Calgary); Reda Alhajj (University of Calgary); Andrew Crichton (University of Calgary)2-A3-D
Modular Graph Attention Network for Complex Visual Relational ReasoningYihan Zheng (South China University of Technology); Zhiquan Wen (South China University of Technology); Mingkui Tan (South China University of Technology)*; Runhao Zeng (South China University of Technology); Qi Chen (South China University of Technology); Yaowei Wang (PengCheng Laboratory); Qi Wu (University of Adelaide)1-B1-D
Second Order enhanced Multi-glimpse Attention in Visual Question AnsweringQiang Sun (Fudan University)*; Binghui Xie (Fudan University); Yanwei Fu (Fudan University)1-A2-C
Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative FeaturesKrishna Kanth Nakka (EPFL)*; Mathieu Salzmann (EPFL)2-B2-D
A Calibration Method for the Generalized Imaging Model with Uncertain Calibration Target CoordinatesDavid Uhlig (Karlsruhe Institute of Technology)*; Michael Heizmann (Karlsruher Institut fuer Technologie)1-D2-B
MIX’EM: Unsupervised Image Classification using a Mixture of EmbeddingsAli Varamesh (KU Leuven)*; Tinne Tuytelaars (KU Leuven)1-D3-B
Channel Pruning for Accelerating Convolutional Neural Networks via Wasserstein MetricHaoran Duan (University of Science and Technology of China (USTC))*; Hui Li (University of Science and Technology of China (USTC))1-C3-A
Human Motion Deblurring using Localized Body PriorJonathan Samuel Lumentut (Inha University); Joshua Santoso (Inha University); In Kyu Park (Inha University)*1-C2-A
Compensating for the Lack of Extra Training Data by Learning Extra RepresentationHyeonseong Jeon (Sungkyunkwan University)*; Siho Han (Sungkyunkwan University); Sangwon Lee (SKKU); Simon S. Woo (SKKU)1-C2-A
Attended-Auxiliary Supervision Representation for Face Anti-spoofingSon Minh Nguyen (Teikyo University)*; Linh Duy Tran (Teikyo University); Masayuki Arai (Teikyo Univ.)3-A3-C
Modeling Cross-Modal interaction in a Multi-detector, Multi-modal Tracking FrameworkYiqi Zhong (University of Southern California)*; Suya You (US Army Research Laboratory); Ulrich Neumann (USC)1-B1-D
Restoring Spatially-Heterogeneous Distortions using Mixture of Experts NetworkSijin Kim (Ajou University); Namhyuk Ahn (Ajou University); Kyung-Ah Sohn (Ajou University)*1-A2-C
Semantic Synthesis of Pedestrian LocomotionMaria Priisalu (Lund University)*; Ciprian Paduraru (IMAR); Aleksis Pirinen (Lund University); Cristian Sminchisescu (Lund University)2-B2-D
HDD-Net: Hybrid Detector Descriptor with Mutual Interactive LearningAxel Barroso-Laguna (Imperial College London)*; Yannick Verdie (Huawei Noah’s Ark Lab); Benjamin Busam (Technical University of Munich); Krystian Mikolajczyk (Imperial College London)1-B2-D
Localize to Classify and Classify to Localize: Mutual Guidance in Object DetectionHeng Zhang (Univ Rennes 1)*; Elisa Fromont (Université Rennes 1, IRISA/INRIA rba); Sébastien Lefèvre (Université de Bretagne Sud / IRISA); Bruno Avignon (Atermes)1-D2-B
Betrayed by Motion: Camouflaged Object Discovery via Motion SegmentationHala Lamdouar (University of Oxford)*; Charig Yang (University of Oxford); Weidi Xie (University of Oxford); Andrew Zisserman (University of Oxford)1-B2-D
Unified Density-Aware Image Dehazing and Object Detection in Real-World Hazy ScenesZhengxi Zhang (Nanjing University of Science & Technology); Liang Zhao (Nanjing University of Science & Technology); Yunan Liu (Nanjing University of Science & Technology); Shanshan Zhang (Max Planck Institute for Informatics)*; Jian Yang (Nanjing University of Science and Technology)2-A2-C
Second-order Camera-aware Color Transformation for Cross-domain Person Re-identificationWangmeng Xiang (The Hong Kong Polytechnic University); Hongwei Yong (The Hong Kong Polytechnic University); Jianqiang Huang (Damo Academy, Alibaba Group); Xian-Sheng Hua (Alibaba Group); Lei Zhang (“Hong Kong Polytechnic University, Hong Kong, China”)*1-C3-A
DEAL: Difficulty-aware Active Learning for Semantic SegmentationShuai Xie (Zhejiang University); Zunlei Feng (Zhejiang University); Ying chen (Zhejiang University); Songtao Sun (Zhejiang University); Chao Ma (Zhejiang University); Mingli Song (Zhejiang University)*1-C2-A
Sequential View Synthesis with TransformerPhong Nguyen-Ha (University of Oulu)*; Lam Huynh ( University of Oulu); Esa Rahtu (Tampere University); Janne Heikkila (University of Oulu, Finland)1-B2-D
Image Captioning through Image TransformerSen He (University of Exeter)*; Wentong Liao (Leibniz University Hannover); Hamed R. Tavakoli (Nokia Technologies); Michael Yang (University of Twente); Bodo Rosenhahn (Leibniz University Hannover); Nicolas Pugeault (University of Glasgow)2-B2-D
Augmentation Network for Generalised Zero-Shot LearningRAFAEL FELIX (The University of Adelaide)*; Michele Sasdelli (The University of Adelaide); Ian Reid (“University of Adelaide, Australia”); Gustavo Carneiro (University of Adelaide)1-A2-C
TSI: Temporal Scale Invariant Network for Action Proposal GenerationShuming Liu (Shanghai Jiao Tong University); Xu Zhao (Shanghai Jiao Tong University)*; Haisheng Su (Shanghai Jiao Tong University); Zhilan Hu (Huawei)3-A3-C
MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial NetworkYi Wei (University at Albany – SUNY)*; Zhe Gan (Microsoft); Wenbo Li (Samsung Research America); Siwei Lyu (University at Albany); Ming-Ching Chang (University at Albany – SUNY); Lei Zhang (Microsoft); Jianfeng Gao (Microsoft Research); Pengchuan Zhang (Microsoft Research AI)2-A3-C
TTPLA: An Aerial-Image Dataset for Detection and Segmentation of Transmission Towers and Power LinesRabab Abdelfattah (University of South Carolina)*; XIAOFENG Wang (USC); Song Wang (University of South Carolina)2-C3-A
Accurate Arbitrary-Shaped Scene Text Detection via Iterative Polynomial Parameter RegressionJiahao Shi (Nanjing University); Long Chen (Nanjing University); Feng Su (Nanjing University)*2-C3-A
Local Facial Makeup Transfer via Disentangled RepresentationZhaoyang Sun (Wuhan University of Technology)*; Feng Liu (Wuhan University of Technology); Wen Liu (Wuhan University of Technology); Shengwu Xiong (Wuhan University of Technology); Wenxuan Liu (Wuhan University of Technology)3-A3-C
Gaussian Vector: An Efficient Solution for Facial Landmark DetectionYilin Xiong (Central South University)*; Zijian Zhou (Horizon); yuhao dou (Horizon); ZHIZHONG SU (Horizon Robotics)1-C2-A
Single-Image Camera Response Function Using Prediction Consistency and Gradual RefinementAashish Sharma (National University of Singapore)*; Robby T. Tan (Yale-NUS College); Loong-Fah Cheong (NUS)1-A1-C
Road Obstacle Detection Method Based on an Autoencoder with Semantic SegmentationToshiaki Ohgushi (TOYOTA); Kenji Horiguchi (TOYOTA); Masao Yamanaka (TOYOTA)*1-D3-B
Any-Shot Object DetectionShafin Rahman (North South University)*; Salman Khan (IIAI); Nick Barnes (ANU); Fahad Shahbaz Khan (Inception Institute of Artificial Intelligence)3-B3-D
Multi-Task Learning for Simultaneous Video Generation and Remote Photoplethysmography EstimationYun-Yun Tsou (National Tsing Hua University)*; Yi-An Lee (National Tsing Hua University); Chiou-Ting Hsu (National Tsing Hua University)3-A3-C
Channel Recurrent Attention Networks for Video Pedestrian RetrievalPengfei Fang (The Australian National University)*; Pan Ji (OPPO US Research Center); Jieming Zhou (The Australian National University); Lars Petersson (Data61/CSIRO); Mehrtash Harandi (Monash University)1-A2-C
Degradation Model Learning for Real-World Single Image Super-resolutionJin XIAO (The Hong Kong Polytechnic University)*; Hongwei Yong (The Hong Kong Polytechnic University); Lei Zhang (“Hong Kong Polytechnic University, Hong Kong, China”)3-B3-D
Novel-View Human Action SynthesisMohamed Ilyes Lakhal (Queen Mary University of London)*; Davide Boscaini (Fondazione Bruno Kessler); Fabio Poiesi (Fondazione Bruno Kessler); Oswald Lanz (Fondazione Bruno Kessler, Italy); Andrea Cavallaro (Queen Mary University of London, UK)1-B2-D
Scale-Aware Polar Representation for Arbitrarily-Shaped Text DetectionYanguang Bi (SenseTime Research); Zhiqiang Hu (SenseTime Research)*1-A2-C
DiscFace: Minimum Discrepancy Learning for Deep Face RecognitionInsoo Kim (Samsung Advanced Institute of Technology)*; Seungju Han (Samsung Advanced Institute of Technology); Seong-Jin Park (Samsung Advanced Institute of Technology); Ji-won Baek (Samsung Advanced Institute of Technology); Jinwoo Shin (KAIST); Jae-Joon Han (Samsung); Changkyu Choi (Samsung)2-C3-A
Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action-Gesture RecognitionLei Shi (Institute of Automation,Chinese Academy of Sciences )*; Yifan Zhang (Institute of Automation, Chinese Academy of Sciences); Jian Cheng (“Chinese Academy of Sciences, China”); Hanqing Lu (NLPR, Institute of Automation, CAS)1-D2-B
Background Learnable Cascade for Zero-Shot Object DetectionYe Zheng (Institute of Computing Technology, Chinese Academy of Sciences)*; Ruoran Huang (Institute of Computing Technology, Chinese Academy of Sciences); Chuanqi Han (Institute of Computing Technology, Chinese Academy of Sciences); Xi Huang (Institute of computing technology of the Chinese Academy of Sciences); Li Cui ( Institute of computing technology of the Chinese Academy of Sciences)1-A2-C
Feature Variance Ratio-Guided Channel Pruning for Deep Convolutional Network AccelerationJunjie He (Zhejiang University)*; Bohua Chen (Zhejiang University); Yinzhang Ding (Zhejiang University); Dongxiao Li (Zhejiang University)1-A3-C
Leveraging Tacit Information Embedded in CNN Layers for Visual TrackingKourosh Meshgi (RIKEN AIP)*; Maryam Sadat Mirzaei (Riken AIP / Kyoto University); Shigeyuki Oba (Kyoto University)1-B3-D
Recursive Bayesian Filtering for Multiple Human Pose Tracking from Multiple CamerasOh-Hun Kwon (University of Bonn); Julian Tanke (University of Bonn)*; Jürgen Gall (University of Bonn)2-D3-B
dpVAEs: Fixing Sample Generation for Regularized VAEsRiddhish Bhalodia (Scientific Computing and Imaging Institute); Iain Lee (Scientific computing and Imaging Institute, University of Utah); Shireen Elhabian (Scientific Computing and Imaging Institute, University of Utah)*2-A3-D
CloTH-VTON: Clothing Three-dimensional reconstruction for Hybrid image-based Virtual Try-ONMatiur Rahman Minar (Seoul National University of Science and Technology); Heejune Ahn (Seoul National Univ. of Science and Technology)*3-B3-D
Homography-based Egomotion Estimation Using Gravity and SIFT FeaturesYaqing Ding (Nanjing University of Science and Technology)*; Daniel Barath (MTA SZTAKI, CMP Prague); Zuzana Kukelova (Czech Technical University in Prague)1-C2-A
Synergistic Saliency and Depth Prediction for RGB-D Saliency DetectionYue Wang (Dalian University of Technology); Yuke Li (UC Berkeley); James H. Elder (York University); Runmin Wu (Dalian University of Technology ); Huchuan Lu (Dalian University of Technology)*; Lu Zhang (Dalian University of Technology)2-C3-A
RAF-AU Database: In-the-Wild Facial Expressions with Subjective Emotion Judgement and Objective AU AnnotationsWen-Jing Yan (JD Digits)*; Shan Li (Beijing University of Posts and Telecommunications); Chengtao Que (JD Digits); Jiquan Pei (JD Digits); Weihong Deng (Beijing University of Posts and Telecommunications)2-A2-C
EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention FusionChia-Yuan Chang (National Taiwan University)*; Shuo-En Chang (National Taiwan University); Pei-Yung Hsiao (National University of Kaohsiung); Li-Chen Fu (National Taiwan University)2-A2-C
SDCNet: Size Divide and Conquer Network for Salient Object DetectionSenbo Yan (Zhejiang University); Xiaowen Song (Zhejiang University)*; chuer yu (ZheJiang University)3-A3-C
Real-Time Segmentation Networks should be Latency AwareEvann Courdier (Idiap Research Institute)*; François Fleuret (University of Geneva)1-D3-B
Faster Self-adaptive Deep StereoHaiyang Wang (Zhejiang University)*; Xinchao Wang (Stevens Institute of Technology); Jie Song (Zhejiang University); Jie Lei (Zhejiang University); Mingli Song (Zhejiang University)1-A2-C
Reconstructing Creative Lego ModelsGeorge Tattersall (University of York)*; Dizhong Zhu (University of York); William A. P. Smith (University of York); Sebastian Deterding (University of York); Patrik Huber (University of York)1-D2-B
Unsupervised Domain Adaptive Object Detection using Forward-Backward Cyclic AdaptationSiqi Yang (University of Queensland)*; Lin Wu (University of Queensland); Arnold Wiliem (the University of Queensland); Brian C. Lovell (University of Queensland)1-D2-B
Learn more, forget less: Cues from human brainArijit Patra (University of Oxford); Tapabrata Chakraborti (University of Oxford)*2-B3-D
BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal GenerationHaisheng Su (SenseTime Group Limited)*2-A2-B
Query by Strings and Return Ranking Word Regions with Only One LookPeng Zhao (Beijing Jiaotong University); Wenyuan Xue (Beijing Jiaotong University); Qingyong Li (Beijing Jiaotong University)*; Siqi Cai (Beijing Jiaotong University)2-C3-A
Rotation Axis Focused Attention Network (RAFA-Net) for Estimating Head PoseArdhendu Behera (Edge Hill University)*; Zachary Wharton (Edge Hill University); Pradeep Hewage (Edge Hill University); Swagat Kumar (Edge Hill University)1-B1-D
COG: COnsistent data auGmentation for object perceptionZewen He (Casia)*; Rui Wu (Horizon Robotics); Dingqian Zhang (Horizon Robotics)1-C2-A
A Two-Stage Minimum Cost Multicut Approach to Self-Supervised Multiple Person TrackingKalun Ho (Fraunhofer ITWM)*; Amirhossein Kardoost (University of Mannheim); Franz-Josef Pfreundt (Fraunhofer ITWM); Janis Keuper (hs-offenburg); Margret Keuper (University of Mannheim)1-D2-B
Cascaded Transposed Long-range Convolutions for Monocular Depth EstimationGo Irie (NTT Corporation)*; Daiki Ikami (NTT Corporation); Takahito Kawanishi (NTT Corporation); Kunio Kashino (NTT Communication Science Laboratories)1-D2-B
SGNet: Semantics Guided Deep Stereo MatchingShuya Chen (Zhejiang University); Zhiyu Xiang (Zhejiang University)*; Chengyu Qiao (Zhejiang University); Yiman Chen (Zhejiang University); Tingming Bai (Zhejiang University)1-B3-D
Reweighted Non-convex Non-smooth Rank Minimization based Spectral Clustering on Grassmann ManifoldXinglin Piao (Peng Cheng Laboratory; Peking University; Dalian University of Technology)*; Yongli Hu (Beijing University of Technology); Junbin Gao (University of Sydney, Australia); Yanfeng Sun (Beijing University of Technology); Xin Yang (Dalian University of Technology); Baocai Yin (Beijing University of Technology)2-C3-A
Branch Interaction Network for Person Re-identificationZengming Tang (Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai, China)*; Jun Huang (Shanghai Advanced Research Institute, Chinese Academy of Sciences)1-C3-A
Learning to Adapt to Unseen Abnormal Activities under Weak SupervisionJaeYoo Park (Seoul National University)*; Junha Kim (Seoul National University); Bohyung Han (Seoul National University)1-D2-B
A Global to Local Double Embedding Method for Multi-person Pose EstimationYiming Xu (UESTC)*; Jiaxin Li (Beijing Institute of Technology); Yan Ding (Beijing Institute of Technology); Hua-Liang Wei (University of Sheffield)3-B3-D
Attention-Based Fine-Grained Classification of Bone Marrow CellsWeining Wang (South China University of Technology); Peirong Guo (South China University of Technology)*; Lemin Li (South China University of Technology); Yan Tan (Peking University People’s Hospital); Hongxia Shi (Peking University People’s Hospital); Yan Wei (Peking University People’s Hospital); Xiangmin Xu (South China University of Technology)3-A3-C
Reconstructing Human Body Mesh from Point Clouds by Adversarial GP NetworkBoyao Zhou (Inria)*; Jean-Sebastien Franco (INRIA); Federica Bogo (Microsoft); Bugra Tekin (Microsoft); Edmond Boyer (Inria)1-B3-D
Learning Local Feature Descriptors for Multiple Object TrackingDmytro Borysenko (Samsung R&D Institute Ukraine); Dmytro Mykheievskyi (Samsung R&D Institute Ukraine); Viktor Porokhonskyy (Samsung Research&Development Institute Ukraine (SRK))*2-B2-D
Knowledge Transfer Graph for Deep Collaborative LearningSoma Minami (Chubu university)*; Tsubasa Hirakawa (Chubu University); Takayoshi Yamashita (Chubu University); Hironobu Fujiyoshi (Chubu University)2-C3-A
Interpreting Video Features: A Comparison of 3D Convolutional Networks and Convolutional LSTM NetworksJoonatan Mänttäri (KTH Royal Institute of Technology); Sofia Broomé (KTH Royal Institute of Technology)*; John Folkesson (KTH Royal Institute of Technology); Hedvig Kjellström (KTH Royal Institute of Technology)2-D3-B
Bi-Directional Attention for Joint Instance and Semantic Segmentation in Point Cloudsguangnan wu (Shandong university)*; Zhiyi Pan (Shandong University); Peng Jiang (Shandong University); Changhe Tu (Shandong University)1-D2-B
Color Enhancement using Global Parameters and Local Features LearningEnyu Liu (Tencent)*; Songnan Li (Tencent); Shan Liu (Tencent America)1-A1-C
Over-exposure Correction via Exposure and Scene Information DisentanglementYuhui Cao (SECE, Shenzhen Graduate School, Peking University)*; Yurui Ren (Shenzhen Graduate School, Peking University); Thomas H. Li (Advanced Institute of Information Technology, Peking University); Ge Li (SECE, Shenzhen Graduate School, Peking University)1-C3-A
Adaptive Spotting: Deep Reinforcement Object Search in 3D Point CloudsOnkar Krishna (NTT Corporation, Japan)*; Go Irie (NTT Corporation); Xiaomeng Wu (NTT Corporation); Takahito Kawanishi (NTT Corporation); Kunio Kashino (NTT Communication Science Laboratories)3-A3-C
Semi-supervised Facial Action Unit Intensity Estimation with Contrastive LearningEnrique Sanchez (Samsung AI Centre)*; Adrian Bulat (Samsung AI Center, Cambridge); Anestis Zaganidis (Samsung); Georgios Tzimiropoulos (Queen Mary University of London)1-B3-D
Multi-label X-ray Imagery Classification via Bottom-up Attention and Meta FusionBenyi Hu (Xi’an Jiaotong University)*; Chi Zhang (Xi’an Jiaotong Univiersity); Le Wang (Xi’an Jiaotong University); Qilin Zhang (HERE Technologies); Yuehu Liu (Xi’an Jiaotong University)2-A2-C
Bridging Adversarial and Statistical Domain Transfer via Spectral Adaptation NetworksChristoph Raab (FHWS)*; Philipp Väth (FHWS); Peter Meier (FHWS); Frank-Michael Schleif (FHWS)1-B2-D
Weakly-supervised Reconstruction of 3D Objects with Large Shape Variation from Single In-the-Wild ImagesShichen Sun (Sichuan University); Zhengbang Zhu (Sichuan University); Xiaowei Dai (Sichuan University); Qijun Zhao (Sichuan University)*; Jing Li (Sichuan University)1-A2-B
FootNet: An efficient convolutional network for multiview 3D foot reconstructionFelix Kok (Cambridge University)*; James Charles (Cambridge University); Roberto Cipolla (University of Cambridge)1-D3-B
MTNAS: Search Multi-Task Networks for Autonomous DrivingHao Liu (Beijing Institute of Technology)*; Dong Li (Xilinx); JinZhang Peng (Xilinx); Qingjie Zhao (Beijing Institute of Technology); Lu Tian (Xilinx,Inc.); Yi Shan (Xilinx)3-B3-D
Active Learning for Video Description With Cluster-Regularized Ensemble RankingDavid M. Chan (University of California, Berkeley)*; Sudheendra Vijayanarasimhan (Google research); David A. Ross (Google); John F. Canny (UC Berkeley)1-B2-D
FAN: Feature Adaptation Network for Surveillance Face Recognition and NormalizationXi Yin (Microsoft Cloud & AI)*; Ying Tai (Tencent YouTu); Yuge Huang (Tencent YouTu); Xiaoming Liu (Michigan State University)1-D3-B
A Day on Campus – An Anomaly Detection Dataset for Events in a Single CameraMantini Pranav (University of Houston)*; Li Zhenggang (University of Houston); Shah Shishir K (University of Houston)1-A1-D
Regularizing Meta-Learning via Gradient DropoutHung-Yu Tseng (University of California, Merced)*; Yi-Wen Chen (University of California, Merced); Yi-Hsuan Tsai (NEC Labs America); Sifei Liu (NVIDIA); Yen-Yu Lin (National Chiao Tung University); Ming-Hsuan Yang (University of California at Merced)2-A3-B
Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and ScoreHe Huang (University of Illinois at Chicago)*; Shunta Saito (Preferred Networks, Inc.); Yuta Kikuchi (Preferred Networks, Inc.); Eiichi Matsumoto (Preferred Networks, Inc.); Wei Tang (University of Illinois at Chicago); Philip S. Yu (UIC)2-A3-B
Spatial Class Distribution Shift in Unsupervised Domain Adaptation: Local Alignment Comes to RescueSafa Cicek (UCLA)*; Ning Xu (Adobe Research); Zhaowen Wang (Adobe Research); Hailin Jin (Adobe Research); Stefano Soatto (UCLA)2-D3-B
BLT: Balancing Long-Tailed Datasets with Adversarially-Perturbed ImagesJedrzej Kozerawski (UC Santa Barbara); Victor Fragoso (Microsoft)*; Nikolaos Karianakis (Microsoft); Gaurav Mittal (Microsoft); Matthew Turk (TTIC); Mei Chen (Microsoft)3-A3-B
Point Proposal based Instance Segmentation with Rectangular Masks for Robot Picking TaskSatoshi Ito (Toshiba Corporation)*; Susumu Kubota (Toshiba Corporation)2-A3-C
OpenGAN: Open Set Generative Adversarial NetworksLuke Ditria (Monash University); Benjamin J. Meyer (Monash University)*; Tom Drummond (Monash University)1-A1-C
Video-Based Crowd Counting Using a Multi-Scale Optical Flow Pyramid NetworkMohammad Asiful Hossain (HUAWEI Technologies Co, LTD.)*; Kevin Cannons (Huawei Technologies Canada Co., Ltd ); Daesik Jang (Personal Research); Fabio Cuzzolin (Oxford Brookes University); Zhan Xu (Huawei Canada)1-B2-D
Synthesizing the Unseen for Zero-shot Object DetectionNasir Hayat (IIAI); Munawar Hayat (IIAI)*; Shafin Rahman (North South University); Salman Khan (Australian National University (ANU)); Syed Waqas Zamir (IIAI); Fahad Shahbaz Khan (Inception Institute of Artificial Intelligence)1-C2-A
SDP-Net: Scene Flow Based Real-time Object Detection and Prediction from Sequential 3D Point CloudsYi Zhang (Zhejiang University); Yuwen Ye (Zhejiang University); Zhiyu Xiang (Zhejiang University)*; Jiaqi Gu (Zhejiang University)1-C2-A
Large-Scale Cross-Domain Few-Shot LearningJiechao Guan (Renmin University of China); Manli Zhang (Renmin University of China); Zhiwu Lu (Renmin University of China)*1-D2-B
Few-Shot Zero-Shot Learning: Knowledge Transfer with Less SupervisionNanyi Fei (Renmin University of China); Jiechao Guan (Renmin University of China); Zhiwu Lu (Renmin University of China)*; Yizhao Gao (Renmin University of China)1-B2-D
Vax-a-Net: Training-time Defence Against Adversarial Patch AttacksThomas Gittings (University of Surrey); Steve Schneider (University of Surrey); John Collomosse (Adobe Research)*2-A3-B
Towards Optimal Filter Pruning with Balanced Performance and Pruning SpeedDong Li (Nuctech)*; Sitong Chen (Nuctech); Xudong Liu (Nuctech); Yunda Sun (Nuctech); Li Zhang (Nuctech)2-B3-D
Jointly Discriminating and Frequent Visual Representation MiningQiannan Wang (Xidian university); Ying Zhou (Xidian University); ZhaoYan Zhu (Xidian university); Xuefeng Liang (Xidian University)*; Yu Gu (School of Artificial Intelligence, Xi’dian University)1-C2-A
Fully Supervised and Guided Distillation for One-Stage DetectorsDeyu Wang (Canon Information Technology (Beijing) Co., LTD)*; Dongchao Wen (Canon Information Technology (Beijing) Co., LTD); Junjie Liu (Canon Information Technology (Beijing) Co., LTD); Wei Tao (Canon Information Technology (Beijing) Co., LTD); Tse-Wei Chen (Canon Inc.); Kinya Osa (Canon Inc.); Masami Kato (Canon Inc.)2-B3-D
Spatial Temporal Attention Graph Convolutional Networks with Mechanics-Stream for Skeleton-based Action RecognitionKatsutoshi Shiraki (Chubu University)*; Tsubasa Hirakawa (Chubu University); Takayoshi Yamashita (Chubu University); Hironobu Fujiyoshi (Chubu University)2-C3-A
Synthetic-to-real domain adaptation for lane detectionNoa Garnett (GM); Roy Uziel (Ben-Gurion University); Netalee Efrat (General Motors); Dan Levi (General Motors)*1-B2-D
Best Buddies Registration for Point CloudsAmnon Drory (Tel-Aviv University)*; Tal Shomer (Tel-Aviv University); Shai Avidan (Tel Aviv University); Raja Giryes (Tel Aviv University)1-D3-B
HPGCNN: Hierarchical Parallel Group Convolutional Neural Networks for Point Clouds ProcessingJisheng Dang (Lanzhou Jiaotong University); Jun Yang (School of Electronic and Information Engineering, Lanzhou Jiaotong University)*1-A1-C
Discrete Spatial Importance-Based Deep Weighted HashingYang Shi (Shandong University); Xiushan Nie (Shandong Jianzhu University)*; Quan Zhou (Shandong University); Xiaoming Xi (Shandong Jianzhu University ); Yilong Yin (Shandong University)1-D3-B
Localin Reshuffle Net: Toward Naturally and Efficiently Facial Image BlendingChengyao Zheng (Southeast Univeristy); Siyu Xia (Southeast University, China); Joseph Robinson (Northeastern University)*; Changsheng Lu (Shanghai Jiao Tong University); Wayne Wu (Tsinghua University); Chen Qian (SenseTime); Ming Shao (University of Massachusetts Dartmouth)1-B3-D
Local Context Attention for Salient Object SegmentationJing Tan (Megvii(face++) Research); Pengfei Xiong (Megvii(face++) Research)*; Zhengyi Lv (Megvii(face++) Research); Kuntao Xiao (Megvii(face++) Research); Yuwen He (Megvii(face++) Research)2-A3-D
Overwater Image Dehazing via Cycle-Consistent Generative Adversarial NetworkShunyuan Zheng (Harbin Institute of Technology)*; Jiamin Sun (Harbin Institute of Technology); Qinglin Liu (Harbin Institute of Technology); Yuankai Qi (Harbin Institute of Technology); Shengping Zhang (Harbin Institute of Technology)1-D2-B
RGB-D Co-attention Network for Semantic SegmentationHao Zhou (Harbin Engineering University)*; Lu Qi (The Chinese University of Hong Kong); Zhaoliang Wan (Harbin Engineering University); Hai Huang (Harbin Engineering University); Xu Yang (Chinese Academy of Sciences)1-B1-D
Dynamic Depth Fusion and Transformation for Monocular 3D Object DetectionErli Ouyang (Fudan University)*; Li Zhang (University of Oxford); Mohan Chen (Fudan University); Anurag Arnab (University of Oxford); Yanwei Fu (Fudan University)1-B2-D
Graph-based Heuristic Search for Module Selection Procedure in Neural Module NetworkYuxuan Wu (The University of Tokyo)*; Hideki Nakayama (The University of Tokyo)1-A2-C
Learning Multi-Instance Sub-pixel Point LocalizationJulien Schroeter (Cardiff University)*; Tinne Tuytelaars (KU Leuven); Kirill Sidorov (Cardiff University); David Marshall (Cardiff University)1-B3-D
Explaining image classifiers by removing input features using generative modelsChirag Agarwal (UIC); Anh Nguyen (Auburn University)*2-A3-D
Hierarchical X-Ray Report Generation via Pathology tags and Multi Head AttentionPreethi Srinivasan (IIT Mandi); Daksh Thapar (Indian Institute of Technology, Mandi)*; Arnav Bhavsar (IIT Mandi); Aditya Nigam (IIT mandi)1-A3-C
OpenTraj: Assessing Prediction Complexity in Human Trajectories DatasetsJavad Amirian (Inria, Rennes, France)*; Bingqing Zhang (UCL); Francisco Valente Castro (Cimat); Juan Jose Baldelomar (Cimat); Jean-Bernard Hayet (CIMAT); Julien Pettré (INRIA Rennes – Bretagne Atlantique)1-B2-D
Compact and Fast Underwater Segmentation Network for Autonomous Underwater VehiclesJiangtao Wang (Loughborough University); Baihua Li (Loughborough University)*; Yang Zhou (Loughborough University); Emanuele Rocco (Witted Srl); Qinggang Meng (Computer Science Department Loughborough University)1-B3-D
Contrastively Smoothed Class Alignment for Unsupervised Domain AdaptationShuyang Dai (Duke University)*; Yu Cheng (Microsoft); Yizhe Zhang (Microsoft Research); Zhe Gan (Microsoft); Jingjing Liu (Microsoft); Lawrence Carin (CS)2-A2-D
TinyGAN: Distilling BigGAN for Conditional Image GenerationTing-Yun Chang (National Taiwan University)*; Chi-Jen Lu (Academia Sinica)3-A3-C
RGB-T Crowd Counting from Drone: A Benchmark and MMCCN NetworkTao Peng (Tianjin University); Qing Li (Northwestern Polytechnical University); Pengfei Zhu (Tianjin university)*1-B2-A
Uncertainty Estimation and Sample Selection for Crowd CountingViresh Ranjan (Stony Brook University)*; Boyu Wang (Stony Brook University); Mubarak Shah (University of Central Florida); Minh Hoai (Stony Brook University)1-A1-D
Double Targeted Universal Adversarial PerturbationsPhilipp Benz (KAIST)*; Chaoning Zhang (KAIST); Tooba Imtiaz (KAIST); In So Kweon (KAIST)2-D3-B
Pose Correction Algorithm for Relative Frames between Keyframes in SLAMYoungseok Jang (Seoul National University)*; Hojoon Shin (Seoul National University); H. Jin Kim (Seoul National University)3-B3-D
Visualizing Color-wise Saliency of Black-Box Image Classification ModelsYuhki Hatakeyama (SenseTime Japan)*; Hiroki Sakuma (SenseTime Japan); Yoshinori Konishi (SenseTime Japan); Kohei Suenaga (Kyoto University)1-A2-C
Adversarially Robust Deep Image Super-Resolution using Entropy RegularizationJun-Ho Choi (Yonsei University); Huan Zhang (UCLA); Jun-Hyuk Kim (Yonsei University); Cho-Jui Hsieh (UCLA); Jong-Seok Lee (“Yonsei University, Korea”)*1-B2-D
CS-MCNet:A Video Compressive Sensing Reconstruction Network with Interpretable Motion CompensationBowen Huang (Fudan University)*; Jinjia Zhou (Hosei University); Xiao Yan (Fudan University); Ming’e Jing (Fudan University); Rentao Wan (Fudan University); Yibo Fan (Fudan University)1-A3-C
Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge DevicesJia-Ren Chang (National Chiao Tung University; aetherAI); Pei-Chun Chang (National Chiao Tung University); Yong-Sheng Chen (National Chiao Tung University)*1-A2-C
ERIC: Extracting Relations Inferred from ConvolutionsJoe Townsend (Fujitsu Laboratories of Europe LTD)*; Theodoros Kasioumis (Fujitsu Laboratories of Europe LTD); Hiroya Inakoshi (Fujitsu Laboratories of Europe)1-D3-B
Show, Conceive and Tell: Image Captioning with Prospective Linguistic InformationYiqing Huang (Tsinghua University); Jiansheng Chen (Tsinghua University)*1-C3-A
MCGKT-Net: Multi-level Context Gating Knowledge Transfer Network for Single Image DerainingKohei Yamamichi (Yamaguchi University)*; Xian-Hua Han (Yamaguchi University)1-A1-B
Lightweight Single-Image Super-Resolution Network with Attentive Auxiliary Feature LearningXuehui Wang (School of Data and Computer Science, Sun Yat-sen University); qing wang (School of Data and Computer Science, Sun Yat-sen University); Yuzhi Zhao (City University of Hong Kong); Junchi Yan (Shanghai Jiao Tong University); Lei Fan (Northwestern University); long chen (School of Data and Computer Science, Sun Yat-sen University)*1-A3-C
MMD based Discriminative Learning for Face Forgery DetectionJian Han (University of Amsterdam)*; Theo Gevers (University of Amsterdam)1-B2-D
Motion Prediction Using Temporal Inception ModuleTim Lebailly (EPFL)*; Sena Kiciroglu (EPFL (École polytechnique fédérale de Lausanne)); Mathieu Salzmann (EPFL); Pascal Fua (EPFL, Switzerland); Wei Wang (EPFL)3-B3-D
VAN: Versatile Affinity Network for End-to-end Online Multi-Object TrackingHyemin Lee (POSTECH)*; Inhan Kim (POSTECH); Daijin Kim (Pohang University of Science and Technology)3-B3-D
SAUM: Symmetry-Aware Upsampling Module for Consistent Point Cloud CompletionHyeontae Son (Seoul National University)*; Young Min Kim (Seoul National University)1-C2-A
Online Knowledge Distillation via Multi-branch Diversity EnhancementZheng Li (Institute of Virtual Reality and Intelligent System, Hangzhou Normal University)*; YING HUANG (Hangzhou Normal University); Defang Chen (Zhejiang University); Tianren Luo (Institute of Virtual Reality and Intelligent System,Hangzhou Normal University); Ning Cai (Institute of Virtual Reality and Intelligent System,Hangzhou Normal University); Zhigeng Pan (Institute of Virtual Reality and Intelligent System,Hangzhou Normal University)1-C2-A
V2A – Vision to Action: Learning robotic arm actions based on vision and languageMichal Nazarczuk (Imperial College London)*; Krystian Mikolajczyk (Imperial College London)2-B2-D
Emotional Landscape Image Generation Using Generative Adversarial NetworksChanjong Park (Yonsei University); In-Kwon Lee (Yonsei University)*2-A2-C
Mask-Ranking Network for Semi-Supervised Video Object SegmentationWenjing Li (University of Electronic Science & Technology of China)*; Xiang Zhang (University of Electronic Science & Technology of China); Yujie Hu (University of Electronic Science & Technology of China); Yingqi Tang (University of Electronic Science & Technology of China)1-A2-C
Rotation Equivariant Orientation Estimation for Omnidirectional LocalizationChao Zhang (Toshiba Europe Limited)*; Ignas Budvytis (Department of Engineering, University of Cambridge); Stephan Liwicki (Toshiba Europe Limited); Roberto Cipolla (University of Cambridge)1-B3-D
Robust High Dynamic Range (HDR) Imaging with Complex Motion and ParallaxZhiyuan Pu (NanJing University); Peiyao Guo (Nanjing University); M. Salman Asif (University of California, Riverside); Zhan Ma (Nanjing University)*2-D3-A
Low-light Color Imaging via Dual Camera AcquisitionPeiyao Guo (Nanjing University); Zhan Ma (Nanjing University)*3-B3-D
Deep Priors inside an Unrolled and Adaptive Deconvolution ModelHung-Chih Ko (National Taiwan University); Je-Yuan Chang (National Taiwan University); Jian-Jiun Ding (National Taiwan University)*3-A3-C
Low-level Sensor Fusion Network for 3D Vehicle Detection using Radar Range-Azimuth Heatmap and Monocular ImageJinhyeong Kim ( Korea Advanced Institute of Science and Technology); Youngseok Kim (Korea Advanced Institute of Science and Technology (KAIST))*; Dongsuk Kum (Korea Advanced Institute of Science and Technology)3-B3-D
Few-Shot Object Detection by Second-order PoolingShan Zhang (ANU, Beijing Union University)*; Dawei Luo (Beijing Key Laboratory of Information Service Engineering, Beijing Union University ); Lei Wang (“University of Wollongong, Australia”); Piotr Koniusz (Data61/CSIRO, ANU)1-A3-C
Multi-scale Attentive Residual Dense Network for Single Image Rain RemovalXiang Chen (Shenyang Aerospace University ); Yufeng Huang (Shenyang Aerospace University)*; Lei Xu (Shenyang Fire Science and Technology Research Institute of MEM)2-C3-A
3D Object Detection from Consecutive Monocular ImagesChia-Chun Cheng (National Tsing Hua University)*; Shang-Hong Lai (Microsoft)1-C2-A
Faster, Better and More Detailed: 3D Face Reconstruction with Graph Convolutional NetworksShiyang Cheng (Samsung)*; Georgios Tzimiropoulos (Samsung AI); Jie Shen (Imperial College London); Maja Pantic (Samsung AI Centre Cambridge/ Imperial College London )2-D3-B
RE-Net: A Relation Embedded Deep Model for AU Occurrence and Intensity EstimationHuiyuan Yang (Binghamton University-SUNY)*; Lijun Yin (State University of New York at Binghamton)1-A1-D
Data-Efficient Ranking Distillation for Image RetrievalZakaria Laskar (Aalto University)*; Juho Kannala (Aalto University, Finland)2-B2-D
Self-supervised Sparse to Dense Motion SegmentationAmirhossein Kardoost (University of Mannheim)*; Kalun Ho (Fraunhofer ITWM); Peter Ochs (Saarland University); Margret Keuper (University of Mannheim)1-D2-B
3D Object Detection and Pose Estimation of Unseen Objects in Color Images with Local Surface EmbeddingsGiorgia Pitteri (Université de Bordeaux, LaBRI)*; Aureélie Bugeau (University of Bordeaux); Slobodan Ilic (Siemens AG); Vincent Lepetit (Ecole des Ponts ParisTech)2-B2-D
Dense-Scale Feature Learning in Person Re-IdentificationLi Wang (Inspur); Baoyu Fan (Inspur Electronic Information Industry Co.,Ltd.)*; Zhenhua Guo (Inspur Electronic Information Industry Co.,Ltd.); Yaqian Zhao (Inspur); Runze Zhang (Inspur Electronic Information Industry Co.,Ltd.); Rengang Li (Inspur); Weifeng Gong ( Inspur Electronic Information Industry Co.,Ltd.)1-B3-D
Contextual Semantic InterpretabilityDiego Marcos (Wageningen University)*; Ruth Fong (University of Oxford); Sylvain Lobry (Wageningen University and Research); Rémi Flamary (Université Côte d’Azur); Nicolas Courty (UBS); Devis Tuia (Wageningen University and Research)2-B2-D
MatchGAN: A Self-Supervised Semi-Supervised Conditional Generative Adversarial NetworkJiaze Sun (Imperial College London)*; Binod Bhattarai (Imperial College London); Tae-Kyun Kim (Imperial College London)2-B2-D
COMET: Context-Aware IoU-Guided Network for Small Object TrackingSeyed Mojtaba Marvasti-Zadeh (University of Alberta)*; Javad Khaghani (University of Alberta); Hossein Ghanei-Yakhdan (Yazd University); Shohreh Kasaei (Sharif University of Technology); Li Cheng (ECE dept., University of Alberta)1-A2-D
MBNet: A Multi-Task Deep Neural Network for Semantic Segmentation and Lumbar Vertebra Inspection on X-ray ImagesVan Luan Tran (National Chung Cheng University)*; Huei-Yung Lin (National Chung Cheng University); Hsiao-Wei Liu (Industrial Technology Research Institute (ITRI))1-C3-A
Feedback Recurrent Autoencoder for Video CompressionAdam Golinski (University of Oxford)*; Reza Pourreza (Qualcomm); Yang Yang (Qualcomm Inc.); Guillaume Sautiere (Qualcomm AI Research); Taco S. Cohen (Qualcomm)1-B1-D
Multi-task Learning with Future States for Vision-based Autonomous DrivingInhan Kim (POSTECH)*; Hyemin Lee (POSTECH); Joonyeong Lee (POSTECH); Eunseop Lee (POSTECH); Daijin Kim (Pohang University of Science and Technology)1-D2-B
Understanding Motion in Sign Language: A New Structured Translation DatasetJefferson Rodriguez (UIS); Juan Chacon (UIS); Edgar Rangel (UIS); Luis Guayacan (UIS); Claudia Hernandez (UIS); Luisa Hernandez (UIS); Fabio Martinez (UIS )*2-D3-A
Discovering Multi-Label Actor-Action Association in a Weakly Supervised SettingSovan Biswas (University of Bonn)*; Juergen Gall (University of Bonn)1-B3-D
Trainable Structure Tensors for Autonomous Baggage Threat Detection Under Extreme OcclusionTaimur Hassan (Khalifa University of Science and Technology)*; Naoufel Werghi (Khalifa University of Science and Technology)2-D3-A