Presentation Schedule

  • All times are Pacific Standard 

Date: Wednesday, January 6, 2021 

Oral 1A: Human Applications : Faces, Driving, Etc.


Paper Title



Enhancing Diversity in Teacher-Student Networks via Asymmetric branches for Unsupervised Person Re-identification

Hao Chen (INRIA)*; Benoit Lagadec (European System Integration); Francois Bremond (Inria Sophia Antipolis, France)


Subject Guided Eye Image Synthesis with Application to Gaze Redirection

Harsimran Kaur (University of California, Santa Cruz)*; Roberto Manduchi (University of California Santa Cruz)


Facial Emotion Recognition with Noisy Multi-task Annotations

Siwei Zhang (ETH Zurich)*; Zhiwu Huang (ETH Zurich); Danda Pani Paudel (ETH Zürich); Luc Van Gool (ETH Zurich)


Relighting Images in the Wild with Self-Supervised Siamese Auto-Encoder

Yang Liu (Microsoft)*; Alexandros Neophytou (Microsoft); Sunando Sengupta (Microsoft); Eric Sommerlade (Microsoft)


Audio- and Gaze-driven Facial Animation of Codec Avatars

Alexander Richard (Facebook Reality Labs)*; Colin Lea (Facebook); Shugao Ma (Facebook); Jürgen Gall (University of Bonn); Fernando De la Torre (Facebook); Yaser Sheikh (Facebook Reality Labs)


Driving among Flatmobiles: Bird-Eye-View occupancy grids from a monocular camera for holistic trajectory planning

abdelhak loukkal (Renault S.A.S/UTC)*; Yves Grandvalet (CNRS / UTC); Tom Drummond (Monash University); You Li (Renault S.A.S)


SynDistNet: Self-Supervised Monocular Fisheye Camera Distance Estimation Synergized with Semantic Segmentation for Autonomous Driving

Varun Ravi Kumar (Valeo); Marvin Klingner (Technische Universität Braunschweig ); Senthil Yogamani (Valeo Vision Systems)*; Stefan Milz ( / Ilmenau University); Tim Fingscheidt ( Technische Universität Braunschweig); Patrick Maeder (Technische Universität Ilmenau)


Guided Attentive Feature Fusion for Multispectral Pedestrian Detection

Heng ZHANG (Univ Rennes 1)*; Elisa Fromont (Université Rennes 1, IRISA/INRIA rba); Sébastien Lefèvre (Université de Bretagne Sud / IRISA); Bruno AVIGNON (Atermes)


Temporally Consistent 3D Human Pose Estimation Using Dual 360° Cameras

Matthew Shere (CVSSP - University Of Surrey)*; Hansung Kim (University Of Southampton); Adrian Hilton (University of Surrey)


Driver Anomaly Detection: A Dataset and Contrastive Learning Approach

Okan Köpüklü (Technical University of Munich)*; Jiapeng Zheng (Technical University of Munich); Hang Xu (Technical University of Munich); Gerhard Rigoll (Institute for Human-Machine Communication, TU Munich, Germany)

Oral 1B : 3D, Domain Adaptation, Video, Etc.


Adaptiope: A Modern Benchmark for Unsupervised Domain Adaptation

Tobias Ringwald (Karlsruhe Institute of Technology)*; Rainer Stiefelhagen (Karlsruhe Institute of Technology)


H2O-Net: Self-Supervised Flood Segmentation via Adversarial Domain Adaptation and Label Refinement

Peri Akiva (Rutgers University)*; Matthew Purri (Rutgers University); Kristin Dana (Rutgers University); Beth Tellman (Cloud to Street); Tyler Anderson (Cloud to Street)


Self-supervised Learning for Domain Adaptation on Point-Clouds

Idan Achituve (Bar-Ilan University)*; Haggai Maron (NVIDIA Research); Gal Chechik (Bar Ilan University)


Continuous Geodesic Convolutions for Learning on 3D Shapes

Zhangsihao Yang (Carnegie Mellon University); Srinath Sridhar (Brown University); Tolga Birdal (Siemens AG); Leonidas Guibas (Stanford University); Or Litany (NVIDIA)*


Identity Unbiased Deception Detection by 2D-to-3D Face Reconstruction

Minh Le Ngo (University of Amsterdam)*; Wei Wang (University of Amsterdam); Burak Mandira (Bilkent University); Sezer Karaoglu (University of Amsterdam); Henri Bouma (TNO); Hamdi Dibeklioglu (Bilkent University); Theo Gevers (University of Amsterdam)


Supervoxel Attention Graphs for Long-Range Video Modeling

Yang Wang (Stony Brook University)*; Gedas Bertasius (Facebook AI); Tae-Hyun Oh (POSTECH); Abhinav Gupta (CMU/FAIR); Minh Hoai Nguyen (Stony Brook University); Lorenzo Torresani (Dartmouth College)


Intro and Recap Detection for Movies and TV Series

Xiang Hao (Amazon)*; Kripa Chettiar (Amazon); Ben Cheung (Amazon); Vernon Germano (Amazon); Raffay Hamid (Amazon)


Representation learning from videos in-the-wild: An object-centric approach

Rob Romijnders (Google AI)*; Aravindh Mahendran (Google); Michael Tschannen (Google Brain); Josip Djolonga (Google AI, Zurich); Marvin Ritter (Google Brain); Neil Houlsby (Google); Mario Lucic (Google Brain)


Separable Four Points Fundamental Matrix

Gil Ben-Artzi (Ariel University)*


SSGP: Sparse Spatial Guided Propagation for Robust and Generic Interpolation

René Schuster (DFKI)*; Oliver Wasenmüller (DFKI); Christian Unger (BMW); Didier Stricker (DFKI)

Oral 1C: Synthesis, Reconstruction, Recognition, Learning


RarePlanes: Synthetic Data Takes Flight

Jacob Shermeyer (CosmiQ Works, In-Q-Tel)*; Thomas Hossler (AI.Reverie); Adam Van Etten (In-Q-Tel); Daniel Hogan (CosmiQ Works, In-Q-Tel); Ryan S Lewis (IQT CosmiQ Works); Daeil Kim (AI.Reverie)


Spatially Aware Metadata for Raw Reconstruction

Abhijith Punnappurath (Samsung AI Center Toronto)*; Michael S Brown (York University)


Saliency Driven Perceptual Image Compression

Yash Patel ( Czech Technical University in Prague)*; Srikar Appalaraju (Amazon); R. Manmatha (Amazon)


Text-to-Image Generation Grounded by Fine-Grained User Attention

Jing Yu Koh (Google Research)*; Jason Baldridge (Google Inc.); Honglak Lee (Google / U. Michigan); Yinfei Yang (Google Research)


A Deep Temporal Fusion Framework for Scene Flow Using a Learnable Motion Model and Occlusions

René Schuster (DFKI)*; Christian Unger (BMW); Didier Stricker (DFKI)


Conflicting Bundles: Adapting Architectures Towards the Improved Training of Deep Neural Networks

David Peer (University of Innsbruck)*; Sebastian Stabinger (University of Innsbruck); Antonio J Rodriguez-Sanchez (University of Innsbruck)


Subsurface Pipes Detection Using DNN-based Back Projection on GPR Data

JInglun Feng (The City College of New York)*; Liang Yang (The City College Of New York); Haiyan Wang (The City College of New York); YingLi Tian (City University of New York); Jizhong Xiao (City College, City University of New York)


TrustMAE: A Noise-Resilient Defect Classification Framework using Memory-Augmented Auto-Encoders with Trust Regions

Daniel Stanley Tan (National Taiwan University of Science and Technology)*; Yi-Chun Chen (National Tsing Hua University); Trista Pei-chun Chen (Inventec Corporation); Wei-Chao Chen (Skywatch Inc. and Inventec Inc.)


From generalized zero-shot learning to long-tail with class descriptors

Dvir Samuel (Bar-Ilan University)*; Yuval Atzmon (NVIDIA Research); Gal Chechik (Bar Ilan University)


Compositional Embeddings for Multi-Label One-Shot Learning

Zeqian Li (Worcester Polytechnic Institute)*; Michael C Mozer (Google Research / University of Colorado); Jacob Whitehill (Worcester Polytechnic Institute)

Oral 2A: Segmentation, Image Manipulation, Image Processing


Deep Interactive Thin Object Selection

Jun Hao Liew (NUS)*; Scott Cohen (Adobe Research); Brian Price (Adobe); Long T Mai (Adobe Research); Jiashi Feng (NUS)


QuadroNet: Multi-task Learning for Real-Time Semantic & Depth Aware Instance Segmentation

Kratarth Goel (Zoox Labs Inc)*; Praveen Srinivasan (Zoox); Sarah Tariq (Zoox); James Philbin (Zoox)


Ensembling Low Precision Models for Binary Biomedical Image Segmentation

Tianyu Ma (Cornell University )*; HANG Zhang (Cornell University); Hanley Ong (Weill Cornell); Amar Vora (Weill Cornell); Thanh D. Nguyen (Cornell University); Ajay Gupta (Weill Cornell); Yi Wang (Cornell University); Mert Sabuncu (Cornell)


SliceNets --- A Scalable Approach for Object Detection in 3D CT Scans

Anqi Yang (Carnegie Mellon University)*; Feng Pan (IDSS Corporation); Vishwanath Saragadam Raja Venkata (Rice University); Duy Dao (IDSS Corporation); ZHUO HUI (Facebook Inc); Jen-Hao Chang (Carnegie Mellon University); Aswin Sankaranarayanan (Carnegie Mellon University)


DANCE: A Deep Attentive Contour Model for Efficient Instance Segmentation

Zichen Liu (National University of Singapore)*; Jun Hao Liew (NUS); Xiangyu Chen (Shopee); Jiashi Feng (NUS)


Hierarchical Generative Adversarial Networks for Single Image Super-Resolution

Weimin Chen (NetEase Fuxi AI Lab)*; Yuqing Ma (BUAA); Xianglong Liu (Beihang University); Yi Yuan (NetEase Fuxi AI Lab)


Deep Image Compositing

He Zhang (Adobe)*; Jianming Zhang (Adobe Research); federico perazzi (facebook); Zhe Lin (Adobe Research); Vishal Patel (Johns Hopkins University)


CAT-Net: Compression Artifact Tracing Network for Detection and Localization of Image Splicing

Myung-Joon Kwon (KAIST)*; IN JAE YU (KAIST); Seung-Hun Nam (Korea advanced institute of science and technology (KAIST)); Heung-Kyu Lee (Korea Advanced Institute of Science and Technology (KAIST) )


Towards Enhancing Fine-grained Details for Image Matting

Chang Liu (Nanyang Technological University)*; Henghui Ding (Nanyang Technological University); Xudong Jiang (Nanyang Technological University)


EAGLE-Eye: Extreme-pose Action Grader using detaiL bird’s-Eye view

Mahdiar Nekoui (University of Alberta)*; Fidel Omar Tito Cruz (Universidad Nacional de Ingeniería); Li Cheng (ECE dept., University of Alberta)


Robust Lensless Image Reconstruction via PSF Estimation

Joshua D Rego (Arizona State University)*; Karthik Kulkarni (Arizona State University); Suren Jayasuriya (Arizona State University)


Domain-Aware Unsupervised Hyperspectral Reconstruction for Aerial Image Dehazing

Aditya Mehta (Birla Institute of Technology and Science, Pilani, Pilani Campus); Harsh Sinha (Birla Institute of Technology and Science, Pilani, Pilani Campus); Murari Mandal (National University of Singapore)*; Pratik Narang (Birla Institute of Technology and Science, Pilani, Pilani Campus)


SWAG: Superpixels Weighted by Average Gradients for Explanations of CNNs

Thomas Hartley (Cardiff University)*; Kirill Sidorov (Cardiff University); Chris Willis (BAE); David Marshall (Cardiff University)


Few-shot Font Style Transfer between Different Languages

Chenhao Li (Kyushu University)*; Yuta Taniguchi (Kyushu University); Min Lu (Kyushu University); Shin'ichi Konomi (Kyushu University)


Size-invariant Detection of Marine Vessels from Visual Time Series

Tunai Porto Marques (University of Victoria )*; Alexandra Branzan Albu (University of Victoria); Patrick O'Hara (Canadian Wildlife Service, Environment and Climate Change Canada); Norma Serra (University Of Victoria); Ben Morrow (University Of Victoria); Lauren McWhinnie (Heriot-Watt University); Rosaline Canessa (University Of Victoria)

Oral 2B: Domain Adaptation, Saliency, Segmentation, Captioning, Tracking, Image Processing


Towards Fair Cross-Domain Adaptation via Generative Learning

Tongxin Wang (Indiana University)*; Zhengming Ding (Indiana University-Purdue University Indianapolis); Wei Shao (Indiana University); Haixu Tang (Indiana University); Kun Huang (Indiana University)


Set Augmented Triplet Loss for Video Person Re-Identification

Pengfei Fang (The Australian National University)*; Pan Ji (OPPO US Research Center); Lars Petersson (Data61/CSIRO); Mehrtash Harandi (Monash University)


SoFA: Source-data-free Feature Alignment for Unsupervised Domain Adaptation

Hao-Wei Yeh (The University of Tokyo)*; Baoyao Yang (Department of Computer Science, Hong Kong Baptist University); PongChi Yuen (Department of Computer Science, Hong Kong Baptist University); Tatsuya Harada (The University of Tokyo / RIKEN)


Saliency Prediction with External Knowledge

Yifeng Zhang (University of Minnesota, Twin Cities)*; Ming Jiang (University of Minnesota); Qi Zhao (University of Minnesota)


Revisiting Batch Normalization for Improving Corruption Robustness

Philipp Benz (KAIST)*; Chaoning Zhang (KAIST); Adil Karjauv (KAIST); In So Kweon (KAIST)


RODNet: Radar Object Detection using Cross-Modal Supervision

Yizhou Wang (University of Washington)*; Zhongyu Jiang (University of Washington); Xiangyu Gao (University of Washington); Jenq-Neng Hwang (University of WA�); Guanbin Xing (University of Washington); Hui Liu (University of Washington)


Context-Aware Domain Adaptation in Semantic Segmentation

JINYU YANG (The University of Texas at Arlington)*; weizhi an (UTA); Chaochao Yan (University of Texas at Arlington); Peilin Zhao (Tencent AI Lab); Junzhou Huang (University of Texas at Arlington)


Variational Prototype Inference for Few-Shot Semantic Segmentation

haochen wang (Beihang University)*; Yandan Yang (Beihang University); Xianbin Cao (Beihang University, China); Xiantong Zhen (University of Amsterdam); Cees Snoek (University of Amsterdam); Ling Shao (Inception Institute of Artificial Intelligence)


Only Time Can Tell: Discovering Temporal Data for Temporal Modeling

Laura Sevilla-Lara (Facebook)*; Shengxin Zha (Facebook); Zhicheng Yan (Facebook AI); Vedanuj Goswami (Facebook AI Research); Matt Feiszli (Facebook Research); Lorenzo Torresani (Facebook AI)


Self-Distillation for Few-Shot Image Captioning

Xianyu Chen (University of Minnesota, Twin Cities); Ming Jiang (University of Minnesota); Qi Zhao (University of Minnesota)*


Defense-friendly Images in Adversarial Attacks: Dataset and Metrics for Perturbation Difficulty

Camilo Andres Pestana (The University of Western Australia)*; Wei Liu (University of Western Australia); David Glance (University of Western Australia); Ajmal Mian (University of Western Australia)


MART: Motion-Aware Recurrent Neural Network for Robust Visual Tracking

Heng Fan (Stony Brook University); Haibin Ling (Stony Brook University)*


Multimodal Humor Dataset: Predicting Laughter tracks for Sitcoms

Badri Patro (IIT Kanpur)*; Mayank Lunayach (IIT Kanpur); Deepankar Srivastava (IIT Kanpur); Sarvesh - (IIT Kanpur); Hunar Preet Singh (IIT Kanpur); Vinay Namboodiri (University of Bath)


Class-wise Metric Scaling for Improved Few-Shot Classification

Ge Liu (Shanghai Jiao Tong University)*; Linglan Zhao (Shanghai Jiao Tong University); Wei Li (Shanghai Jiao Tong University); Da-shan Guo (Shanghai Jiao Tong University); Xiangzhong Fang (Shanghai Jiao Tong University)


High-quality Frame Interpolation via Tridirectional Inference

Jinsoo Choi (KAIST)*; Jaesik Park (POSTECH); In So Kweon (KAIST)

Oral 2C: Domain Adaptation, Representation, Visual Analytics, Uncertainty and Attention


Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptation

Taotao Jing (Tulane University); Zhengming Ding (Indiana University-Purdue University Indianapolis)*


Domain Impression: A Source Data Free Domain Adaptation Method

Vinod Kumar Kurmi (IIT Kanpur)*; K. S. Venkatesh (IIT Kanpur); Vinay P Namboodiri (IIT Kanpur)


IncreACO: Incrementally Learned Automatic Check-out with Photorealistic Exemplar Augmentation

Yandan Yang (Beihang University); Lu Sheng (Beihang University)*; Xiaolong Jiang (Alibaba Youku Cognitive and Intelligent Lab); haochen wang (Beihang University); Dong Xu (University of Sydney); Xianbin Cao (Beihang University, China)


Adversarial Reinforcement Learning for Unsupervised Domain Adaptation

Youshan Zhang (Lehigh University)*; Hui Ye (Georgia State University); Brian D. Davison (Lehigh University)


Representation Learning Through Latent Canonicalizations

Or Litany (NVIDIA)*; Ari S Morcos (Facebook AI Research (FAIR)); Srinath Sridhar (Brown University); Leonidas Guibas (Stanford University); Judy Hoffman (Georgia Tech)


Meta Module Network for Compositional Visual Reasoning

Wenhu Chen (University of California, Santa Barbara)*; Zhe Gan (Microsoft); Linjie Li (Microsoft); Yu Cheng (Microsoft); William Yang (UCSB); Jingjing Liu (Microsoft)


Data-efficient Alignment of Multimodal Sequences by Aligning Gradient Updates and Internal Feature Distributions

Jianan Wang (Fudan University); Boyang Li (Nanyang Technological University)*; Xiangyu Fan (Fudan University); Jing Lin (Fudan University); Yanwei Fu (Fudan University)


Keypoint-Aligned Embeddings for Image Retrieval and Re-identification

Olga Moskvyak (Queensland University of Technology)*; Frederic Maire (Queensland University of Technology); Feras Dayoub (Queensland University of Technology); Mahsa Baktashmotlagh (University of Queensland)


Deep Poisoning: Towards Robust Image Data Sharing against Visual Disclosure

Hao Guo (University of South Carolina)*; Brian Dolhansky (Facebook); Eric Hsin (Facebook); Phong Dinh (Facebook); Canton Cristian (Facebook AI); Song Wang (University of South Carolina)


Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context

Xinyi Zheng (University of Michigan, Ann Arbor, Michigan); Doug Burdick (IBM Research); Lucian Popa (IBM Almaden Research Center); Xu Zhong (IBM Research Australia); Nancy X.R. Wang (IBM Research - Almaden)*


Real-Time Uncertainty Estimation in Computer Vision via Uncertainty-Aware Distribution Distillation

Yichen Shen (Samsung)*; Zhilu Zhang (Cornell University); Mert Sabuncu (Cornell); Lin Sun (Samsung, Stanford, HKUST)


Auxiliary Tasks for Efficient Learning of Point-Goal Navigation

Saurabh Satish Desai (Oregon State University)*; Stefan Lee (Oregon State University)


Self Supervision for Attention Networks

Badri Patro (IIT Kanpur)*; Kasturi G S (Netaji Subhas University of Technology); Ansh Jain (Netaji Subhas University of Technology); Vinay Namboodiri (University of Bath)


Do not Forget to Attend to Uncertainty while Mitigating Catastrophic Forgetting

Vinod Kumar Kurmi (IIT Kanpur)*; Badri Patro (IIT Kanpur); K. S. Venkatesh (IIT Kanpur); Vinay P Namboodiri (IIT Kanpur)


Overcomplete Deep Subspace Clustering Networks

Jeya Maria Jose Valanarasu (Johns Hopkins University)*; Vishal Patel (Johns Hopkins University)

Oral 3A: Rectification and Tracking, 3D and Action, Motion and Tracking


Revisiting Street-to-Aerial View Image Geo-localization and Orientation Estimation

Sijie Zhu (University of North Carolina at Charlotte); Taojiannan Yang (University of North Carolina at Charlotte); Chen Chen (University of North Carolina at Charlotte)*


Let's Get Dirty: GAN Based Data Augmentation for Camera Lens Soiling Detection in Autonomous Driving

Michal Uricar (Valeo); Ganesh Sistu (Valeo Vision Systems); Hazem Rashed (Valeo); Antonin Vobecky (Valeo); Varun Ravi Kumar (Valeo); Pavel Krizek (Valeo); Fabian Bürger (Valeo); Senthil Yogamani (Valeo Vision Systems)*


A Learning-Based Approach to Parametric Rotoscoping of Multi-Shape Systems

Nadine Dabby (Intel Corp.)*; Luis Bermudez (Intel Corp.); Yingxi Adelle Lin ( n/a); Sara Hilmarsdottir (n/a); Narayan Sundararajan (Intel Corp.); Swarnendu Kar (Intel Corp.)


Splatty- A Unified Image demosaicing and Rectification Method

Pranav Verma (UC San Diego)*; Dominique E Meyer (UC San Diego); Falko Kuester (UC San Diego)


Goal-driven Long-Term Trajectory Prediction

Hung Tran (Deakin University)*; Vuong Le (Deakin University); Truyen Tran (Deakin University)


DeepCSR: A 3D Deep Learning Approach for Cortical Surface Reconstruction

Rodrigo Santa Cruz (CSIRO)*; Leo Lebrat (CSIRO); Pierrick Bourgeat (CSIRO); Clinton Fookes (Queensland University of Technology); Jurgen Fripp (Australian e-Health Research Centre); Olivier Salvado (Australian e-Health Research Centre)


Attention-Based Spatial Guidance for Image-to-Image Translation

Yu Lin (University of Texas at Dallas)*; Yigong Wang (University of Texas at Dallas); Yi-Fan Li (University of Texas at Dallas); Yang Gao (University of Texas at Dallas); ZHUOYI WANG (University of Texas at Dallas); Latifur Khan (The university of Texas at Dallas)


Triangle-Net: Towards Robustness in Point Cloud Learning

Chenxi Xiao (Purdue University)*; Juan Wachs (Purdue University)


MVHM: A Large-Scale Multi-View Hand Mesh Benchmark for Accurate 3D Hand Pose Estimation

Liangjian Chen (University of California, Irvine)*; Shih-Yao Lin (Tencent America); Yusheng Xie (Amazon); Yen-Yu Lin (National Chiao Tung University); Xiaohui Xie (University of California, Irvine)


The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose

Yizhak Ben-Shabat (ANU)*; Xin Yu (University of Technology Sydney); Fatemeh Sadat Saleh (Australian National University (ANU)); Dylan Campbell (Australian National University); Cristian Rodriguez (Australian National University); HONGDONG LI (Australian National University, Australia); Stephen Gould (Australian National University, Australia)


Visual tracking of deepwater animals using machine learning-controlled robotic underwater vehicles

Kakani Katija (Monterey Bay Aquarium Research Institute)*; Paul Roberts (Monterey Bay Aquarium Research Institute); Benjamin Woodward (CVision AI); Jonathan Takahashi (CVision AI); Michael Risi (Monterey Bay Aquarium Research Institute); Kevin Barnard (Monterey Bay Aquarium Research Institute); Alexandra Lapides (Monterey Bay Aquarium Research Institute); Joost Daniels (Monterey Bay Aquarium Research Institute); Ben Ranaan (Monterey Bay Aquarium Research Institute)


Class-agnostic Few-shot Object Counting

SHUO-DIAO YANG (National Taiwan University)*; Hung-Ting Su (National Taiwan University); Winston H. Hsu (National Taiwan University); Wen-Chin Chen (National Taiwan University)


GlocalNet: Class-aware Long-term Human Motion Synthesis

Neeraj Battan (IIIT Hyderabad); Yudhik Agrawal ( IIIT Hyderabad)*; Sai Soorya Rao Veeravalli (IIIT Hyderabad); Aman Goel (IIIT Hyderabad); Avinash Sharma (CVIT, IIIT-Hyderabad)

Oral 3B: Detection and Recognition, Segmentation and Tracking, Low-level Vision


DualSANet: Dual Spatial Attention Network for Iris Recognition

Kai Yang (SenseTime Research)*; Zihao Xu (Tongji University); Jingjing Fei (Tongji University)


Learning to Distill Convolutional Features into Compact Local Descriptors

Jongmin Lee (POSTECH)*; Yoonwoo Jeong (POSTECH); Seungwook Kim (POSTECH); Juhong Min (POSTECH); Minsu Cho (POSTECH)


Disentangled Contour Learning for Quadrilateral Text Detection

Yanguang Bi (SenseTime Research); Zhiqiang Hu (SenseTime Research)*


Class-agnostic Object Detection

Ayush Jaiswal ( Inc.)*; Yue Wu ( Inc.); Pradeep Natarajan ( Inc.); Prem Natarajan (Amazon)


The Devil is in the Boundary: Exploiting Boundary Representation for Basis-based Instance Segmentation

Myungchul Kim (KAIST)*; Sanghyun Woo (KAIST); Dahun Kim (KAIST); In So Kweon (KAIST)


Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation

Hao Tang (University of California Irvine)*; Xingwei Liu (University of California Irvine); Shanlin Sun (DeepVoxel Inc.); Kun Han (University of California Irvine); Xuming Chen (Shanghai Jiao Tong University School of Medicine); Narisu Bai (DeepVoxel Inc.); Huang Qian (Shanghai Jiao Tong University School of Medicine); Yong Liu (Shanghai Jiao Tong University School of Medicine); Xiaohui Xie (University of California, Irvine)


Asymmetric Contextual Modulation for Infrared Small Target Detection

Yimian Dai (Nanjing University of Aeronautics and Astronautics)*; Yiquan Wu (Nanjing University of Aeronautics and Astronautics); Fei Zhou (Nanjing University of Aeronautics and Astronautics); Kobus Barnard (University of Arizona)


CAP: Context-Aware Pruning for Semantic Segmentation

Wei He (Nanyang Technological University)*; Meiqing Wu (Nanyang Technological University Singapore); Mingfu Liang (Nanyang Technological University); Siew-Kei Lam (Nanyang Technological University)


TracKlinic: Diagnosis of Challenge Factors in Visual Tracking

Heng Fan (Stony Brook University); Fan Yang (Temple University); Peng Chu (Temple University); Yuewei Lin (Brookhaven National Laboratory); Lin Yuan (Amazon); Haibin Ling (Stony Brook University)*


Video Captioning of Future Frames

Mehrdad Hosseinzadeh (University of Manitoba)*; Yang Wang (University of Manitoba; Huawei Technologies Canada)


AutoRetouch: Automatic Professional Face Retouching

Alireza Shafaei (The University of British Columbia)*; Jim Little (University of British Columbia, Canada); Mark Schmidt (University of British Columbia)


StressNet: Detecting Stress in Thermal Videos

Satish Kumar (University of California, Santa Barbara)*; A S M Iftekhar (University of California Santa Barbara); Michael Goebel (University of California, Santa Barbara); Tom Bullock (University of California Santa Barbara); Mary Maclean (University of California, Santa Barbara); Mike Miller (University of California Santa Barbara); Tyler Santander (University of California, Santa Barbara); Barry Giesbrecht (University of California Santa Barbara); Scott Grafton (University of California Santa Barbara); B.S. Manjunath (University of California, Santa Barbara)


Where to Look?: Mining Complementary Image Regions for Weakly Supervised Object Localization

Sadbhavana M Babar (Indian Institute of Technology, Madras)*; Sukhendu Das (Indian Institute of Technology, Madras)


Weakly Supervised Instance Segmentation by Deep Community Learning

Jaedong Hwang (Seoul National University)*; SEOHYUN KIM (Seoul National University); Jeany Son (ETRI); Bohyung Han (Seoul National University)


Unsupervised Multimodal Video-to-Video Translation via Self-Supervised Learning

Kangning Liu (New York University)*; Shuhang Gu (ETH Zurich, Switzerland); Andres Felipe Romero Vergara (); Radu Timofte (ETH Zurich)

Oral 3C: 3D, Video Processing, Detection and Recognition


Cinematic-L1 Video Stabilization with a Log-Homography Model

Arwen Bradley (Apple Inc.)*; Jason Klivington (Apple Inc.); Joseph Triscari (Apple Inc.); Rudolph van der Merwe (Apple Inc.)


Temporal-Aware Self-Supervised Learning for 3D Hand Pose and Mesh Estimation in Videos

Liangjian Chen (University of California, Irvine)*; Shih-Yao Lin (Tencent America); Yusheng Xie (Amazon); Yen-Yu Lin (National Chiao Tung University); Xiaohui Xie (University of California, Irvine)


MEVA: A Large-Scale Multiview, Multimodal Video Dataset for Activity Detection

Kellie N Corona (Kitware Inc.)*; Katie Osterdahl (Kitware inc. ); Roddy Collins (Kitware Inc. ); Anthony Hoogs (Kitware)


Integrating Human Gaze into Attention for Egocentric Activity Recognition

Kyle Min (University of Michigan)*; Jason J Corso (University of Michigan)


DORi: Discovering Objects Relationship for Temporal Moment Localization of a Natural-Language Query in Video

Cristian Rodriguez (Australian National University)*; Edison Marrese-Taylor (The University of Tokyo); Basura Fernando (Agency for Science, Technology and Research, A*STAR, Singapore); HONGDONG LI (Australian National University, Australia); Stephen Gould (Australian National University, Australia)


Real-time Localized Photorealistic Video Style Transfer

XIDE XIA (Boston University)*; Tianfan Xue (Google); Wei-Sheng Lai (Google); Zheng Sun (Google); Abby Chang (Google); Brian Kulis (Boston University and Amazon); Jiawen Chen (Google)


Revisiting Adaptive Convolutions for Video Frame Interpolation

Simon Niklaus (Adobe Research)*; Long T Mai (Adobe Research); Oliver Wang (Adobe Systems Inc)


VideoSSL : Semi-supervised learning for video classification

Longlong Jing (The City University of New York)*; Toufiq Parag (Comcast); Zhe Wu (University of Maryland); YingLi Tian (City University of New York); Hongcheng Wang (Comcast)


Towards Visually Explaining Video Understanding Networks with Perturbation

Zhenqiang Li (The University of Tokyo)*; Weimin Wang (AIST); Zuoyue Li (ETH Zurich); Yifei Huang (The University of Tokyo); Yoichi Sato (University of Tokyo)


How to Make a BLT Sandwich? Learning VQA towards Understanding Web Instructional Videos

Shaojie Wang (Washington University in St. Louis)*; Wentian Zhao (Adobe); Ziyi Kou (University of Notre Dame); Jing Shi (university of rochester); Chenliang Xu (University of Rochester)


Compositional Learning of Image-Text Query for Image Retrieval

Muhammad Umer Anwaar (TUM)*; Egor Labintcev (Mercateo); Martin Kleinsteuber (Mercateo)


Regional Attention Networks with Context-aware Fusion for Group Emotion Recognition

AHMED-SHEHAB KHAN (University of South Carolina)*; Zhiyuan Li (University of South Carolina); Jie Cai (InnoPeak Technology, Inc.); Yan Tong (University of South Carolina)


Effective Fusion Factor in FPN for Tiny Object Detection

Yuqi Gong (University of Chinese Academy of Sciences); Xuehui Yu (University of Chinese Academy of Sciences); Yao Ding (University of Chinese Academy of Sciences); Xiaoke Peng (University of Chinese Academy of Sciences); Jian Zhao (Institute of North Electronic Equipment); Zhenjun Han (University of Chinese Academy of Sciences)*


Adaptive Privacy Preserving Deep Learning Algorithms for Medical Data

Xinyue Zhang (University of Houston)*; Jiahao Ding (University of Houston); Maoqiang Wu (Guangdong University of Technology); Stephen Wong (Weill Cornell Medical College); Hien V Nguyen (University of Houston); Miao Pan (University of Houston)


CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing

Ajian Liu (MUST); Zichang Tan (NLPR); Jun Wan (NLPR, CASIA)*; Sergio Escalera (Computer Vision Center (UAB) & University of Barcelona,); Guodong Guo (Baidu); Stan Z. Li (Westlake University)

Date: Thursday, January 7, 2021 

Oral 4A: Face, Head, Action, GANs


A Vector-based Representation to Enhance Head Pose Estimation

Zhiwen Cao (Purdue University)*; Zongcheng Chu (Purdue University); Dongfang Liu (Purdue University); Yingjie Chen (Purdue University)


Continual Representation Learning for Biometric Identification

Bo Zhao (The University of Edinburgh)*; Shixiang Tang (The University of Sydney); Dapeng Chen (Sensetime Group Limited); Hakan Bilen (University of Edinburgh); Rui Zhao (SenseTime Group Limited)


Exploiting Spatial Relation for Reducing Distortion in Style Transfer

Jia-Ren Chang (National Chiao Tung University; aetherAI)*; Yong-Sheng Chen (National Chiao Tung University)


Seeing Through your Skin: Recognizing Objects with a Novel Visuotactile Sensor

Francois R Hogan (Samsung Electronics)*; Michael Jenkin (Samsung); Sahand Rezaei-Shoshtari (Samsung); Yogesh Girdhar (Samsung); David Meger (Samsung); Gregory Dudek (McGill University)


Detecting Human-Object Interaction with Mixed Supervision

Suresh Kirthi Kumaraswamy (IRISA/INRIA/University Le Mans)*; Miaojing Shi (King's College London); Ewa Kijak (IRISA)


Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences

Rosaura G VidalMata (University of Notre Dame)*; Walter Scheirer (University of Notre Dame); David Cox (MIT-IBM Watson AI Lab); Anna Kukleva (MPII); Hilde Kuehne (IBM)


Synthetic Expressions are Better Than Real for Learning to Detect Facial Actions

Koichiro Niinuma (FUJITSU LABORATORIES OF AMERICA, INC.)*; Itir Onal Ertugrul (Tilburg University); Jeffrey Cohn (University of Pittsburgh); Laszlo A Jeni (Carnegie Mellon University)


Benchmark for Evaluating Pedestrian Action Prediction

Iuliia Kotseruba (York University)*; Amir Rasouli (Huawei); John Tsotsos (York University)


SALAD: Self-Assessment Learning for Action Detection

Guillaume VAUDAUX-RUTH (Sorbonne université)*; adrien CHAN-HON-TONG (ONERA); Catherine Achard ()


Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognition

Zachary Wharton (Edge Hill University); Ardhendu Behera (Edge Hill University)*; Yonghuai Liu (Edge Hill University); Nik Bessis (Edge Hill University)


A Multi-Class Hinge Loss for Conditional GANs

Ilya Kavalerov (UMD)*; Wojciech Czaja (University of Maryland, College Park); Rama Chellappa (University of Maryland)


Improved Techniques for Training Single-Image GANs

Tobias Hinz (University of Hamburg)*; Matthew Fisher (Adobe Research); Oliver Wang (Adobe Systems Inc); Stefan Wermter (University of Hamburg)


SinGAN-GIF: Learning a Generative Video Model from a Single GIF

Rajat Arora (UC Davis)*; Yong Jae Lee (University of California, Davis)


This Face Does Not Exist... But It Might Be Yours! Identity Leakage in Generative Models

Patrick Tinsley (University of Notre Dame)*; Adam Czajka (University of Notre Dame); Patrick Flynn (University of Notre Dame)


FACEGAN: Facial Attribute Controllable rEenactment GAN

Soumya Tripathy (Tampere University of Technology)*; Juho Kannala (Aalto University, Finland); Esa Rahtu (Tampere University of Technology)

Oral 4B: Learning


Unsupervised Multi-Target Domain Adaptation Through Knowledge Distillation

Le Thanh Nguyen-Meidine (ETS Montreal)*; Eric Granger (ETS Montreal ); Atif Belal (Department of Computer Engineering, Aligarh Muslim University); Jose Dolz (ETS Montreal); Madhu Kiran (ETS Montreal); Louis-Antoine Blais-Morin (Genetec Inc.)


Unsupervised Meta-Domain Adaptation for Fashion Retrieval

Vivek Sharma (Harvard, MIT, KIT)*; Naila Murray (Naver Labs); Diane Larlus (Naver Labs Europe); Saquib Sarfraz (Karlsruhe Institute of Technology); Rainer Stiefelhagen (Karlsruhe Institute of Technology); Gabriela Csurka (Naver Labs Europe)


Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings

Marco Toldo (University of Padova)*; Umberto Michieli (University of Padova); Pietro Zanuttigh (University of Padova)


ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning

Viktor Olsson (Chalmers University of Technology); Wilhelm Tranheden (Chalmers University of Technology)*; Juliano T. A. L. Pinto (Chalmers University of Technology); Lennart Svensson (Chalmers University of Technology)


DACS: Domain Adaptation via Cross-domain Mixed Sampling

Wilhelm Tranheden (Chalmers University of Technology)*; Viktor Olsson (Chalmers University of Technology); Juliano T. A. L. Pinto (Chalmers University of Technology); Lennart Svensson (Chalmers University of Technology)


Domain-Adaptive Few-Shot Learning

An Zhao (Renmin University of China); Mingyu Ding (The University of Hong Kong); Zhiwu Lu (Renmin University of China)*; Tao Xiang (University of Surrey); Yulei Niu (Nanyang Technological University); Jiechao Guan (Renmin University of China); Ji-Rong Wen (Renmin University of China)


TResNet: High Performance GPU-Dedicated Architecture

Tal Ridnik (Alibaba)*; Hussam Lawen (Alibaba group); Asaf Noy (Alibaba); Emanuel Ben Baruch (Alibaba); Gilad Sharir (Alibaba Group); Itamar Friedman (Alibaba)


Exploiting the Redundancy in Convolutional Filters for Parameter Reduction

Kumara Kahatapitiya (Stony Brook University)*; Ranga Rodrigo (University of Moratuwa)


Covariance-free Partial Least Squares: An Incremental Dimensionality Reduction Method

Artur Jordão L Correia (UFMG)*; Maiko Lie (Federal University of Minas Gerais); Victor Hugo C. de Melo (Federal University of Minas Gerais); William R Schwartz (Federal University of Minas Gerais)


Effectiveness of Arbitrary Transfer Sets for Data-free Knowledge Distillation

Gaurav Kumar Nayak (Indian Institute of Science, Bangalore)*; Konda Reddy Mopuri (Indian Institute of Technology Tirupati); Anirban Chakraborty (Indian Institute of Science)


MeliusNet: An Improved Network Architecture for Binary Neural Networks

Joseph Bethge (Hasso Plattner Institute)*; Christian Bartz (Hasso Plattner Institute); Haojin Yang (Alibaba Group); Ying Chen (Alibaba Group); Meinel Christoph (Hasso Plattner Institut, Potsdam Germany)


Receptive Field Size Optimization with Continuous Time Pooling

Dora Babicz (Peter Pazmany Catholic Unviersity); Soma Kontar (Peter Pazmany Catholic Unviersity); Mark Peto (Peter Pazmany Catholic Unviersity); Andras Fulop (Peter Pazmany Catholic Unviersity); Gergely Szabo (Peter Pazmany Catholic Unviersity); Andras Horvath (Peter Pazmany Catholic University)*


Illumination Normalization by Partially Impossible Encoder-Decoder Cost Function

Steve Dias Da Cruz (IEE S.A.)*; Bertram Taetz (TU Kaiserslautern); Thomas Stifter (IEE S.A.); Didier Stricker (DFKI)


Multi-Loss Weighting with Coefficient of Variations

Rick Groenendijk (University of Amsterdam)*; Sezer Karaoglu (University of Amsterdam); Theo Gevers (University of Amsterdam); Thomas Mensink (Google Research / University of Amsterdam)


De-biasing Neural Networks with Estimated Offset for Class Imbalanced Learning

Byungju Kim (KAIST)*; Hyeong Gwon Hong (KAIST); Junmo Kim (KAIST)

Oral 4C: Objects, Detection, Segmentation


Automatic Object Recoloring Using Adversarial Learning

Siavash Khodadadeh (University of Central Florida)*; Saeid Motiian (Adobe); Zhe Lin (Adobe Research); Ladislau Boloni (University of Central Florida); Shabnam Ghadar (Adobe)


Weakly-supervised Object Representation Learning for Few-shot Semantic Segmentation

Xiaowen Ying (Lehigh University)*; Xin Li (Lehigh University); Mooi Choo Chuah (Lehigh University)


Deep Template-based Object Instance Detection

Jean-Philippe Mercier (Laval University)*; Mathieu Garon (Université Laval); Philippe Giguère (Laval University); Jean-Francois Lalonde (Université Laval)


Object Recognition with Continual Open Set Domain Adaptation for Home Robot

Ikki Kishida (The University of Tokyo)*; Hong Chen (The University of Tokyo); Masaki Baba (The University of Tokyo); Jiren Jin (The University of Tokyo); Ayako Amma (Toyota Motor Corporation); Hideki Nakayama (The University of Tokyo)


CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection

Ramin Nabati (University of Tennessee Knoxville)*; Hairong Qi (University of Tennessee-Knoxville)


Large datasets: A Pyrrhic win for computer vision?

Abeba Birhane (University College Dublin)*; Vinay Uday Prabhu (UnifyID AI Labs)


FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age for Bias Measurement and Mitigation

Kimmo Kärkkäinen (University of California, Los Angeles); Jungseock Joo (University of California Los Angeles)*


A Large-Scale, Time-Synchronized Visible and Thermal Face Dataset

Domenick Poster (WVU)*; Matthew Thielke (US Army Research Laboratory); Robert Nguyen (Booz Allen Hamilton); Srinivasan Rajaraman (Booz Allen Hamilton); Xing Di (Johns Hopkins University); Cedric A Nimpa Fondje (University of Nebraska-Lincoln); Nathan Short (Booz allen Hamilton); Benjamin Riggan (University of Nebraska-Lincoln); Vishal Patel (Johns Hopkins University); Nasser Nasrabadi (West Virginia University); Shuowen (Sean) Hu (ARL)


The MECCANO Dataset: Understanding Human-Object Interactions from Egocentric Videos in an Industrial-like Domain

Francesco Ragusa (University of Catania)*; Antonino Furnari (University of Catania); Salvo Livatino (); Giovanni Maria Farinella (University of Catania, Italy)


EDEN: Multimodal Synthetic Dataset of Enclosed GarDEN Scenes

Hoang-An Le (University of Amsterdam)*; Thomas Mensink (Google Research / University of Amsterdam); Partha Das (University of Amsterdam); Sezer Karaoglu (University of Amsterdam); Theo Gevers (University of Amsterdam)


Benefiting from Bicubically Down-Sampled Images for Learning Real-World Image Super-Resolution

Mohammad Saeed Rad (École Polytechnique Fédérale de Lausanne)*; Thomas Yu (École Polytechnique Fédérale de Lausanne); Claudiu Musat (Swisscom); Hazim Kemal Ekenel (EPFL); Behzad Bozorgtabar (EPFL); Jean-Philippe Thiran (École Polytechnique Fédérale de Lausanne)


A Unified Framework for Compressive Video Recovery from Coded Exposure Techniques

Prasan A Shedligeri (Indian Institute of Technology Madras)*; Anupama S (Qualcomm); Kaushik Mitra (IIT Madras)


Foreground color prediction through inverse compositing

Sebastian Lutz (Trinity College Dublin)*; Aljosa Smolic (Trinity College Dublin)


Foreground-aware Semantic Representations for Image Harmonization

Konstantin Sofiiuk (Samsung AI Center Moscow)*; Polina Popenova (Samsung AI Center Moscow); Anton S. Konushin (Lomonosov Moscow State University)


DualSR: Zero-Shot Dual Learning for Real-World Super-Resolution

Mohammad Emad (Eindhoven University of Technology)*; Maurice Peemen (Thermo Fisher Scientific); Henk Corporaal (TU Eindhoven)

Oral 5A: Motion, Classification, Recognition


Multi-Modal Trajectory Prediction of NBA Players

Sandro Hauri (Temple University)*; Nemanja Djuric (Uber ATG); Vladan Radosavljevic (Spotify); Slobodan Vucetic (Temple University)


Understanding the impact of mistakes on background regions in crowd counting

Davide Modolo (Amazon)*; Bing Shuai (Amazon); Rahul Rama Varior (Amazon); Joseph Tighe (Amazon)


Autonomous Tracking For Volumetric Video Sequences

Matthew Moynihan (Trinity College Dublin)*; Rafael Pagés (Volograms); Susana Ruano (Trinity College Dublin); Aljosa Smolic (Trinity College Dublin)


Unsupervised Video Representation Learning by Bidirectional Feature Prediction

Nadine Behrmann (Bosch Center for Artificial Intelligence)*; Jürgen Gall (University of Bonn); Mehdi Noroozi (Bosch Gmb)


Mask Selection and Propagation for Unsupervised Video Object Segmentation

Shubhika Garg (IIT Kharagpur)*; Vidit Goel (Indian Institute of Technology, Kharagpur)


Learning Data Augmentation with Online Bilevel Optimization for Image Classification

Saypraseuth Mounsaveng (ETS Montreal)*; Issam Hadj Laradji (Element AI); David Vazquez (Element AI); Ismail Ben Ayed (ETS Montreal); Marco Pedersoli (École de technologie supérieure)


Structured Visual Search via Composition-aware Learning

Mert Kilickaya (University of Amsterdam)*; Arnold W.M. Smeulders (University of Amsterdam)


Fusion Learning using Semantics and Graph Convolutional Network for Visual Food Recognition

Zhao Heng (Nanyang Technological Univeristy)*; Kim-Hui Yap (Nanyang Technological University); Alex Kot (Nanyang Technological University)


Kernel Self-Attention for Weakly-supervised Image Classification using Deep Multiple Instance Learning

Dawid Rymarczyk (Jagiellonian University)*; Adriana Borowa (Jagiellonian University); Jacek Tabor (Jagiellonian University); Bartosz Zieliński (Jagiellonian University)


Mutual Information Maximization on Disentangled Representations for Differential Morph Detection

Sobhan Soleymani (West Virginia University)*; Ali Dabouei (West Virginia university); Fariborz Taherkhani (West Virginia University); Jeremy Dawson (West Virginia University); Nasser Nasrabadi (West Virginia University)


Part Segmentation of Unseen Objects using Keypoint Guidance

Shujon Naha (Indiana University)*; Qingyang Xiao (Indiana University); Prianka Banik (Indiana University); Md Alimoor Reza (Indiana University); David Crandall (Indiana University)


Efficient Real-Time Radial Distortion Correction for UAVs

Marcus Valtonen Örnhag (Lund University)*; Patrik Persson (Lund University); Mårten Wadenbäck (Linköping University); Kalle Åström (Lund University); Anders Heyden (Lund University)

Oral 5B: 3D and Pose


SLAM in the Field: An Evaluation of Monocular Mapping and Localization on Challenging Dynamic Agricultural Environment

Fangwen Shu (DFKI)*; Paul Lesur (DFKI); Yaxu Xie (DFKI); A. Pagani (DFKI); Didier Stricker (DFKI)


Automatic Calibration of the Fisheye Camera for Egocentric 3D Human Pose Estimation from a Single Image

Yahui Zhang (University of Amsterdam)*; Shaodi You (); Theo Gevers (University of Amsterdam)


A Deflation based Fast and Robust Preconditioner for Bundle Adjustment

Shrutimoy Das (International Institute of Information Technology,Hyderabad); Siddhant Katyan (International Institute of Information Technology, Hyderabad); pawan kumar (IIIT, Hyderabad)*


MinkLoc3D: Point Cloud Based Large-Scale Place Recognition

Jacek Komorowski (Warsaw University of Technology)*


Multi Projection Fusion for Real-time Semantic Segmentation of 3D LiDAR Point Clouds

Yara Aly (Nile University); Karim M Amer (Nile University)*; Mohamed Ahmed Afifi (Nile University); Mohamed ElHelw (Nile University)


SMPLpix: Neural Avatars from 3D Human Models

Sergey Prokudin (MPI Intelligent Systems)*; Michael J. Black (Max Planck Institute for Intelligent Systems); Javier Romero (Amazon)


Dense 3D-Reconstruction from Monocular Image Sequences for Computationally Constrained UAS

Matthias Domnik (University of Applied Sciences and Arts Dortmund); Pedro Proenca (Jet Propulsion Laboratory); Jeff Delaune (Jet Propulsion Laboratory, California Institute of Technology); Jörg Thiem (University of Applied Sciences and Arts Dortmund); Roland Brockers (JPL)*


Dynamic Plane Convolutional Occupancy Networks

Stefan P Lionar (ETH Zurich); Dusan Svilarkovic (ETH Zurich); Daniil Emtsev (ETH); Songyou Peng (ETH Zurich and MPI-IS)*


Adaptive Streaming of 360-Degree Videos with Reinforcement Learning

Sohee Kim Park (Stony Brook University)*; Minh Hoai Nguyen (Stony Brook University); Arani Bhattacharya (IIIT DELHI); Samir Das (Stony Brook University)


Embedded Dense Camera Trajectories in Multi-Video Image Mosaics by Geodesic Interpolation-based Reintegration

Lars Haalck (University of Münster); Benjamin Risse (University of Münster)*


Pretraining boosts out-of-domain robustness for pose estimation

Alexander Mathis (Harvard University | EPFL)*; Thomas Biasi (Harvard); Mert Yüksekgönül (Bogazici University | Massachusetts Institute of Technology); Steffen Schneider (University of Tübingen); Byron Rogers (Performance Genetics); Matthias Bethge (University of Tübingen); Mackenzie Mathis (EPFL)


Making DensePose fast and light

Ruslan Rakhimov (Skoltech)*; Emil Bogomolov (Skoltech); Alexandr Notchenko (Skoltech); Fung Mao (Huawei Moscow Research Center (Russia)); Alexey Artemov (Skoltech); Denis Zorin (New York University); Evgeny Burnaev (Skoltech)


3DPoseLite: A Compact 3D Pose Estimation Using Node Embeddings

Meghal Dani (TCS Research); Ramya Hebbalaguppe (TCS Research)*; Karan Narain (TCS Research)


3D Human Pose and Shape Estimation Through Collaborative Learning and Multi-view Model-fitting

Zhongguo Li (Lund University)*; Magnus Oskarsson (Lund University); Anders Heyden (Lund University)


Fast Pose Graph Optimization via Krylov-Schur and Cholesky Factorization

Gabriel Moreira (Instituto Superior Técnico)*; Manuel Marques (Instituto Superior Tecnico, Portugal); Joao Paulo Costeira (Instituto Superior Tecnico)

Oral 5C: Applications


Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows

Marco Rudolph (Leibniz University Hannover)*; Bastian Wandt (Leibniz University Hannover); Bodo Rosenhahn (Leibniz University Hannover)


ChartOCR: Data Extraction from Charts Images via a Deep Hybrid Framework

Junyu Luo (Pennstate University); Zekun Li (USC)*; Jinpeng Wang (Microsoft Research); Chin-Yew Lin (Microsoft Research Asia)


Visual Speech Enhancement Without A Real Visual Stream

Sindhu B Hegde (International Institute of Information Technology (IIIT) Hyderabad)*; Prajwal K R (International Institute of Information Technology, Hyderabad); Rudrabha Mukhopadhyay (IIIT Hyderabad); Vinay Namboodiri (University of Bath); C.V. Jawahar (IIIT-Hyderabad)


A Robust and Efficient Framework for Sports-Field Registration

Xiaohan Nie (amazon)*; Shixing Chen (Amazon); Raffay Hamid (Amazon)


Motion Adaptive Deblurring with Single-Photon Cameras

Trevor Seets (University of Wisconsin-Madison)*; Atul N Ingle (University of Wisconsin-Madison); Martin Laurenzis (French-German Research Institute of Saint-Louis (ISL)); Andreas Velten (University of Wisconsin - Madison)


TranstextNet: Transducing Text for Recognizing Unseen Visual Relationships

Gal Sadeh Kenigsfield (Technion)*; Ran El-Yaniv (Technion)


Automatic Quantification of Plant Disease from Field Image Data Using Deep Learning

Kanish Garg (Indian Institute of Technology, Delhi)*; Swati Bhugra (IIT Delhi); Prof. Brejesh Lall (IIT Delhi)


Interpretable and Trustworthy Deepfake Detection via Dynamic Prototypes

Loc Trinh (University of Southern California)*; Michael Y Tsang (University of Southern California); Sirisha Rambhatla (University of Southern California); Yan Liu (USC)


Automatic Open-World Reliability Assessment

Mohsen Jafarzadeh (University of Colorado Colorado Springs)*; Touqeer Ahmad (University of Colorado, Colorado Springs); Akshay Dhamija (Univ. Colorado Colorado Springs); Chunchun Li (VAST LAB ); Steve Cruz (University of Colorado Colorado Springs); Terrance E Boult (University of Colorado Colorado Springs)


Generating Physically Sound Training Data for Image Recognition of Additively Manufactured Parts

Tobias Nickchen (Paderborn University)*; Stefan Heindorf (Paderborn University); Gregor Engels (Paderborn University)


G2D: Generate to Detect Anomaly

Mohammad Sabokrou (Institute for Research in fundamental science (IPM))*; Hichem Snoussi (University of Troyes, France); Samir bouindour (University of Troyes); Bahram Mohammadi (Sharif University of Technology); Masoud Pourreza (HAMIM); Mostafa Khakighahjaverestani (IPM)


Assessing Image and Text Generation with Topological Analysis and Fuzzy Logic

Gonçalo F Mordido (Hasso Plattner Institute)*; Julian Niedermeier (Hasso Plattner Institute); Meinel Christoph (Hasso Plattner Institut, Potsdam Germany)


MSNet: A Multilevel Instance Segmentation Network for Natural Disaster Damage Assessment in Aerial Videos

Xiaoyu Zhu (Carnegie Mellon University)*; Junwei Liang (Carnegie Mellon University); Alexander Hauptmann (Carnegie Mellon University)


Single Image Reflection Removal with Edge Guidance, Reflection Classifier, and Recurrent Decomposition

Ya Chu Chang (National Chiao Tung University); Chia-Ni Lu (National Chiao Tung University )*; Chia-Chi Cheng (National Chiao Tung University); Wei-Chen Chiu (National Chiao Tung University)


Active Latent Space Shape Model: A Bayesian Treatment of Shape Model Adaptation with an Application to Psoriatic Arthritis Radiographs

Adwaye M Rambojun (University of Bath); William Tillett (University of Bath); Tony Shardlow (University of Bath); Neill Campbell (University of Bath)*

Oral 6A: Video and Computational Photography


Action Duration Prediction for Segment-Level Alignment of Weakly-Labeled Videos

Reza Ghoddoosian (University of Texas at Arlington)*; Saif Sayed (University of Texas at Arlington); Vassilis Athitsos (University of Texas at Arlington)


End-to-end Learning Improves Static Object Geo-localization from Video

Mohamed Chaabane (Colorado State University)*; Lionel Gueguen (Uber); Ameni Trabelsi (Colorado State University); Ross Beveridge (CSU); Stephen Ohara (Uber)


The Laughing Machine: Predicting Humor in Video

Yuta Kayatani (Osaka University); Zekun Yang (Osaka University); Mayu Otani (CyberAgent, Inc.); Noa Garcia (Osaka University); Chenhui Chu (Kyoto University); Yuta Nakashima (Osaka University)*; Haruo Takemura (Osaka University)


LoGAN: Latent Graph Co-Attention Network for Weakly-Supervised Video Moment Retrieval

Reuben Tan (Boston University)*; Huijuan Xu (University of California, Berkeley); Kate Saenko (Boston University); Bryan Plummer (Boston University)


DynaVSR: Dynamic Adaptive Blind Video Super-Resolution

SuYoung Lee (Seoul National University); Myungsub Choi (Seoul National University); Kyoung Mu Lee (Seoul National University)*


Legacy Photo Editing with Learned Noise Prior

Yuzhi Zhao (City University of Hong Kong)*; Po Lai Man (CITY UNIVERSITY OF HONG KONG); Tingyu Lin (City University of Hong Kong); Xuehui Wang (School of Data and Computer Science, Sun Yat-sen University); Kangcheng LIU (The Chinese University of Hong Kong); Yujia ZHANG (CITY UNIVERSITY OF HONG KONG); Wing Yin Yu (CITY UNIVERSITY OF HONG KONG); Pengfei Xian (CITY UNIVERSITY OF HONG KONG); Jingjing Xiong (CITY UNIVERSITY OF HONG KONG)


Deep Preset: Blending and Retouching Photos with Color Style Transfer

Man M. Ho (Hosei University); Jinjia Zhou (Hosei University)*


Painting Outside as Inside: Edge Guided Image Outpainting via Bidirectional Rearrangement with Progressive Step Learning

KyungHun Kim (Sogang University)*; Yeohun Yun (Sogang University); Keon-Woo Kang (Sogang University); kyeongbo kong (POSTECH); Siyeong Lee (NAVER LABS); Suk-Ju Kang (Sogang University)


Self-Supervised Poisson-Gaussian Denoising

Wesley Khademi (California Polytechnic State University); Sonia Rao (University of Georgia); Clare Minnerath (Providence College); Guy Hagen (University of Colorado Colorado Springs); Jonathan Ventura (California Polytechnic State University)*


Controllable and Progressive Image Extrapolation

Yijun Li (Adobe Research)*; Lu Jiang (Google Research); Ming-Hsuan Yang (University of California at Merced)

Oral 6B: Aerial Imagery and 3D, Vision and Language


Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors

Jingru Yi (Computer Science, Rutgers)*; Pengxiang Wu (Computer Science, Rutgers); Bo Liu (; Qiaoying Huang (Rutgers University); Hui Qu (Rutgers); Dimitris N. Metaxas (Rutgers)


Scale Aware Adaptation for Land-Cover Classification in Remote Sensing Imagery

Xueqing Deng (University of California, Merced)*; Yi Zhu (Amazon); Yuxin Tian (University of California, Merced); Shawn Newsam (UC Merced)


Learning to Generate Dense Point Clouds with Textures on Multiple Categories

Tao Hu (university of maryland)*; Geng Lin (University of Maryland, College Park); Zhizhong Han (University of Maryland, College Park); Matthias Zwicker (University of Maryland)


On the generalization of learning-based 3D reconstruction

Miguel Angel Bautista (Apple)*; Nitish Srivastava (Apple); Walter Talbott (Apple); Shuangfei Zhai (Apple); Joshua M Susskind (Apple)


SChISM: Semantic Clustering via Image Sequence Merging for Images of Human-Decomposition

Sara Mousavi (University of Tennessee, Knoxville)*; Dylan Lee (University of Tennessee, Knoxville); Tatianna Griffin (University of Tennessee, Knoxville); kelley cross (University of Tennessee, Knoxville); Dawnie Steadman (University of Tennessee); Audris Mockus (University of Tennessee, Knoxville)


DocVQA: A Dataset for VQA on Document Images

Minesh Mathew (CVIT, IIIT-Hyderabad)*; Dimosthenis Karatzas (Computer Vision Centre); C.V. Jawahar (IIIT-Hyderabad)


Utilizing Every Image Object for Semi-supervised Phrase Grounding

Haidong Zhu (University of Southern California)*; Arka Sadhu (University of Southern California); Zhaoheng Zheng (University of Southern California); Ram Nevatia (U of Southern California)


StacMR: Scene-Text Aware Cross Modal Retrieval

Andres Mafla (Computer Vision Centre)*; Rafael S Rezende (Naver Labs); Lluis Gomez (Universitat Autónoma de Barcelona); Diane Larlus (Naver Labs Europe); Dimosthenis Karatzas (Computer Vision Centre)


Local to Global: Efficient Visual Localization for a Monocular Camera

Sang Jun Lee (Naverlabs)*; Deokhwa Kim (Naverlabs); Sung Soo Hwang (Handong Global University); Donghwan Lee (NAVER LABS)

Oral 6C: Object Detection, Segmentation and 0/1-shot learning


Towards Zero-Shot Learning with Fewer Seen Class Examples

Vinay Kumar Verma (Duke University); Ashish Mishra (IIT Madras)*; Anubha Pandey (Indian Institute of Technology Madras); Hema A Murthy (IIT Madras); Piyush Rai (IIT Kanpur)


One-Shot Image Recognition Using Prototypical Encoders with Reduced Hubness

Chenxi Xiao (Purdue University)*; Naveen Madapana (Purdue University); Juan Wachs (Purdue University)


Learning of low-level feature keypoints for accurate and robust detection

Suwichaya Suwanwimolkul (KDDI Research, Inc. )*; Satoshi Komorita (KDDI Research, Inc.); Kazuyuki Tasaka (KDDI Research, Inc.)


Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Metrics and Baseline

Hazem Rashed (Valeo)*; Eslam Bakr (Valeo); Ganesh Sistu (Valeo Vision Systems); Varun Ravi Kumar (Valeo); Senthil Yogamani (Valeo Vision Systems); Ahmad ElSallab (Valeo Deep Learning Research); Ciaran Eising (University of Limerick)


Exploration of Spatial and Temporal Modeling Alternatives for HOI

Sai Praneeth Reddy Sunkesula (Indian Institute of Technology, Bombay)*; Rishabh Dabral (IIT Bombay); Srijon Sarkar (IIT Bombay); Ganesh Ramakrishnan (IIT Bombay)


Proposal Learning for Semi-Supervised Object Detection

Peng Tang (Salesforce Research)*; Chetan Ramaiah (Salesforce Research); Yan Wang (Johns Hopkins University); Ran Xu (Salesforce Research); Caiming Xiong (Salesforce Research)


Multi-frame Recurrent Adversarial Network for Moving Object Segmentation

Prashant Patil (IIT Ropar)*; Akshay A Dudhane (IIT Ropar); Subrahmanyam Murala (IIT Ropar)


Shape from semantic segmentation via the geometric Renyi divergence

Tatsuro Koizumi (University of York); William Smith (University of York)*


Alleviating Over-segmentation Errors by Detecting Action Boundaries

Yuchi Ishikawa (National Institute of Advanced Industrial Science and Technology (AIST))*; Seito Kasai (National Institute of Advanced Industrial Science and Technology (AIST)); Yoshimitsu Aoki (Keio University); Hirokatsu Kataoka (National Institute of Advanced Industrial Science and Technology (AIST))


S-VVAD: Visual Voice Activity Detection by Motion Segmentation

Muhammad Shahid ( Istituto Italiano di Tecnologia); Cigdem Beyan (Istituto Italiano di Tecnologia)*; Vittorio Murino (Istituto Italiano di Tecnologia)

Oral 7A: Pose Estimation, Humans and Actions


Recovering Trajectories of Unmarked Joints in 3D Human Actions Using Latent Space Optimization

Suhas Lohit (Mitsubishi Electric Research Laboratories)*; Rushil Anirudh (Lawrence Livermore National Laboratory); Pavan Turaga (Arizona State University)


A Multi-Task Learning Approach for Human Activity Segmentation and Ergonomics Risk Assessment

Behnoosh Parsa (University of Washington)*; Ashis G. Banerjee (University of Washington)


Selective Spatio-Temporal Aggregation Based Pose Refinement System: Towards Understanding Human Activities in Real-World Videos

Di Yang (INRIA)*; Rui Dai (INRIA); Yaohui Wang (INRIA); Rupayan Mallick (INRIA); Luca Minciullo (Toyota Motor Europe); Gianpiero Francesca (Toyota-Europe); Francois Bremond (Inria Sophia Antipolis, France)


Two-hand Global 3D Pose Estimation Using Monocular RGB

Fanqing Lin (Brigham Young University)*; Connor Wilhelm (Brigham Young University); Tony Martinez (Brigham Young University)


A Pose Proposal and Refinement Network for Better 6D Object Pose Estimation

Ameni Trabelsi (Colorado State University)*; Mohamed Chaabane (Colorado State University); Nathaniel Blanchard (Colorado State University); Ross Beveridge (CSU)


3D Dense Geometry-Guided Facial Expression Synthesis by Adversarial Learning

Rumeysa Bodur (Imperial College London)*; Binod Bhattarai (Imperial College London); Tae-Kyun Kim (Imperial College London)


Facial Expression Recognition in the Wild via Deep Attentive Center Loss

Amir Hossein Farzaneh (Utah State University)*; Xiaojun Qi (USU)


CIT-GAN: Cyclic Image Translation Generative Adversarial Network With Application in Iris Presentation Attack Detection

Shivangi Yadav (Michigan State University)*; Arun Ross (Michigan State University)


Unsupervised Attention Based Instance Discriminative Learning for Person Re-Identification

Kshitij N Nikhal (University of Nebraska Lincoln)*; Benjamin Riggan (University of Nebraska-Lincoln)


Learning Shape Representations for Person Re-Identification under Clothing Change

Yu-Jhe Li (Carnegie Mellon University)*; Xinshuo Weng (Carnegie Mellon University); Kris Kitani (Carnegie Mellon University)

Oral 7B: Medical, Risk, Bias, Uncertainty and Defects


DeepOpht: Medical Report Generation for Retinal Images via Deep Models and Visual Explanation

Jia-Hong Huang (University of Amsterdam)*; ChaoHan Yang (KAUST); Fangyu Liu (University of Cambridge); Meng Tian (Department of Ophthalmology, Bern University Hospital); Yi-Chieh Liu (National Taiwan University); Ting-Wei Wu (University of California, Berkeley); I-Hung Lin M.D. (Department of Ophthalmology, Tri-Service General Hospital, National Defense Medical Center); Kang Wang (Beijing Friendship Hospital); Hiromasa Morikawa (Kyoto University); HERNG HUA CHANG (National Taiwan University); Jesper Tegner (KAUST); Marcel Worring (University of Amsterdam)


A Weakly Supervised Consistency-based Learning Method for COVID-19 Segmentation in CT Images

Issam Hadj Laradji (Element AI)*; Pau Rodriguez (Element AI); Oscar Mañas (Element AI); Keegan Lensink (University of British Columbia); Marco Law (University of British Columbia); Lironne Kurzman (University of British Columbia (UBC)); William Parker (University of British Columbia); David Vazquez (Element AI); Derek Nowrouzezahrai (McGill University)


HealTech - A System for Predicting Patient Hospitalization Risk and Wound Progression in Old Patients

Subba Reddy Oota (IIIT Hyderabad)*; Vijay Rowtula (IIIT Hyderabad); Shahid Saleem Mohammed (Woundtech); Jeffrey Galitz (Woundtech); Minghsun Liu (Woundtech); Manish Gupta (Microsoft,India)


Learn like a Pathologist: Curriculum Learning by Annotator Agreement for Histopathology Image Classification

Jerry Wei (Dartmouth College)*; Arief Suriawinata (Dartmouth Collegue); Bing Ren (Dartmouth College); Xiaoying Liu (Dartmouth-Hitchcock Medical Center); Mikhail Lisovsky (Dartmouth-Hitchcock Medical Center); Louis Vaickus (Dartmouth-Hitchcock Medical Center); Charles Brown (Dartmouth-Hitchcock Medical Center); Michael Baker (Dartmouth-Hitchcock Medical Center); Mustafa Nasir-Moin (Dartmouth College); Naofumi Tomita (Dartmouth College); Lorenzo Torresani (Dartmouth College); Jason Wei (Dartmouth College); Saeed Hassanpour (Dartmouth College)


Misclassification Risk and Uncertainty Quantification in Deep Classifiers

Murat Sensoy (Ozyegin University)*; Maryam Saleki (Ozyegin University); Simon Julier (UCL); Reyhan Aydoğan (Özyeğin Üniv.); John Reid (Blue Prisim AI Labs)


AI on the Bog: Monitoring and Evaluating Cranberry Crop Risk

Peri Akiva (Rutgers University)*; Benjamin Planche (Siemens Corporate Technology, Germany); Aditi Roy (Siemens Corporation); Kristin Dana (Rutgers University); Peter Oudemans (Rutgers University); Michael Mars (Rutgers University)


Confidence-Driven Hierarchical Classification of Cultivated Plant Stresses

Logan Frank (Ohio State University)*; Chris Wiegman (Ohio State University); Jim Davis (Ohio State University); Scott Shearer (Ohio State University)


Representation Learning with Statistical Independence to Mitigate Bias

Ehsan Adeli (Stanford University)*; Qingyu Zhao (Stanford University); Adolf Pfefferbaum (SRI International); Edith Sullivan (Stanford University); Li Fei-Fei (Stanford University); Juan Carlos Niebles (Stanford University); Kilian Pohl (Stanford University)


Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection

Gongjie Zhang (Nanyang Technological University); Kaiwen Cui (Nanyang Technology University); Tzu-Yi HUNG (Delta Research Center); Shijian Lu (Nanyang Technological University)*

Oral 7C: Deep Learning and Generative Networks


Generative Patch Priors for Practical Compressive Image Recovery

Rushil Anirudh (Lawrence Livermore National Laboratory)*; Suhas Lohit (Mitsubishi Electric Research Laboratories); Pavan Turaga (Arizona State University)


Accelerated WGAN update strategy with loss change rate balancing

Xu Ouyang (Illinois Institute of Technology)*; Ying Chen (Illinois Institute of Technology); Gady Agam (Illinois Institute of Technology)


Adaptive Multiplane Image Generation from a Single Internet Picture

Diogo C Luvizon (ETIS)*; Gustavo Sutter P. Carvalho (Universidade de São Paulo (ICMC-USP)); Andreza A. dos Santos (IC-Unicamp); Jhonatas S. Conceição (IC-Unicamp); Jose Luis Flores Campana (IC-Unicamp); Luís G. Decker (IC-Unicamp); Marcos R Souza (Universidade Estadual de Campinas); Helio Pedrini (Institute of Computing - UNICAMP); Antonio Joia (SAMSUNG); Otávio Penatti (SAMSUNG )


Learning Fast Converging, Effective Conditional Generative Adversarial Networks with a Mirrored Auxiliary Classifier

Zi Wang (UTK)*


Style Transfer by Rigid Alignment in Neural Net Feature Space

Suryabhan Singh Hada (UC Merced)*; Miguel A Carreira-Perpinan (UC Merced)


MUSCLE: Strengthening Semi-Supervised Learning Via Concurrent Unsupervised Learning Using Mutual Information Maximization

Hanchen Xie (USC/ISI)*; Mohamed Hussein (USC/ISI); Aram Galstyan (USC Information Sciences Institute); Wael Abd-Almageed (Information Sciences Institute)


Holistic Filter Pruning for Efficient Deep Neural Networks

Lukas Enderich (Bosch GmbH)*; Fabian Timm (Robert Bosch GmbH); Wolfram Burgard (University of Freiburg)


Constrained Weight Optimization for Learning without Activation Normalization

Daiki Ikami (NTT Corporation)*; Go Irie (NTT Corporation); Takashi Shibata (NTT/Japan)


Group Softmax Loss with Discriminative Feature Grouping

Takumi Kobayashi (National Institute of Advanced Industrial Science and Technology)*


Phase-wise Parameter Aggregation For Improving SGD Optimization

Takumi Kobayashi (National Institute of Advanced Industrial Science and Technology)*

Date: Friday, January 8, 2021 

Oral 8A: Low-shot Learning, Computational Photography, Super-resolution


Scaling digital screen reading with one-shot learning and re-identification

James Charles (Cambridge University)*; Stefano Bucciarelli (Cambridge University); Roberto Cipolla (University of Cambridge)


Multimodal Prototypical Networks for Few-shot Learning

Frederik Pahde (Humboldt Universität zu Berlin); Mihai O Puscas (Huawei); Tassilo Klein (SAP); Moin Nabi (SAP SE.)*


Improving Few-Shot Learning using Composite Rotation based Auxiliary Task

Pratik Mazumder (Indian Institute of Technology, Kanpur)*; Pravendra Singh (Indian Institute of Technology Kanpur); Vinay Namboodiri (University of Bath)


RNNP: A Robust Few-Shot Learning Approach

Pratik Mazumder (Indian Institute of Technology, Kanpur)*; Pravendra Singh (Indian Institute of Technology Kanpur); Vinay Namboodiri (University of Bath)


On the Texture Bias for Few-Shot CNN Segmentation

Reza Azad (Sharif University of Technology); Abdur Fayjie (ETS Montreal); Claude Kauffmann (CRCHUM); Ismail Ben Ayed (ETS Montreal); Marco Pedersoli (École de technologie supérieure); Jose Dolz (ETS Montreal)*


Dual-Stream Fusion Network for Spatiotemporal Video Super-Resolution

Min-Yuan Tseng (National Chiao Tung University)*; Yen-Chung Chen (National Chiao Tung University); Yi-Lun Lee (National Chiao Tung University); Wei-Sheng Lai (Google); Yi-Hsuan Tsai (NEC Labs America); Wei-Chen Chiu (National Chiao Tung University)


OverNet: Lightweight Multi-Scale Super-Resolution with Overscaling Network

parichehr behjati ardakani (Computer Vision Center)*; Pau Rodriguez (Element AI); Armin Mehri (Computer Vision Center); Isabelle Hupont (Herta Security); Gonzàlez Jordi (Universitat Autònoma de Barcelona); Carles Fernández Tena (Herta Security)


MPRNet: Multi-Path Residual Network for Lightweight Image Super Resolution

Armin Mehri (Computer Vision Center)*; parichehr behjati ardakani (Computer Vision Center); Angel Sappa (Computer Vision Center, Spain)


R-MNet: A perceptual adversarial network for image inpainting

Jireh Jam (Manchester Metropolitan University)*; Connah Kendrick (Manchester Metropolitan University); Vincent Drouard (Image Metrics); Kevin Walker (Image Metrics); Gee-Sern Hsu (National Taiwan University of Science and Technology); Moi Hoon Yap (Manchester Metropolitan University)


Self-supervised training for blind multi-frame video denoising

Valéry Dewil (Centre Borelli)*; Jérémy Anger (ENS Paris-Saclay); Axel Davy (Ens Paris-Saclay); Thibaud Ehret (CMLA, ENS Cachan); Gabriele Facciolo (ENS Paris - Saclay); Pablo Arias (ENS Paris-Saclay)

Oral 8B: Human Action, Tracking, Pose


JOLO-GCN: Mining Joint-Centered Light-Weight Information for Skeleton-Based Action Recognition

Jinmiao Cai (South China University of Technology)*; Nianjuan Jiang (Shenzhen SmartMore Technology Co., Ltd.); Xiaoguang Han (Shenzhen Research Institute of Big Data, the Chinese University of Hong Kong (Shenzhen)); Kui Jia (South China University of Technology); Jiangbo Lu (SmartMore Corporation)


A Variational Information Bottleneck Based Method to Compress Sequential Networks for Human Action Recognition

Ayush Srivastava (Indian Institute of Technology, Delhi)*; Oshin Dutta (IITD); Prathosh AP (IITD); Sumeet Agarwal (Indian Institute of Technology Delhi); Jigyasa Gupta (Samsung R&D Institue India, Delhi)


Distillation Multiple Choice Learning for Multimodal Action Recognition

Nuno C Garcia (Italian Institute of Technology)*; Sarah Bargal (Boston University); Pietro Morerio (Istituto Italiano di Tecnologia); Vitaly Ablavsky (Boston University); Vittorio Murino (Istituto Italiano di Tecnologia); Stan Sclaroff (Boston University)


Scale Equivariance Improves Siamese Tracking

Ivan Sosnovik (University of Amsterdam)*; Artem Moskalev (University of Amsterdam); Arnold W.M. Smeulders (University of Amsterdam)


IGSSTRCF: Importance Guided Sparse Spatio-Temporal Regularized Correlation Filters For Tracking

Monika Jain (Queensland University Of Technology, Brisbane)*; A Subramanyam (IIITD); SIMON DENMAN (Queensland University of Technology, Australia); Sridha Sridharan (QUT); Clinton Fookes (Queensland University of Technology)


Single Image Human Proxemics Estimation for Visual Social Distancing

Maya Aghaei (Istituto Italiano di Tecnologia)*; Matteo Bustreo (IIT); Yiming Wang (IIT); Gian Luca Bailo (Istituto Italiano di Tecnologia); Pietro Morerio (Istituto Italiano di Tecnologia); Alessio Del Bue (Istituto Italiano di Tecnologia (IIT))


PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation

Wen GUO (INRIA)*; Enric Corona (IRI); Francesc Moreno (IRI); Xavier Alameda-Pineda (INRIA)


Real-time RGBD-based Extended Body Pose Estimation

Renat Bashirov (Samsung); Anastasia Ianina (Samsung AI Center Moscow); Karim Iskakov (Samsung AI Center); Yevgeniy Kononenko (Samsung); Valeriya Strizhkova (AINSI); Victor Lempitsky (Samsung)*; Alexander Vakhitov (SLAMCore)


SuPEr-SAM: Using the Supervision Signal from a Pose Estimator to Train a Spatial Attention Module for Personal Protective Equipment Recognition

Adrian Sandru (SecurifAI); Georgian Emilian Duta (SecurifAI); Mariana-Iuliana Georgescu (University of Bucharest); Radu Tudor Ionescu (University of Bucharest)*


Person-in-Context Synthesis with Compositional Structural Space

Weidong Yin (University of British Columbia)*; Ziwei Liu (Nanyang Technological University); Leonid Sigal (University of British Columbia)

Oral 8C: Applications, Misc.


Neuron matching in C. elegans with robust approximate linear regression without correspondence

Amin Nejatbakhsh (Columbia University); Erdem Varol (Columbia University)*


2D to 3D Medical Image Colorization

Aradhya Mathur (IIITD)*; Apoorv Khattar (IIIT Delhi); ojaswa sharma (IIITD)


Lip-reading with Densely Connected Temporal Convolutional Networks

Pingchuan Ma (Imperial College London); Yujiang Wang (Imperial College London)*; Jie Shen (Imperial College London); Stavros Petridis (Imperial College London); Maja Pantic (Imperial College London / Samsung )


ExMaps: Long-Term Localization in Dynamic Scenes using Exponential Decay

Alexandros Rotsidis (University of Bath)*; Christof Lutteroth (University of Bath); Peter M Hall (University of Bath); Christian Richardt (University of Bath)


Shape from Caustics: Reconstruction of 3D-Printed Glass from Simulated Caustic Images

Marc Kassubeck (Technische Universität Braunschweig)*; Florian Bürgel (Technische Universität Braunschweig); Susana Castillo (Technische Universität Braunschweig); Sebastian Stiller (Technische Universität Braunschweig); Marcus Magnor (Technische Universität Braunschweig)


Minimal Solvers for Single-View Lens-Distorted Camera Auto-Calibration

Yaroslava Lochman (Ukrainian Catholic University)*; Oles Dobosevych (Ukrainian Catholic University); Rostyslav Hryniv (Ukrainian Catholic University); James Pritts (Facebook)


DeepCFL: Deep Contextual Features Learning from a Single Image

Indra Deep Mastan (Indian Institute of Technology Gandhinagar)*; Shanmuganathan Raman (Indian Institute of Technology (IIT) Gandhinagar)


CoMoDA: Continuous Monocular Depth Adaptation Using Past Experiences

Yevhen Kuznietsov (KU Leuven)*; Marc Proesmans (KU Leuven); Luc Van Gool (KU Leuven & ETH Zurich)


Adaptive-Attentive Geolocalization from few queries: a hybrid approach

Gabriele Berton (Politecnico di Torino)*; Valerio Paolicelli (Politecnico di Torino); Carlo Masone (Istituto Italiano di Tecnologia); Barbara Caputo (Politecnico di Torino)


Ontology-driven Event Type Classification in Images

Eric Müller-Budack (TIB - Leibniz Information Centre for Science and Technology)*; Matthias Springstein (TIB); Sherzod Hakimov (TIB - Leibniz Information Centre for Science and Technology); Kevin Mrutzek (Leibniz Universität Hannover); Ralph Ewerth (TIB - Leibniz Information Center for Science and Technology)

Oral 9A: Recognition, Detection, Classification


DB-GAN: Boosting Object Recognition Under Strong Lighting Conditions

Luca Minciullo (Toyota Motor Europe)*; Fabian Manhardt (TU Munich); Kei Yoshikawa (Toyota Motor Coorporation); Sven Meier (Toyota Motor Europe); Federico Tombari (Google, TU Munich); Norimasa Kobori (Toyota Research Institute - Advanced Development)


Improving Point Cloud Semantic Segmentation by Learning 3D Object Detection

Ozan Unal (ETH Zurich)*; Luc Van Gool (ETH Zurich); Dengxin Dai (ETH Zurich)


We don't Need Thousand Proposals: Single Shot Actor-Action Detection in Videos

Aayush Jung Bahadur Rana (University of Central Florida)*; Yogesh Rawat (University of Central Florida)


PDAN: Pyramid Dilated Attention Network for Action Detection

Rui Dai (INRIA)*; Srijan Das (INRIA); Luca Minciullo (Toyota Motor Europe); Lorenzo Garattoni (Toyota-Europe); Gianpiero Francesca (Toyota-Europe); Francois Bremond (Inria Sophia Antipolis, France)


DeepMark++: Real-time Clothing Detection at the Edge

Alexey Sidnev (Huawei)*; Alexander Krapivin (Huawei); Alexey Trushkov (Huawei); Ekaterina Krasikova (Huawei); Maxim Kazakov (Huawei); Mikhail Viryasov (Huawei)


Task-Assisted Domain Adaptation with Anchor Tasks

Zhizhong Li (University of Illinois Urbana Champaign)*; Linjie Luo (ByteDance Inc); Sergey Tulyakov (Snap Inc); Qieyun Dai (UIUC); Derek Hoiem (University of Illinois at Urbana-Champaign)


Fast Kernelized Correlation Filter without Boundary Effect

Ming Tang (Institute of Automation, Chinese Academy of Sciences)*; Linyu Zheng (Institute of Automation, Chinese Academy of Sciences); Bin Yu (Institute of Automation, Chinese Academy of Sciences); Jinqiao Wang (Institute of Automation, Chinese Academy of Sciences)


RGPNet: A Real-Time General Purpose Semantic Segmentation

Elahe Arani (Navinfo Europe )*; Shabbir Marzban (Navinfo Europe); Andrei Pata (Navinfo Europe); Bahram Zonooz (Navinfo Europe)


Multi-path Neural Networks for On-device Multi-domain Visual Classification

Qifei Wang (Google)*; Junjie Ke (Google); Joshua Greaves‎ (Google); Grace Chu (Google); Gabriel Bender (Google); Luciano Sbaiz (Google AI); Alec Go (Google); Andrew Howard (Google); Feng Yang (Google Research); Ming-Hsuan Yang (Google Research); Jeff Gilbert (Google); Peyman Milanfar (Google)


Temporal Stochastic Softmax for 3D CNNs: An Application in Facial Expression Recognition

Theo Ayral (École de technologie supérieure)*; Marco Pedersoli (École de technologie supérieure); Simon Bacon (Concordia University); Eric Granger (ETS Montreal )

Oral 9B: Vision/Language, Video, Zero-shot Learning


Improving Video Captioning with Temporal Composition of a Visual-Syntactic Embedding

Jesus Perez-Martin (Department of Computer Science, University of Chile)*; Benjamin Bustos (Department of Computer Science, University of Chile); Jorge Pérez (universidad de Chile)


Transductive Visual Verb Sense Disambiguation

Sebastiano Vascon (Ca' Foscari University of Venice & European Centre for Living Technology)*; Sinem Aslan (Ca' Foscari University of Venice); Gianluca Bigaglia (Ca' Foscari University of Venice); Lorenzo Giudice (Ca' Foscari University of Venice); Marcello Pelillo (Ca' Foscari University of Venice)


Reducing the Annotation Effort for Video Object Segmentation Datasets

Paul Voigtlaender (RWTH Aachen University)*; lishu luo (Tsinghua University); Chun Yuan (Graduate school at ShenZhen,Tsinghua university); Yong Jiang (Tsinghua University); Bastian Leibe (RWTH Aachen University-)


Efficient video annotation with visual interpolation and frame selection guidance

Alina Kuznetsova (Google)*; Aakrati Talati (Google); Yiwen Luo (Google); Keith Simmons (Google); Vittorio Ferrari (Google Research)


HyperCon: Image-To-Video Model Transfer for Video-To-Video Translation Tasks

Ryan Szeto (University of Michigan Ann Arbor)*; Mostafa El-Khamy (Samsung Research USA); Jungwon Lee (Samsung Semiconductor, Inc.); Jason J Corso (U Michigan and Voxel51)


AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing Label Features from Multi-Modal Embeddings

Pratik Mazumder (Indian Institute of Technology, Kanpur)*; Pravendra Singh (Indian Institute of Technology Kanpur); Kranti K Parida (IIT Kanpur); Vinay Namboodiri (University of Bath)


Two-Level Adversarial Visual-Semantic Coupling for Generalized Zero-shot Learning

Shivam Chandhok (Indian Institute of Technology, Hyderabad)*; Vineeth N Balasubramanian (Indian Institute of Technology, Hyderabad)


Transductive Zero-Shot Learning by Decoupled Feature Generation

Federico Marmoreo (Istituto Italiano di Tecnologia; Università degli Studi di Genova)*; Jacopo Cavazza (Istituto Italiano di Tecnologia); Vittorio Murino (Istituto Italiano di Tecnologia)

Oral 9C: Learning, Deep Learning, Generative Approaches


Novel View Synthesis via Depth-guided Skip Connections

Yuxin Hou (Aalto University)*; Arno Solin (Aalto University); Juho Kannala (Aalto University, Finland)


Noise as a Resource for Learning in Knowledge Distillation

Elahe Arani (Navinfo Europe )*; Fahad Sarfraz (Navinfo Europe); Bahram Zonooz (Navinfo Europe)


Rotate to Attend: Convolutional Triplet Attention Module

Diganta Misra (Kalinga Institute of Industrial Technology)*; Trikay Nalamada (Indian Institute of Technology, Guwahati); Ajay U Arasanipalai (University of Illinois at Urbana-Champaign); Qibin Hou (National University of Singapore)


Cross-Domain Latent Modulation for Variational Transfer Learning

Jinyong Hou (University of Otago)*; Jeremiah Deng (University of Otago, New Zealand); Stephen Cranefield (University of Otago); Xuejie Ding (University of Otago)


Noisy Concurrent Training for Efficient Learning under Label Noise

Fahad Sarfraz (Navinfo Europe); Elahe Arani (Navinfo Europe ); Bahram Zonooz (Navinfo Europe)*


Fast Fourier Intrinsic Network

Yanlin Qian (Tampere University); Miaojing Shi (King's College London)*; Joni-Kristian Kamarainen (Tampere University); Jiri Matas (CMP CTU FEE)


Temporal Shift GAN for Large Scale Video Generation

Andrés Muñoz Garza (University of Freiburg)*; Mohammadreza Zolfaghari (University of Freiburg); Max J. Argus (University Of Freiburg); Thomas Brox (University of Freiburg)


LT-GAN: Self-Supervised GAN with Latent Transformation Detection

Parth Shailesh Patel (BITS Pilani); Nupur Kumari (Adobe Systems)*; Mayank Singh (Adobe Systems); Balaji Krishnamurthy ()

Oral 10A: Image and Video Understanding


Appending Adversarial Frames for Universal Video Attack

Zhikai Chen (Xi'an Jiaotong University); Lingxi Xie (Huawei Inc.); Shanmin Pang (Xi'an Jiaotong University)*; Yong He (Xi'an jiaotong university); Qi Tian (Huawei Cloud & AI)


Intra-class Part Swapping for Fine-Grained Image Classification

Lianbo Zhang (University of Technology Sydney)*; Shaoli Huang (University of Sydney); Wei Liu (University of Technology Sydney)


Future Moment Assessment for Action Query

Qiuhong Ke (The University of Melbourne)*; Mario Fritz (CISPA Helmholtz Center for Information Security); Bernt Schiele (MPI Informatics)


Towards Precise Intra-camera Supervised Person Re-Identification

Menglin Wang (Zhejiang University)*; Baisheng Lai (Alibaba Group); Haokun Chen (Zhejiang University); Jianqiang Huang (Alibaba Group); Xiaojin Gong (Zhejiang University); Xian-Sheng Hua (Alibaba Group)


Weakly Supervised Deep Reinforcement Learning for Video Summarization With Semantically Meaningful Reward

Zutong Li (Weibo)*; Lei Yang (Weibo R&D USA)


CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection

Bin Zhu (Beijing University of Posts and Telecommunications); Qing Song (Beijing University of Posts and Telecommunications)*; Lu Yang (Beijing University of Posts and Telecommunications); Zhihui Wang (Beijing University of Posts and Telecommunications); Chun Liu ( Beijing University of Posts and Telecommunications); Mengjie Hu (Beijing University of Posts and Telecommunications)


Towards Resolving the Challenge of Long-tail Distribution in UAV Images for Object Detection

Weiping Yu (University of North Carolina at Charlotte); Taojiannan Yang (University of North Carolina at Charlotte); Chen Chen (University of North Carolina at Charlotte)*


Temporal Context Aggregation for Video Retrieval with Contrastive Learning

Jie Shao (Fudan University)*; Xin Wen (Tongji University); Bingchen Zhao (Tongji University); Xiangyang Xue (Fudan University)


Towards Contextual Learning in Few-shot Object Classification

Mathieu Pagé Fortin (Laval University)*; Brahim Chaib-draa (Laval University)


Data-free Knowledge Distillation for Object Detection

Akshay Chawla (CMU)*; Hongxu Yin (NVIDIA Research); Pavlo Molchanov (NVIDIA); Jose M Alvarez (NICTA)


Vid2Int: Detecting Implicit Intention from Long Dialog Videos

Xiaoli Xu (Renmin University of China); Yao Lu (Renmin University of China); Zhiwu Lu (Renmin University of China)*; Tao Xiang (University of Surrey)


Fair Comparison: Quantifying Variance in Results for Fine-grained Visual Categorization

Matthew A Gwilliam (Brigham Young University)*; Adam Teuscher (Brigham Young University); Connor Anderson (Brigham Young University); Ryan Farrell (Brigham Young University)


RefineLoc: Iterative Refinement for Weakly-Supervised Action Localization

Alejandro Pardo (KAUST)*; Humam Alwassel (KAUST); Fabian Caba (Adobe Research); Ali K Thabet (KAUST); Bernard Ghanem (KAUST)


S3-Net: A Fast and Lightweight Video Scene Understanding Network by Single-shot Segmentation

Yuan Cheng (Shanghai Jiao Tong University)*; Yuchao Yang (Southern University of Science and Technology); Hai-Bao Chen (Shanghai Jiao Tong University); Ngai Wong (The University of Hong Kong); Hao Yu (Southern University of Science and Technology)


Deep Active Learning for Joint Classification & Segmentation with Weak Annotator

Soufiane Belharbi (ÉTS Montreal)*; Ismail Ben Ayed (ETS Montreal); Luke McCaffrey (McGill University); Eric Granger (ETS Montreal )

Oral 10B: Humans and Faces


Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples

Shehzeen S Hussain (UCSD)*; Paarth Neekhara (UCSD); Malhar S Jere (University of California San Diego); Farinaz Koushanfar (UC San Diego); Julian McAuley (UCSD)


Red Carpet to Fight Club: Partially-supervised Domain Transfer for Face Recognition in Violent Videos

Yunus Can Bilge (Hacettepe University)*; Mehmet Kerim Yücel (Hacettepe University); Ramazan Gokberk Cinbis (METU); Nazli Ikizler-Cinbis (Hacettepe University); Pinar Duygulu (Hacettepe University)


Focus and retain: Complement the Broken Pose in Human Image Synthesis

Zhun Sun (BIGO Ltd.); Wei Xiang (BIGO Ltd.)*; Xue Jing (; Pu Ge (BIGO Ltd.); Qiushi Huang (BIGO Ltd.); Yule Li (BIGO Ltd.); Yiyong Li (BIGO Ltd.)


Faces `a la Carte: Text-to-Face Generation via Attribute Disentanglement

Tianren Wang (The University of Queensland)*; Teng Zhang (The University of Queensland); Brian C Lovell (University of Queensland)


maskedFaceNet: A Progressive Semi-Supervised Masked Face Detector

Shitala Prasad (Institute for Infocomm Research)*; Yiqun Li (Institute for Infocomm Research); Dongyun Lin (Institute for Infocomm Research); Sheng Dong (Institute for Infocomm Research)


Whose hand is this? Person Identification from Egocentric Hand Gestures

Satoshi Tsutsui (Indiana University)*; Yanwei Fu (Fudan University); David Crandall (Indiana University)


FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition

Vinoj Jayasundara (University of Moratuwa)*; Debaditya Roy (Agency for Science, Technology and Research, A*STAR, Singapore); Basura Fernando (Agency for Science, Technology and Research, A*STAR, Singapore)


Active Learning for Bayesian 3D Hand Pose Estimation

Razvan Caramalau (Imperial College)*; Binod Bhattarai (Imperial College London); Tae-Kyun Kim (Imperial College London)


Hand Pose Guided 3D Pooling for Word-level Sign Language Recognition

Al Amin Hosain (George Mason University)*; Panneer Selvam Santhalingam (George Mason University); Parth Pathak (George Mason University); Huzefa Rangwala (George Mason University); Jana Kosecka (George Mason University)


Conditional Link Prediction of Category-Implicit Keypoint Detection

Ellen Yi-Ge (Carnegie Mellon University)*; Rui R. Fan (UC San Diego); Zechun Liu (HKUST); Zhiqiang Shen (Carnegie Mellon University)


GraphTCN: Spatio-Temporal Interaction Modeling for Human Trajectory Prediction

Chengxin Wang (National University of Singapore)*; Shaofeng Cai (National University of Singapore); Gary Tan (National University of Singapore)


Real-Time Gait-Based Age Estimation and Gender Classification from a Single Image

Chi Xu (Nanjing University of Science and Technology)*; Yasushi Makihara ("""Osaka University, Japan"""); Ruochen Liao (Osaka University); Hirotaka Niitsuma (Osaka University); Xiang Li (Nanjing University of Science and Technology); Prof. Yasushi Yagi (Osaka University); Jianfeng Lu (Nanjing University of Science and Technology)

Oral 10C: Learning


Zero-Shot Recognition via Optimal Transport

Wenlin Wang (Duke Univeristy)*; Wenqi Wang (Facebook)


AdarGCN: Adaptive Aggregation GCN for Few-Shot Learning

Jianhong Zhang (Renmin University of China); Manli Zhang (Renmin University of China); Zhiwu Lu (Renmin University of China)*; Tao Xiang (University of Surrey)


Improved Training of Generative Adversarial Networks Using Decision Forests

Gil Avraham (Monash University)*; Yan Zuo (Monash University); Tom Drummond (Monash University)


ADA-AT/DT: An Adversarial Approach for Cross-Domain and Cross-Task Knowledge Transfer

Ruchika R Chavhan (Indian Institute of Technology, Bombay, India)*; Ankit Jha (IIT Bombay); Biplab Banerjee (Indian Institute of Technology, Bombay); Subhasis Chaudhuri (Indian Institute of Technology Bombay)


Zero-Pair Image to Image Translation using Domain Conditional Normalization

Samarth Shukla (ETH Zurich)*; Andrés Romero (ETH Zürich); Luc Van Gool (ETH Zurich); Radu Timofte (ETH Zurich)


Breaking Shortcuts by Masking for Robust Visual Reasoning

Keren Ye (University of Pittsburgh)*; Mingda Zhang (University of Pittsburgh); Adriana Kovashka (University of Pittsburgh)


Efficient Attention: Attention with Linear Complexities

Zhuoran Shen (Google)*; Mingyuan Zhang (Beijing SenseTime Technology Development Limited); Haiyu Zhao (SenseTime International Pte Ltd); Shuai Yi (SenseTime Group Limited); Hongsheng Li (Chinese University of Hong Kong)


SubICap: Towards Subword-informed Image Captioning

Naeha Sharif (The University of Western Australia)*; Mohammed Bennamoun (University of Western Australia); Wei Liu (University of Western Australia); Syed Afaq Ali Shah (Murdoch University)


ResNet or DenseNet? Introducing Dense Shortcuts to ResNet

Chaoning Zhang (KAIST)*; Philipp Benz (KAIST); Dawit Mureja Argaw (KAIST); Seokju Lee (KAIST); Junsik Kim (Korea Advanced Institute of Science and Technology (KAIST)); Francois Rameau (KAIST); Jean-Charles Bazin (KAIST); In So Kweon (KAIST, Korea)


Attentional Feature Fusion

Yimian Dai (Nanjing University of Aeronautics and Astronautics)*; Fabian Gieseke (University of Copenhagen); Stefan Oehmcke (University of Copenhagen); Yiquan Wu (Nanjing University of Aeronautics and Astronautics); Kobus Barnard (University of Arizona)


Class Anchor Clustering: a Loss for Distance-based Open Set Recognition

Dimity Miller (Queensland University of Technology)*; Niko Suenderhauf (Queensland University of Technology); Michael Milford (ACRV and QUT, Australia); Feras Dayoub (Queensland University of Technology)


EVET: Enhancing Visual Explanations of Deep Neural Networks Using Image Transformations

Youngrock Oh (Samsung SDS)*; Hyungsik Jung (Samsung SDS); Jeonghyung Park (SAMSUNG); Min Soo Kim (Advanced Research Lab, R&D Center, Samsung SDS)


Dynamic Routing Networks

Shaofeng Cai (National University of Singapore)*; Yao Shu (National University of Singapore); Wei Wang (National University of Singapore)


Improve CAM with Auto-adapted Segmentation and Co-supervised Augmentation

Ziyi Kou (University of Notre Dame); Guofeng Cui (Rutgers University); Shaojie Wang (Washington University in St. Louis); WENTIAN ZHAO (University of Rochester); Chenliang Xu (University of Rochester)*


EvidentialMix: Learning with Combined Open-set and Closed-set Noisy Labels

Ragav Sachdeva (University of Adelaide)*; Filipe Rolim Cordeiro (Universidade Federal Rural de Pernambuco); Vasileios Belagiannis (Universität Ulm); Ian Reid ("University of Adelaide, Australia"); Gustavo Carneiro (University of Adelaide)

Oral 11A: Applications


SHAD3S : a Model for Sketch, Shade and Shadow

Raghav Brahmadesam Venkataramaiyer (Indian Institute of Technology Kanpur)*; Abhishek Joshi (IIT Kanpur); Saisha Narang (Indian Institute of Technology); Vinay Namboodiri (IIT Kanpur)


Multi-Level Generative Chaotic Recurrent Network for Image Inpainting

Cong Chen (Virginia Tech)*; Amos L Abbott (Virginia Tech); Daniel Stilwell (Virginia Tech.)


Deep unsupervised anomaly detection

Siying Liu (I2R Singapore); Zheng Wang (I2R Singapore); Wen-Yan Lin (SMU); Tangqing Li (National University of Singapore)*


Fine-grained Foreground Retrieval Via Teacher-Student Learning

Zongze Wu (Hebrew University of Jerusalem)*; Dani Lischinski (The Hebrew University of Jerusalem); Eli Shechtman (Adobe Research, US)


TB-Net: A Three-Stream Boundary-Aware Network for Fine-Grained Pavement Disease Segmentation

Yujia Zhang (Institue of Automation, Chinese Academy of Sciences)*; qianzhong li (Institute of Automation Chinese Academic of Science); Xiaoguang Zhao (Institue of Automation, Chinese Academy of Sciences); Min Tan (Institiute of Automation, Chinese academy of sciences)


Coarse-to-Fine Gaze Redirection with Numerical and Pictorial Guidance

Jingjing Chen (Zhejiang University); Jichao Zhang (University of Trento)*; Enver Sangineto (University of Trento); Tao Chen (Fudan University); jiayuan fan (Fudan University); Nicu Sebe (University of Trento)


Coarse- and Fine-grained Attention Network with Background-aware Loss for Crowd Density Map Estimation

Liangzi Rong (Tsinghua University)*; Chunping Li (Tsinghua University)


WDNet: Watermark-Decomposition Network for Visible Watermark Removal

Yang Liu (Huazhong University of Science and Technology)*; Zhen Zhu (Huazhong University of Science and Technology); Xiang Bai (Huazhong University of Science and Technology)


End-to-end Lane Shape Prediction with Transformers

Ruijin Liu (Xi`an Jiaotong Unversity)*; Zejian Yuan (Xi‘an Jiaotong University); Tie Liu (Capital Normal University); Zhiliang Xiong (Shenzhen Forward Innovation Digital Technology Co. Ltd)


Have Fun Storming the Castle(s)!

Connor Anderson (Brigham Young University)*; Adam Teuscher (Brigham Young University); Elizabeth Anderson (BYU); Alysia Larsen (BYU); Josh Shirley (Brigham Young University); Ryan Farrell (Brigham Young University)


Learned Dual-View Reflection Removal

Simon Niklaus (Adobe Research)*; Xuaner Zhang (UC Berkeley); Jonathan T Barron (Google Research); Neal Wadhwa (Google); Rahul Garg (Google); Feng Liu (Portland State University); Tianfan Xue (Google)


Multimodal Trajectory Predictions for Autonomous Driving without a Detailed Prior Map

Atsushi Kawasaki (TOSHIBA Corporation)*; Akihito Seki (Toshiba)


Optimistic Agent: Accurate Graph-Based Value Estimation for More Successful Visual Navigation

Mahdi Kazemi Moghaddam (University of Adelaide)*; Qi Wu (University of Adelaide); Ehsan M Abbasnejad (The University of Adelaide); Qinfeng Shi (University of Adelaide)


Auto-Navigator: Decoupled Neural Architecture Search for Visual Navigation

Tianqi Tang (University of Technology Sydney)*; Xin Yu (University of Technology Sydney); Xuanyi Dong (University of Technology Sydney); Yi Yang (UTS)


Are These from the Same Place? Seeing the Unseen in Cross-View Image Geo-Localization

Royston Rodrigues (NEC)*; Masahiro Tani (NEC)

Oral 11B: 3D and Applications


Self-supervised 4D Spatio-temporal Feature Learning via Order Prediction of Sequential Point Cloud Clips

Haiyan Wang (The City College of New York)*; Yang Liang (apple); Xuejian Rong (Facebook); JInglun Feng (The City College of New York); YingLi Tian (City University of New York)


Cross-Modality 3D Object Detection

Ming Zhu (Shanghai Jiao Tong University)*; Pan Ji (OPPO US Research Center); Chao Ma (Shanghai Jiao Tong University); Xiaokang Yang (Shanghai Jiao Tong University of China)


Long-range Attention Network for Multi-View Stereo

Xudong Zhang (Beihang University)*; Yutao Hu (Beihang University); haochen wang (Beihang University); Xianbin Cao (Beihang University, China); Baochang Zhang (Beihang University)


Efficient 3D Video Engine Using Frame Redundancy

Gao Peng (Shanghai Jiao Tong University); Bo Pang (Shanghai Jiao Tong University); Cewu Lu (Shanghai Jiao Tong University)*


Viewpoint-agnostic Image Rendering

Hiroaki Aizawa (Gifu University)*; Hirokatsu Kataoka (National Institute of Advanced Industrial Science and Technology (AIST)); Yutaka Satoh (National Institute of Advanced Industrial Science and Technology (AIST)); Kunihito Kato (Gifu University)


Dense-Resolution Network for Point Cloud Classification and Segmentation

Shi Qiu (ANU)*; Saeed Anwar (ANU); Nick Barnes (ANU)


PNPDet: Efficient Few-shot Detection without Forgetting via Plug-and-Play Sub-networks

Gongjie Zhang (Nanyang Technological University); Kaiwen Cui (Nanyang Technology University); Rongliang Wu (Nanyang Technological University); Shijian Lu (Nanyang Technological University)*; Yonghong Tian (Peking University)


An Alternative of LIDAR in Nighttime: Unsupervised Depth Estimation Based on Single Thermal Image

Yawen Lu (Rochester Institute of Technology); Guoyu Lu (Rochester Institute of Technology)*


Self-supervised Visual-LiDAR Odometry with Flip Consistency

Bin Li (Zhejiang University); Mu Hu (Zhejiang University); Shuling Wang (Zhejiang University); Lianghao Wang (Zhejiang University); Xiaojin Gong (Zhejiang University)*


Boosting Monocular Depth with Panoptic Segmentation Maps

Faraz Saeedan (TU Darmstadt)*; Stefan Roth (TU Darmstadt)


End-to-End Chinese Landscape Painting Creation Using Generative Adversarial Networks

Alice W Xue (Princeton University)*


Line Art Correlation Matching Feature Transfer Network for Automatic Animation Colorization

Qian Zhang (iQIYI Inc)*; Bo Wang (iQIYI Inc); Wei Wen (iQIYI Inc); Hai Li (iQIYI Inc); Junhui Liu (iQIYI Inc)


Handwritten Chinese Font Generation with Collaborative Stroke Refinement

Chuan Wen (Shanghai Jiao Tong University)*; Yujie Pan (Cooperative Medianet Innovation Center, Shanghai Jiao Tong University); Jie Chang (Shanghai Jiao Tong University); Ya Zhang (Cooperative Medianet Innovation Center, Shang hai Jiao Tong University); Siheng Chen (Mitsubishi Electric Research Laboratories (MERL)); Yan-Feng Wang (Cooperative medianet innovation center of Shanghai Jiao Tong University); Mei Han (Ping An Technology); Qi Tian (Huawei Cloud & AI)


Ellipse Detection and Localization with Applications to Knots in Sawn Timber Images

Shenyi Pan (University of British Columbia)*; Shuxian Fan (University of British Columbia); Samuel W. K. Wong (University of Waterloo); James Zidek (University of British Columbia); Helge Rhodin (UBC)


ATM: Attentional Text Matting

Peng Kang (Northwestern University)*; Jianping Zhang (Northwestern University); Chen Ma (McGill University); Guiling Sun (Nankai University)


Hyperrealistic Image Inpainting with Hypergraphs

Gourav Wadhwa (Indian Institute of Technology Ropar); Abhinav Dhall (Monash University)*; Subrahmanyam Murala (IIT Ropar); Usman Tariq (American University of Sharjah)

Oral 11C: Learning, Medical and other Applications


Do We Really Need Gold Samples for Sample Weighting under Label Noise?

Aritra Ghosh (University of Massachusetts Amherst)*; Andrew Lan (University of Massachusetts Amherst)


Analyzing Deep Neural Network’s Transferability via Fr ́echet Distance

Yifan Ding (University of Central Florida)*; Boqing Gong (Google); Liqiang Wang (University of Central Florida)


InfoMax-GAN: Improved Adversarial Image Generation via Information Maximization and Contrastive Learning

Kwot Sin Lee (University of Cambridge; Snap Inc.)*; Ngoc-Trung Tran (Singapore University of Technology and Design); Ngai-Man Cheung (Singapore University of Technology and Design)


Spike-Thrift: Towards Energy-Efficient Deep Spiking Neural Networks by Limiting Spiking Activity via Attention-Guided Compression

Souvik Kundu (University of Southern California)*; Gourav Datta (University of Southern California); Massoud Pedram (University of Southern California); Peter A. Beerel (University of Southern California)


Few-Shot Learning via Feature Hallucination with Variational Inference

Qinxuan Luo (Institute of Automation,Chinese Academy of Sciences)*; Lingfeng Wang (NLPR, Institute of Automation, Chinese Academy of Sciences); Jingguo Lv (Beijing University of Civil Engineering and Architecture); SHIMING XIANG (Chinese Academy of Sciences, China); Chunhong Pan (Institute of Automation, Chinese Academy of Sciences)


Neural Contrast Enhancement of CT Image

Minkyo Seo (POSTECH); Dongkeun Kim (POSTECH); Kyungmoon Lee (POSTECH); Seunghoon Hong (KAIST); Jae Seok Bae (Seoul National University Hospital); Jung Hoon Kim (Department of Radiology, Seoul National University College of Medicine, ); Suha Kwak (POSTECH)*


Multi-Task Knowledge Distillation for Eye Disease Prediction

Sahil Chelaramani (Microsoft); Manish Gupta (Microsoft,India)*; Vipul Agarwal (Microsoft); Prashant Gupta (Microsoft); Ranya Habash (Bascom Palmer)


Style Consistent Image Generation for Nuclei Instance Segmentation

Xuan Gong (University at Buffalo)*; Shuyan Chen (University at buffalo); Baochang Zhang (Beihang University); David Doermann (University at Buffalo)


Deformable Gabor Feature Networks for Biomedical Image Classification

Xuan Gong (University at Buffalo)*; Xin Xia (Beihang University); Wentao Zhu (NVIDIA); Baochang Zhang (Beihang University); David Doermann (University at Buffalo); Li'an Zhuo (Beihang University)


Audio-Visual Event Localization via Recursive Fusion by Joint Co-Attention

Bin Duan (Texas State University)*; Hao Tang (University of Trento); Wei Wang (EPFL); Ziliang Zong (Texas State University); Guowei Yang (Texas State University); Yan Yan (Texas State University)


Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval

Andres Mafla (Computer Vision Centre)*; Sounak Dey (Computer Vision Center); Ali Furkan Biten (Computer Vision Center); Lluis Gomez (Universitat Autónoma de Barcelona); Dimosthenis Karatzas (Computer Vision Centre)


MoRe: A Large-Scale Motorcycle Re-Identification Dataset

Augusto M Figueiredo (Universidade Federal de Minas Gerais)*; Johnata Brayan (Universidade Federal de Minas Gerais ); Renan Oliveira Reis (Federal University of Minas Gerais ); Raphael Felipe Prates (Universidade Estadual de Campinas); William R Schwartz (Federal University of Minas Gerais)


Can Selfless Learning improve accuracy of a single classification task?

Soumya Roy (IIT, Kanpur)*; Bharat Sau (IITH)


Improving Robustness and Uncertainty modelling in Neural Ordinary Differential Equations

srinivas anumasa (Indian Institute of Technology, Hyderabad)*; P. K. Srijith (IIT Hyderabad)