【CVPR2021】论文汇总列表--Part2

- 本帖汇总了CVPR2021目前在arxiv上公布的文章列表，持续更新中。

• Best wishes! ☔ ❤ 🍜 👉 part1 👈
• ckpt: 20210501， data from arxiv.org

Online Learning of a Probabilistic and Adaptive Scene Representation AuthorsZike Yan, Xin Wang, Hongbin Zha

Towards Open World Object Detection AuthorsK J Joseph, Salman Khan, Fahad Shahbaz Khan, Vineeth N Balasubramanian

Learning Asynchronous and Sparse Human-Object Interaction in Videos AuthorsRomero Morais, Vuong Le, Svetha Venkatesh, Truyen Tran

DeepTag: An Unsupervised Deep Learning Method for Motion Tracking on Cardiac Tagging Magnetic Resonance Images AuthorsMeng Ye, Mikael Kanski, Dong Yang, Qi Chang, Zhennan Yan, Qiaoying Huang, Leon Axel, Dimitris Metaxas

A Cross Channel Context Model for Latents in Deep Image Compression AuthorsChangyue Ma, Zhao Wang, Ruling Liao, Yan Ye

PointGuard: Provably Robust 3D Point Cloud Classification AuthorsHongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong

TPCN: Temporal Point Cloud Networks for Motion Forecasting AuthorsMaosheng Ye, Tongyi Cao, Qifeng Chen

Self-supervised Geometric Perception AuthorsHeng Yang, Wei Dong, Luca Carlone, Vladlen Koltun

Anycost GANs for Interactive Image Synthesis and Editing AuthorsJi Lin, Richard Zhang, Frieder Ganz, Song Han, Jun-Yan Zhu

Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food AuthorsQuin Thames, Arjun Karpur, Wade Norris, Fangting Xia, Liviu Panait, Tobias Weyand, Jack Sim

Teachers Do More Than Teach: Compressing Image-to-Image Models AuthorsQing Jin, Jian Ren, Oliver J. Woodford, Jiazhuo Wang, Geng Yuan, Yanzhi Wang, Sergey Tulyakov

Unsupervised Learning for Robust Fitting:A Reinforcement Learning Approach AuthorsGiang Truong, Huu Le, David Suter, Erchuan Zhang, Syed Zulqarnain Gilani

LOHO: Latent Optimization of Hairstyles via Orthogonalization AuthorsRohit Saha, Brendan Duke, Florian Shkurti, Graham W. Taylor, Parham Aarabi

Selective Replay Enhances Learning in Online Continual Analogical Reasoning AuthorsTyler L. Hayes, Christopher Kanan

Simultaneously Localize, Segment and Rank the Camouflaged Objects AuthorsYunqiu Lv, Jing Zhang, Yuchao Dai, Aixuan Li, Bowen Liu, Nick Barnes, Deng-Ping Fan

Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning AuthorsAli Cheraghian, Shafin Rahman, Pengfei Fang, Soumava Kumar Roy, Lars Petersson, Mehrtash Harandi

Learning Statistical Texture for Semantic Segmentation AuthorsLanyun Zhu, Deyi Ji, Shiping Zhu, Weihao Gan, Wei Wu, Junjie Yan

Consensus Maximisation Using Influences of Monotone Boolean Functions AuthorsRuwan Tennakoon, David Suter, Erchuan Zhang, Tat-Jun Chin, Alireza Bab-Hadiashar

MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection AuthorsVibashan VS, Vikram Gupta, Poojan Oza, Vishwanath A. Sindagi, Vishal M. Patel

Robust Point Cloud Registration Framework Based on Deep Graph Matching AuthorsKexue Fu, Shaolei Liu, Xiaoyuan Luo, Manning Wang

ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring AuthorsDongxu Li, Chenchen Xu, Kaihao Zhang, Xin Yu, Yiran Zhong, Wenqi Ren, Hanna Suominen, Hongdong Li

Repurposing GANs for One-shot Semantic Part Segmentation AuthorsNontawat Tritrong, Pitchaporn Rewatbowornwong, Supasorn Suwajanakorn

What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels AuthorsJeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa

OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection AuthorsTingting Liang, Yongtao Wang, Zhi Tang, Guosheng Hu, Haibin Ling

Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing AuthorsTianfei Zhou, Wenguan Wang, Si Liu, Yi Yang, Luc Van Gool

Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification AuthorsFengxiang Yang, Zhun Zhong, Zhiming Luo, Yuanzheng Cai, Yaojin Lin, Shaozi Li, Nicu Sebe

Behavior-Driven Synthesis of Human Dynamics AuthorsAndreas Blattmann, Timo Milbich, Michael Dorkenwald, Björn Ommer

How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D Lines AuthorsKunal Chelani, Fredrik Kahl, Torsten Sattler

Multiple Instance Captioning: Learning Representations from Histopathology Textbooks and Articles AuthorsJevgenij Gamper, Nasir Rajpoot

Knowledge Evolution in Neural Networks AuthorsAhmed Taha, Abhinav Shrivastava, Larry Davis

MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation AuthorsXiaoqing Guo, Chen Yang, Baopu Li, Yixuan Yuan

BASAR:Black-box Attack on Skeletal Action Recognition AuthorsYunfeng Diao, Tianjia Shao, Yong-Liang Yang, Kun Zhou, He Wang

Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation AuthorsGengcong Yang, Jingyi Zhang, Yong Zhang, Baoyuan Wu, Yujiu Yang

Open-book Video Captioning with Retrieve-Copy-Generate Network AuthorsZiqi Zhang, Zhongang Qi, Chunfeng Yuan, Ying Shan, Bing Li, Ying Deng, Weiming Hu

Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack AuthorsHe Wang, Feixiang He, Zhexi Peng, Tianjia Shao, Yong-Liang Yang, Kun Zhou, David Hogg

PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency AuthorsXuyang Bai, Zixin Luo, Lei Zhou, Hongkai Chen, Lei Li, Zeyu Hu, Hongbo Fu, Chiew-Lan Tai

Contrastive Neural Architecture Search with Neural Architecture Comparators AuthorsYaofo Chen, Yong Guo, Qi Chen, Minli Li, Wei Zeng, Yaowei Wang, Mingkui Tan

NeX: Real-time View Synthesis with Neural Basis Expansion AuthorsSuttisak Wizadwongsa, Pakkapon Phongthawee, Jiraphon Yenphraphai, Supasorn Suwajanakorn

ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis AuthorsYinan He, Bei Gan, Siyu Chen, Yichun Zhou, Guojun Yin, Luchuan Song, Lu Sheng, Jing Shao, Ziwei Liu

Manifold Regularized Dynamic Network Pruning AuthorsYehui Tang, Yunhe Wang, Yixing Xu, Yiping Deng, Chao Xu, Dacheng Tao, Chang Xu

AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation AuthorsDenis Gudovskiy, Luca Rigazio, Shun Ishizaka, Kazuki Kozuka, Sotaro Tsukizawa

Limitations of Post-Hoc Feature Alignment for Robustness AuthorsCollin Burns, Jacob Steinhardt

VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples AuthorsTian Pan, Yibing Song, Tianyu Yang, Wenhao Jiang, Wei Liu

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding AuthorsBo Sun, Banghuai Li, Shengcai Cai, Ye Yuan, Chi Zhang

SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distance AuthorsFu-Zhao Ou, Xingyu Chen, Ruixin Zhang, Yuge Huang, Shaoxin Li, Jilin Li, Yong Li, Liujuan Cao, Yuan-Gen Wang

Reformulating HOI Detection as Adaptive Set Prediction AuthorsMingfei Chen, Yue Liao, Si Liu, Zhiyuan Chen, Fei Wang, Chen Qian

FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space AuthorsQuande Liu, Cheng Chen, Jing Qin, Qi Dou, Pheng-Ann Heng

Spatially Consistent Representation Learning AuthorsByungseok Roh, Wuhyun Shin, Ildoo Kim, Sungwoong Kim

Involution: Inverting the Inherence of Convolution for Visual Recognition AuthorsDuo Li, Jie Hu, Changhu Wang, Xiangtai Li, Qi She, Lei Zhu, Tong Zhang, Qifeng Chen

Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations AuthorsUmberto Michieli, Pietro Zanuttigh

Holistic 3D Scene Understanding from a Single Image with Implicit Representation AuthorsCheng Zhang, Zhaopeng Cui, Yinda Zhang, Bing Zeng, Marc Pollefeys, Shuaicheng Liu

Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition AuthorsShancheng Fang, Hongtao Xie, Yuxin Wang, Zhendong Mao, Yongdong Zhang

Affect2MM: Affective Analysis of Multimedia Content Using Emotion Causality AuthorsTrisha Mittal, Puneet Mathur, Aniket Bera, Dinesh Manocha

MagFace: A Universal Representation for Face Recognition and Quality Assessment AuthorsQiang Meng, Shichao Zhao, Zhida Huang, Feng Zhou

Temporal Action Segmentation from Timestamp Supervision AuthorsZhe Li, Yazan Abu Farha, Juergen Gall

SMPLicit: Topology-aware Generative Model for Clothed People AuthorsEnric Corona, Albert Pumarola, Guillem Alenyà, Gerard Pons-Moll, Francesc Moreno-Noguer

Fast and Accurate Model Scaling AuthorsPiotr Dollár, Mannat Singh, Ross Girshick

Diverse Semantic Image Synthesis via Probability Distribution Modeling AuthorsZhentao Tan, Menglei Chai, Dongdong Chen, Jing Liao, Qi Chu, Bin Liu, Gang Hua, Nenghai Yu

CoMoGAN: continuous model-guided image-to-image translation AuthorsFabio Pizzati, Pietro Cerri, Raoul de Charette

The Semi-Supervised iNaturalist-Aves Challenge at FGVC7 Workshop AuthorsJong-Chyi Su, Subhransu Maji

CRFace: Confidence Ranker for Model-Agnostic Face Detection Refinement AuthorsNoranart Vesdapunt, Baoyuan Wang

Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging AuthorsTao Huang, Weisheng Dong, Xin Yuan, Jinjian Wu, Guangming Shi

Learnable Companding Quantization for Accurate Low-bit Neural Networks AuthorsKohei Yamamoto

Deep Dual Consecutive Network for Human Pose Estimation AuthorsZhenguang Liu, Haoming Chen, Runyang Feng, Shuang Wu, Shouling Ji, Bailin Yang, Xun Wang

Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator AuthorsSian-Yao Huang, Wei-Ta Chu

ACTION-Net: Multipath Excitation for Action Recognition AuthorsZhengwei Wang, Qi She, Aljosa Smolic

Cross-Domain Similarity Learning for Face Recognition in Unseen Domains AuthorsMasoud Faraki, Xiang Yu, Yi-Hsuan Tsai, Yumin Suh, Manmohan Chandraker

Uncertainty-guided Model Generalization to Unseen Domains AuthorsFengchun Qiao, Xi Peng

Student-Teacher Learning from Clean Inputs to Noisy Inputs AuthorsGuanzhe Hong, Zhiyuan Mao, Xiaojun Lin, Stanley H. Chan

Reconsidering Representation Alignment for Multi-view Clustering AuthorsDaniel J. Trosten, Sigurd Løkse, Robert Jenssen, Michael Kampffmeyer

Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding AuthorsXin Wen, Zhizhong Han, Yan-Pei Cao, Pengfei Wan, Wen Zheng, Yu-Shen Liu

Learning a Proposal Classifier for Multiple Object Tracking AuthorsPeng Dai, Renliang Weng, Wongun Choi, Changshui Zhang, Zhangping He, Wei Ding

Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images AuthorsHaolin Liu, Anran Lin, Xiaoguang Han, Lei Yang, Yizhou Yu, Shuguang Cui

Semi-Supervised Video Deraining with Dynamical Rain Generator AuthorsZongsheng Yue, Jianwen Xie, Qian Zhao, Deyu Meng

Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion AuthorsHo Kei Cheng, Yu-Wing Tai, Chi-Keung Tang

Monte Carlo Scene Search for 3D Scene Understanding AuthorsShreyas Hampali, Sinisa Stekovic, Sayan Deb Sarkar, Chetan Srinivasa Kumar, Friedrich Fraundorfer, Vincent Lepetit

3DCaricShop: A Dataset and A Baseline Method for Single-view 3D Caricature Face Reconstruction AuthorsYuda Qiu, Xiaojie Xu, Lingteng Qiu, Yan Pan, Yushuang Wu, Weikai Chen, Xiaoguang Han

Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation AuthorsMingi Ji, Seungjae Shin, Seunghyun Hwang, Gibeom Park, Il-Chul Moon

Rotation Coordinate Descent for Fast Globally Optimal Rotation Averaging AuthorsÁlvaro Parra, Shin-Fang Chng, Tat-Jun Chin, Anders Eriksson, Ian Reid

Beyond Image to Depth: Improving Depth Prediction using Echoes AuthorsKranti Kumar Parida, Siddharth Srivastava, Gaurav Sharma

Track to Detect and Segment: An Online Multi-Object Tracker AuthorsJialian Wu, Jiale Cao, Liangchen Song, Yu Wang, Ming Yang, Junsong Yuan

Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation AuthorsJungbeom Lee, Eunji Kim, Sungroh Yoon

BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation AuthorsJungbeom Lee, Jihun Yi, Chaehun Shin, Sungroh Yoon

Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection AuthorsJiaming Li, Hongtao Xie, Jiahong Li, Zhongyuan Wang, Yongdong Zhang

Back to the Feature: Learning Robust Camera Localization from Pixels to Pose AuthorsPaul-Edouard Sarlin, Ajaykumar Unagar, Måns Larsson, Hugo Germain, Carl Toft, Viktor Larsson, Marc Pollefeys, Vincent Lepetit, Lars Hammarstrand, Fredrik Kahl, Torsten Sattler

Learning Discriminative Prototypes with Dynamic Time Warping AuthorsXiaobin Chang, Frederick Tung, Greg Mori

Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE AuthorsJialun Peng, Dong Liu, Songcen Xu, Houqiang Li

On Semantic Similarity in Video Retrieval AuthorsMichael Wray, Hazel Doughty, Dima Damen

SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation AuthorsDongfang Liu, Yiming Cui, Wenbo Tan, Yingjie Chen

Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild AuthorsZhaoyuan Yin, Jia Zheng, Weixin Luo, Shenhan Qian, Hanling Zhang, Shenghua Gao

Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks AuthorsDespoina Paschalidou, Angelos Katharopoulos, Andreas Geiger, Sanja Fidler

CDFI: Compression-Driven Network Design for Frame Interpolation AuthorsTianyu Ding, Luming Liang, Zhihui Zhu, Ilya Zharkov

Generic Perceptual Loss for Modeling Structured Output Dependencies AuthorsYifan Liu, Hao Chen, Yu Chen, Wei Yin, Chunhua Shen

Dynamic Transfer for Multi-Source Domain Adaptation AuthorsYunsheng Li, Lu Yuan, Yinpeng Chen, Pei Wang, Nuno Vasconcelos

Skeleton Merger: an Unsupervised Aligned Keypoint Detector AuthorsRuoxi Shi, Zhengrong Xue, Yang You, Cewu Lu

Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark AuthorsJoakim Bruslund Haurum, Thomas B. Moeslund

Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild AuthorsAkash Sengupta, Ignas Budvytis, Roberto Cipolla

Video Class Agnostic Segmentation Benchmark for Autonomous Driving AuthorsMennatullah Siam, Alex Kendall, Martin Jagersand

Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation AuthorsM. Saquib Sarfraz, Naila Murray, Vivek Sharma, Ali Diba, Luc Van Gool, Rainer Stiefelhagen

MoViNets: Mobile Video Networks for Efficient Video Recognition AuthorsDan Kondratyuk, Liangzhe Yuan, Yandong Li, Li Zhang, Mingxing Tan, Matthew Brown, Boqing Gong

Context-aware Biaffine Localizing Network for Temporal Sentence Grounding AuthorsDaizong Liu, Xiaoye Qu, Jianfeng Dong, Pan Zhou, Yu Cheng, Wei Wei, Zichuan Xu, Yulai Xie

Anchor-Free Person Search AuthorsYichao Yan, Jinpeng Li, Jie Qin, Song Bai, Shengcai Liao, Li Liu, Fan Zhu, Ling Shao

Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking AuthorsNing Wang, Wengang Zhou, Jie Wang, Houqaing Li

Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales AuthorsYifan Sun, Yuke Zhu, Yuhan Zhang, Pengkun Zheng, Xi Qiu, Chi Zhang, Yichen Wei

Context-Aware Layout to Image Generation with Enhanced Object Appearance AuthorsSen He, Wentong Liao, Michael Ying Yang, Yongxin Yang, Yi-Zhe Song, Bodo Rosenhahn, Tao Xiang

Human-like Controllable Image Captioning with Verb-specific Semantic Roles AuthorsLong Chen, Zhihong Jiang, Jun Xiao, Wei Liu

Deep Implicit Moving Least-Squares Functions for 3D Reconstruction AuthorsShi-Lin Liu, Hao-Xiang Guo, Hao Pan, Peng-Shuai Wang, Xin Tong, Yang Liu

Group-aware Label Transfer for Domain Adaptive Person Re-identification AuthorsKecheng Zheng, Wu Liu, Lingxiao He, Tao Mei, Jiebo Luo, Zheng-Jun Zha

Transferable Semantic Augmentation for Domain Adaptation AuthorsShuang Li, Mixue Xie, Kaixiong Gong, Chi Harold Liu, Yulin Wang, Wei Li

MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition AuthorsShuang Li, Kaixiong Gong, Chi Harold Liu, Yulin Wang, Feng Qiao, Xinjing Cheng

MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation AuthorsHansheng Chen, Yuyao Huang, Wei Tian, Zhong Gao, Lu Xiong

Scaling Local Self-Attention for Parameter Efficient Visual Backbones AuthorsAshish Vaswani, Prajit Ramachandran, Aravind Srinivas, Niki Parmar, Blake Hechtman, Jonathon Shlens

Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency AuthorsQing Liu, Vignesh Ramanathan, Dhruv Mahajan, Alan Yuille, Zhenheng Yang

Efficient Regional Memory Network for Video Object Segmentation AuthorsHaozhe Xie, Hongxun Yao, Shangchen Zhou, Shengping Zhang, Wenxiu Sun

Scene-Intuitive Agent for Remote Embodied Visual Grounding AuthorsXiangru Lin, Guanbin Li, Yizhou Yu

Convex Online Video Frame Subset Selection using Multiple Criteria for Data Efficient Autonomous Driving AuthorsSoumi Das, Harikrishna Patibandla, Suparna Bhattacharya, Kshounis Bera, Niloy Ganguly, Sourangshu Bhattacharya

Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning AuthorsAmaia Salvador, Erhan Gundogdu, Loris Bazzani, Michael Donoser

Repetitive Activity Counting by Sight and Sound AuthorsYunhua Zhang, Ling Shao, Cees G. M. Snoek

Temporal Context Aggregation Network for Temporal Action Proposal Refinement AuthorsZhiwu Qing, Haisheng Su, Weihao Gan, Dongliang Wang, Wei Wu, Xiang Wang, Yu Qiao, Junjie Yan, Changxin Gao, Nong Sang

M3DSSD: Monocular 3D Single Stage Object Detector AuthorsShujie Luo, Hang Dai, Ling Shao, Yong Ding

Structure-Aware Face Clustering on a Large-Scale Graph with $\bf{10^{7}}$ Nodes AuthorsShuai Shen, Wanhua Li, Zheng Zhu, Guan Huang, Dalong Du, Jiwen Lu, Jie Zhou

Dynamic Slimmable Network AuthorsChanglin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, Xiaojun Chang

Affective Processes: stochastic modelling of temporal context for emotion and facial expression recognition AuthorsEnrique Sanchez, Mani Kumar Tellamekala, Michel Valstar, Georgios Tzimiropoulos

Diverse Branch Block: Building a Convolution as an Inception-like Unit AuthorsXiaohan Ding, Xiangyu Zhang, Jungong Han, Guiguang Ding

DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation AuthorsSeunghun Lee, Sunghyun Cho, Sunghoon Im

Efficient Feature Transformations for Discriminative and Generative Continual Learning AuthorsVinay Kumar Verma, Kevin J Liang, Nikhil Mehta, Piyush Rai, Lawrence Carin

Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation AuthorsYuntong Ye, Yi Chang, Hanyu Zhou, Luxin Yan

SSLayout360: Semi-Supervised Indoor Layout Estimation from 360-Degree Panorama AuthorsPhi Vu Tran

Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting AuthorsAyan Kumar Bhunia, Pinaki Nath Chowdhury, Yongxin Yang, Timothy M. Hospedales, Tao Xiang, Yi-Zhe Song

I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors AuthorsChaoqi Chen, Zebiao Zheng, Yue Huang, Xinghao Ding, Yizhou Yu

Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning AuthorsZheda Mai, Ruiwen Li, Hyunwoo Kim, Scott Sanner

Robust and Accurate Object Detection via Adversarial Learning AuthorsXiangning Chen, Cihang Xie, Mingxing Tan, Li Zhang, Cho-Jui Hsieh, Boqing Gong

More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval AuthorsAyan Kumar Bhunia, Pinaki Nath Chowdhury, Aneeshan Sain, Yongxin Yang, Tao Xiang, Yi-Zhe Song

Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution AuthorsChi Zhang, Baoxiong Jia, Song-Chun Zhu, Yixin Zhu

ACRE: Abstract Causal REasoning Beyond Covariation AuthorsChi Zhang, Baoxiong Jia, Mark Edmonds, Song-Chun Zhu, Yixin Zhu

Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification AuthorsPeng Wang, Kai Han, Xiu-Shen Wei, Lei Zhang, Lei Wang

Bidirectional Projection Network for Cross Dimension Scene Understanding AuthorsWenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong

Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation AuthorsDohun Lim, Hyeonseok Lee, Sungchan Kim

Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modeling AuthorsZhichao Huang, Xintong Han, Jia Xu, Tong Zhang

Distilling Object Detectors via Decoupled Features AuthorsJianyuan Guo, Kai Han, Yunhe Wang, Han Wu, Xinghao Chen, Chunjing Xu, Chang Xu

Tuning IR-cut Filter for Illumination-aware Spectral Reconstruction from RGB AuthorsBo Sun, Junchi Yan, Xiao Zhou, Yinqiang Zheng

LiBRe: A Practical Bayesian Approach to Adversarial Detection AuthorsZhijie Deng, Xiao Yang, Shizhen Xu, Hang Su, Jun Zhu

Video Rescaling Networks with Joint Optimization Strategies for Downscaling and Upscaling AuthorsYan-Cheng Huang, Yi-Hsin Chen, Cheng-You Lu, Hui-Po Wang, Wen-Hsiao Peng, Ching-Chun Huang

SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences AuthorsShun-Cheng Wu, Johanna Wald, Keisuke Tateno, Nassir Navab, Federico Tombari

Embedding Transfer with Label Relaxation for Improved Metric Learning AuthorsSungyeon Kim, Dongwon Kim, Minsu Cho, Suha Kwak

Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation AuthorsZixiang Zhou, Yang Zhang, Hassan Foroosh

Picasso: A CUDA-based Library for Deep Learning over 3D Meshes AuthorsHuan Lei, Naveed Akhtar, Ajmal Mian

Learning Placeholders for Open-Set Recognition AuthorsDa-Wei Zhou, Han-Jia Ye, De-Chuan Zhan

Bridging the Visual Gap: Wide-Range Image Blending AuthorsChia-Ni Lu, Ya-Chu Chang, Wei-Chen Chiu

ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning AuthorsDominik Bauer, Timothy Patten, Markus Vincze

Zero-shot Adversarial Quantization AuthorsYuang Liu, Wei Zhang, Jun Wang

Generalizing to the Open World: Deep Visual Odometry with Online Adaptation AuthorsShunkai Li, Xin Wu, Yingdian Cao, Hongbin Zha

LiDAR R-CNN: An Efficient and Universal 3D Object Detector AuthorsZhichao Li, Feng Wang, Naiyan Wang

Checkerboard Context Model for Efficient Learned Image Compression AuthorsDailan He, Yaoyan Zheng, Baocheng Sun, Yan Wang, Hongwei Qin

POSEFusion: Pose-guided Selective Fusion for Single-view Human Volumetric Capture AuthorsZhe Li, Tao Yu, Zerong Zheng, Kaiwen Guo, Yebin Liu

Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton AuthorsXi Zhang, Xiaolin Wu

No frame left behind: Full Video Action Recognition AuthorsXin Liu, Silvia L. Pintea, Fatemeh Karimi Nejadasl, Olaf Booij, Jan C. van Gemert

Capsule Network is Not More Robust than Convolutional Network AuthorsJindong Gu, Volker Tresp, Han Hu

Cloud2Curve: Generation and Vectorization of Parametric Sketches AuthorsAyan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song

TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events AuthorsLi Xu, He Huang, Jun Liu

Enhancing the Transferability of Adversarial Attacks through Variance Tuning AuthorsXiaosen Wang, Kun He

RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening AuthorsSungha Choi, Sanghun Jung, Huiwon Yun, Joanne Kim, Seungryong Kim, Jaegul Choo

StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval AuthorsAneeshan Sain, Ayan Kumar Bhunia, Yongxin Yang, Tao Xiang, Yi-Zhe Song

Slimmable Compressive Autoencoders for Practical Neural Image Compression AuthorsFei Yang, Luis Herranz, Yongmei Cheng, Mikhail G. Mozerov

Adaptive Methods for Real-World Domain Generalization AuthorsAbhimanyu Dubey, Vignesh Ramanathan, Alex Pentland, Dhruv Mahajan

High-Fidelity and Arbitrary Face Editing AuthorsYue Gao, Fangyun Wei, Jianmin Bao, Shuyang Gu, Dong Chen, Fang Wen, Zhouhui Lian

High-fidelity Face Tracking for AR/VR via Deep Lighting Adaptation AuthorsLele Chen, Chen Cao, Fernando De la Torre, Jason Saragih, Chenliang Xu, Yaser Sheikh

Domain-robust VQA with diverse datasets and methods but no target labels AuthorsMingda Zhang, Tristan Maidment, Ahmad Diab, Adriana Kovashka, Rebecca Hwa

AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning AuthorsMadeleine Grunde-McLaughlin, Ranjay Krishna, Maneesh Agrawala

Noise-resistant Deep Metric Learning with Ranking-based Instance Selection AuthorsChang Liu, Han Yu, Boyang Li, Zhiqi Shen, Zhanning Gao, Peiran Ren, Xuansong Xie, Lizhen Cui, Chunyan Miao

Face Forensics in the Wild AuthorsTianfei Zhou, Wenguan Wang, Zhiyuan Liang, Jianbing Shen

Fully Convolutional Scene Graph Generation AuthorsHengyue Liu, Ning Yan, Masood S. Mortazavi, Bir Bhanu

Self-Guided and Cross-Guided Learning for Few-Shot Segmentation AuthorsBingfeng Zhang, Jimin Xiao, Terry Qin

Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking AuthorsJiawei He, Zehao Huang, Naiyan Wang, Zhaoxiang Zhang

Repopulating Street Scenes AuthorsYifan Wang, Andrew Liu, Richard Tucker, Jiajun Wu, Brian L. Curless, Steven M. Seitz, Noah Snavely

Delving into Localization Errors for Monocular 3D Object Detection AuthorsXinzhu Ma, Yinmin Zhang, Dan Xu, Dongzhan Zhou, Shuai Yi, Haojie Li, Wanli Ouyang

Model-Contrastive Federated Learning AuthorsQinbin Li, Bingsheng He, Dawn Song

Locate then Segment: A Strong Pipeline for Referring Image Segmentation AuthorsYa Jing, Tao Kong, Wei Wang, Liang Wang, Lei Li, Tieniu Tan

Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection AuthorsZhenyu Wang, Yali Li, Ye Guo, Lu Fang, Shengjin Wang

Distribution Alignment: A Unified Framework for Long-tail Visual Recognition AuthorsSongyang Zhang, Zeming Li, Shipeng Yan, Xuming He, Jian Sun

Source-Free Domain Adaptation for Semantic Segmentation AuthorsYuang Liu, Wei Zhang, Jun Wang

Graph Stacked Hourglass Networks for 3D Human Pose Estimation AuthorsTianhan Xu, Wataru Takano

CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning AuthorsCan Zhang, Meng Cao, Dongming Yang, Jie Chen, Yuexian Zou

Dynamic Domain Adaptation for Efficient Inference AuthorsShuang Li, Jinming Zhang, Wenxuan Ma, Chi Harold Liu, Wei Li

Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction AuthorsShanyan Guan, Jingwei Xu, Yunbo Wang, Bingbing Ni, Xiaokang Yang

Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection AuthorsLi Wang, Liang Du, Xiaoqing Ye, Yanwei Fu, Guodong Guo, Xiangyang Xue, Jianfeng Feng, Li Zhang

Read and Attend: Temporal Localisation in Sign Language Videos AuthorsGül Varol, Liliane Momeni, Samuel Albanie, Triantafyllos Afouras, Andrew Zisserman

Benchmarking Representation Learning for Natural World Image Collections AuthorsGrant Van Horn, Elijah Cole, Sara Beery, Kimberly Wilber, Serge Belongie, Oisin Mac Aodha

Recognizing Actions in Videos from Unseen Viewpoints AuthorsAJ Piergiovanni, Michael S. Ryoo

Visual Room Rearrangement AuthorsLuca Weihs, Matt Deitke, Aniruddha Kembhavi, Roozbeh Mottaghi

Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers AuthorsAntoine Miech, Jean-Baptiste Alayrac, Ivan Laptev, Josef Sivic, Andrew Zisserman

Boundary IoU: Improving Object-Centric Image Segmentation Evaluation AuthorsBowen Cheng, Ross Girshick, Piotr Dollár, Alexander C. Berg, Alexander Kirillov

Rectification-based Knowledge Retention for Continual Learning AuthorsPravendra Singh, Pratik Mazumder, Piyush Rai, Vinay P. Namboodiri

DAP: Detection-Aware Pre-training with Weak Supervision AuthorsYuanyi Zhong, Jianfeng Wang, Lijuan Wang, Jian Peng, Yu-Xiong Wang, Lei Zhang

Denoise and Contrast for Category Agnostic Shape Completion AuthorsAntonio Alliegro, Diego Valsesia, Giulia Fracastoro, Enrico Magli, Tatiana Tommasi

Mask-ToF: Learning Microlens Masks for Flying Pixel Correction in Time-of-Flight Imaging AuthorsIlya Chugunov, Seung-Hwan Baek, Qiang Fu, Wolfgang Heidrich, Felix Heide

SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification AuthorsZijian Hu, Zhengyu Yang, Xuefeng Hu, Ram Nevatia

Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark AuthorsXiao Wang, Xiujun Shu, Zhipeng Zhang, Bo Jiang, Yaowei Wang, Yonghong Tian, Feng Wu

Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation AuthorsXiangyu Yue, Zangwei Zheng, Shanghang Zhang, Yang Gao, Trevor Darrell, Kurt Keutzer, Alberto Sangiovanni Vincentelli

Convolutional Hough Matching Networks AuthorsJuhong Min, Minsu Cho

Online Learning of a Probabilistic and Adaptive Scene Representation AuthorsZike Yan, Xin Wang, Hongbin Zha

SRWarp: Generalized Image Super-Resolution under Arbitrary Transformation AuthorsSanghyun Son, Kyoung Mu Lee

Fourier Contour Embedding for Arbitrary-Shaped Text Detection AuthorsYiqin Zhu, Jianyong Chen, Lingyu Liang, Zhanghui Kuang, Lianwen Jin, Wayne Zhang

Brittle Features May Help Anomaly Detection AuthorsKimberly T. Mai, Toby Davies, Lewis D. Griffin

Camouflaged Object Segmentation with Distraction Mining AuthorsHaiyang Mei, Ge-Peng Ji, Ziqi Wei, Xin Yang, Xiaopeng Wei, Deng-Ping Fan

IB-DRR: Incremental Learning with Information-Back Discrete Representation Replay AuthorsJian Jiang, Edoardo Cetin, Oya Celiktutan

Visualizing Adapted Knowledge in Domain Transfer AuthorsYunzhong Hou, Liang Zheng

GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review AuthorsAlceu Bissoto, Eduardo Valle, Sandra Avila

MetricOpt: Learning to Optimize Black-Box Evaluation Metrics AuthorsChen Huang, Shuangfei Zhai, Pengsheng Guo, Josh Susskind

Multi-task Learning with Attention for End-to-end Autonomous Driving AuthorsKeishi Ishihara, Anssi Kanervisto, Jun Miura, Ville Hautamäki

MVFuseNet: Improving End-to-End Object Detection and Motion Forecasting through Multi-View Fusion of LiDAR Data AuthorsAnkit Laddha, Shivam Gautam, Stefan Palombo, Shreyash Pandey, Carlos Vallespi-Gonzalez

DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation AuthorsXinyi Wu, Zhenyao Wu, Hao Guo, Lili Ju, Song Wang

A Strong Baseline for Vehicle Re-Identification AuthorsSu V. Huynh, Nam H. Nguyen, Ngoc T. Nguyen, Vinh TQ. Nguyen, Chau Huynh, Chuong Nguyen

Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation AuthorsHang Zhou, Yasheng Sun, Wayne Wu, Chen Change Loy, Xiaogang Wang, Ziwei Liu

Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation AuthorsRyuhei Hamaguchi, Yasutaka Furukawa, Masaki Onishi, Ken Sakurada

ManipulaTHOR: A Framework for Visual Object Manipulation AuthorsKiana Ehsani, Winson Han, Alvaro Herrasti, Eli VanderBilt, Luca Weihs, Eric Kolve, Aniruddha Kembhavi, Roozbeh Mottaghi

Hierarchical Motion Understanding via Motion Programs AuthorsSumith Kulal, Jiayuan Mao, Alex Aiken, Jiajun Wu

KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control AuthorsTomas Jakab, Richard Tucker, Ameesh Makadia, Jiajun Wu, Noah Snavely, Angjoo Kanazawa

Motion Representations for Articulated Animation AuthorsAliaksandr Siarohin, Oliver J. Woodford, Jian Ren, Menglei Chai, Sergey Tulyakov

Skip-Convolutions for Efficient Video Processing AuthorsAmirhossein Habibian, Davide Abati, Taco S. Cohen, Babak Ehteshami Bejnordi

SBNet: Segmentation-based Network for Natural Language-based Vehicle Search AuthorsSangrok Lee, Taekang Woo, Sang Hun Lee

Region-Adaptive Deformable Network for Image Quality Assessment AuthorsShuwei Shi, Qingyan Bai, Mingdeng Cao, Weihao Xia, Jiahao Wang, Yifan Chen, Yujiu Yang

Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities AuthorsJulia Rosenzweig, Joachim Sicking, Sebastian Houben, Michael Mock, Maram Akila

Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-scale Distributional Dynamics AuthorsStone Yun, Alexander Wong

Class-Incremental Experience Replay for Continual Learning under Concept Drift AuthorsŁukasz Korycki, Bartosz Krawczyk

The 5th AI City Challenge AuthorsMilind Naphade, Shuo Wang, David C. Anastasiu, Zheng Tang, Ming-Ching Chang, Xiaodong Yang, Yue Yao, Liang Zheng, Pranamesh Chakraborty, Anuj Sharma, Qi Feng, Vitaly Ablavsky, Stan Sclaroff

Delving into Data: Effectively Substitute Training for Black-box Attack AuthorsWenxuan Wang, Bangjie Yin, Taiping Yao, Li Zhang, Yanwei Fu, Shouhong Ding, Jilin Li, Feiyue Huang, Xiangyang Xue

An Exploration into why Output Regularization Mitigates Label Noise AuthorsNeta Shoham, Tomer Avidor, Nadav Israel

Detecting and Matching Related Objects with One Proposal Multiple Predictions AuthorsYang Liu, Luiz G. Hafemann, Michael Jamieson, Mehrsan Javan

Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets AuthorsYuan-Hong Liao, Amlan Kar, Sanja Fidler

Instance-wise Causal Feature Selection for Model Interpretation AuthorsPranoy Panda, Sai Srinivas Kancheti, Vineeth N Balasubramanian

Unsupervised Multi-Source Domain Adaptation for Person Re-Identification AuthorsZechen Bai, Zhigang Wang, Jian Wang, Di Hu, Errui Ding

Three-stream network for enriched Action Recognition AuthorsIvaxi Sheth

Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation AuthorsSimon Reiß, Constantin Seibold, Alexander Freytag, Erik Rodner, Rainer Stiefelhagen

Width Transfer: On the (In)variance of Width Optimization AuthorsTing-Wu Chin, Diana Marculescu, Ari S. Morcos

Unsupervised 3D Shape Completion through GAN Inversion AuthorsJunzhe Zhang, Xinyi Chen, Zhongang Cai, Liang Pan, Haiyu Zhao, Shuai Yi, Chai Kiat Yeo, Bo Dai, Chen Change Loy

FrameExit: Conditional Early Exiting for Efficient Video Recognition AuthorsAmir Ghodrati, Babak Ehteshami Bejnordi, Amirhossein Habibian

Towards Fair Federated Learning with Zero-Shot Data Augmentation AuthorsWeituo Hao, Mostafa El-Khamy, Jungwon Lee, Jianyi Zhang, Kevin J Liang, Changyou Chen, Lawrence Carin

Extreme Rotation Estimation using Dense Correlation Volumes AuthorsRuojin Cai, Bharath Hariharan, Noah Snavely, Hadar Averbuch-Elor

Shot Contrastive Self-Supervised Learning for Scene Boundary Detection AuthorsShixing Chen, Xiaohan Nie, David Fan, Dongqing Zhang, Vimal Bhat, Raffay Hamid

HOTR: End-to-End Human-Object Interaction Detection with Transformers AuthorsBumsoo Kim, Junhyun Lee, Jaewoo Kang, Eun-Sol Kim, Hyunwoo J. Kim

Boosting Co-teaching with Compression Regularization for Label Noise AuthorsYingyi Chen, Xi Shen, Shell Xu Hu, Johan A. K. Suykens

Unsupervised Detection of Cancerous Regions in Histology Imagery using Image-to-Image Translation AuthorsDejan Stepec, Danijel Skocaj

Pushing it out of the Way: Interactive Visual Navigation AuthorsKuo-Hao Zeng, Luca Weihs, Ali Farhadi, Roozbeh Mottaghi

Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection AuthorsJiachen Li, Bowen Cheng, Rogerio Feris, Jinjun Xiong, Thomas S. Huang, Wen-Mei Hwu, Humphrey Shi

Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answering AuthorsJungin Park, Jiyoung Lee, Kwanghoon Sohn

Decoupled Dynamic Filter Networks AuthorsJingkai Zhou, Varun Jampani, Zhixiong Pi, Qiong Liu, Ming-Hsuan Yang

Condensation-Net: Memory-Efficient Network Architecture with Cross-Channel Pooling Layers and Virtual Feature Maps AuthorsTse-Wei Chen, Motoki Yoshinaga, Hongxing Gao, Wei Tao, Dongchao Wen, Junjie Liu, Kinya Osa, Masami Kato

CASSOD-Net: Cascaded and Separable Structures of Dilated Convolution for Embedded Vision Systems and Applications AuthorsTse-Wei Chen, Deyu Wang, Wei Tao, Dongchao Wen, Lingxiao Yin, Tadayuki Ito, Kinya Osa, Masami Kato

The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth AuthorsJamie Watson, Oisin Mac Aodha, Victor Prisacariu, Gabriel Brostow, Michael Firman

AutoFlow: Learning a Better Training Set for Optical Flow AuthorsDeqing Sun, Daniel Vlasic, Charles Herrmann, Varun Jampani, Michael Krainin, Huiwen Chang, Ramin Zabih, William T. Freeman, Ce Liu

LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search AuthorsBin Yan, Houwen Peng, Kan Wu, Dong Wang, Jianlong Fu, Huchuan Lu

Ensembling with Deep Generative Views AuthorsLucy Chai, Jun-Yan Zhu, Eli Shechtman, Phillip Isola, Richard Zhang

A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning AuthorsChristoph Feichtenhofer, Haoqi Fan, Bo Xiong, Ross Girshick, Kaiming He