CVPR - arXivDaily 期刊&会议

2103.13660 2021-03-26 eess.IV cs.CV

Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation

Yuntong Ye, Yi Chang, Hanyu Zhou, Luxin Yan

Comments 10 pages, Accepted by 2021 CVPR

2103.13558 2021-03-26 cs.LG cs.AI cs.CV

Efficient Feature Transformations for Discriminative and Generative Continual Learning

Vinay Kumar Verma, Kevin J Liang, Nikhil Mehta, Piyush Rai, Lawrence Carin

Comments Accepted in CVPR 2021

2012.13253 2021-03-26 cs.LG cs.AI cs.CV

Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencoder

Tal Daniel, Aviv Tamar

Comments CVPR 2021, Extended version. Code and additional information is available on the project website - https://taldatech.github.io/soft-intro-vae-web

2011.09230 2021-03-26 cs.CV

FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation

Jaemin Na, Heechul Jung, Hyung Jin Chang, Wonjun Hwang

Comments Accepted to CVPR 2021

2002.05712 2021-03-26 cs.LG cs.CV stat.ML

Cross-Iteration Batch Normalization

Zhuliang Yao, Yue Cao, Shuxin Zheng, Gao Huang, Stephen Lin

Comments Accepted to CVPR 2021

2103.13372 2021-03-25 cs.CV cs.LG

Affective Processes: stochastic modelling of temporal context for emotion and facial expression recognition

Enrique Sanchez, Mani Kumar Tellamekala, Michel Valstar, Georgios Tzimiropoulos

Comments Accepted at CVPR 2021

2103.13258 2021-03-25 cs.CV

Dynamic Slimmable Network

Changlin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, Xiaojun Chang

Comments Accepted to CVPR 2021 as an Oral Presentation

2103.13164 2021-03-25 cs.CV

M3DSSD: Monocular 3D Single Stage Object Detector

Shujie Luo, Hang Dai, Ling Shao, Yong Ding

Comments Accepted to CVPR 2021

2103.13061 2021-03-25 cs.CV

Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning

Amaia Salvador, Erhan Gundogdu, Loris Bazzani, Michael Donoser

Comments CVPR 2021

2103.13029 2021-03-25 cs.CV

Jo-SRC: A Contrastive Approach for Combating Noisy Labels

Yazhou Yao, Zeren Sun, Chuanyi Zhang, Fumin Shen, Qi Wu, Jian Zhang, Zhenmin Tang

Comments accepted by IEEE Conference on Computer Vision and Pattern Recognition, 2021

2103.13021 2021-03-25 cs.LG cs.CV

Convex Online Video Frame Subset Selection using Multiple Criteria for Data Efficient Autonomous Driving

Soumi Das, Harikrishna Patibandla, Suparna Bhattacharya, Kshounis Bera, Niloy Ganguly, Sourangshu Bhattacharya

Comments Submitted to CVPR 2020

2103.12944 2021-03-25 cs.CV

Scene-Intuitive Agent for Remote Embodied Visual Grounding

Xiangru Lin, Guanbin Li, Yizhou Yu

Comments Accepted by CVPR 2021

2103.12886 2021-03-25 cs.CV

Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency

Qing Liu, Vignesh Ramanathan, Dhruv Mahajan, Alan Yuille, Zhenheng Yang

Comments 14 pages, 8 figures, accepted by CVPR 2021

2103.12605 2021-03-25 cs.CV

MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation

Hansheng Chen, Yuyao Huang, Wei Tian, Zhong Gao, Lu Xiong

Comments CVPR 2021

2103.11681 2021-03-25 cs.CV

Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking

Ning Wang, Wengang Zhou, Jie Wang, Houqaing Li

Comments To appear in CVPR 2021 (Oral)

2103.01100 2021-03-25 cs.CV

Categorical Depth Distribution Network for Monocular 3D Object Detection

Cody Reading, Ali Harakeh, Julia Chae, Steven L. Waslander

Comments Accepted in CVPR 2021

2004.06711 2021-03-25 cs.CV

Deformable Siamese Attention Networks for Visual Object Tracking

Yuechen Yu, Yilei Xiong, Weilin Huang, Matthew R. Scott

Comments CVPR 2020, with code available at: https://github.com/msight-tech/research-siamattn

2103.12562 2021-03-24 cs.CV

Transferable Semantic Augmentation for Domain Adaptation

Shuang Li, Mixue Xie, Kaixiong Gong, Chi Harold Liu, Yulin Wang, Wei Li

Comments Accepted as CVPR 2021. The code is publicly available at https://github.com/BIT-DA/TSA

2103.12366 2021-03-24 cs.CV

Group-aware Label Transfer for Domain Adaptive Person Re-identification

Kecheng Zheng, Wu Liu, Lingxiao He, Tao Mei, Jiebo Luo, Zheng-Jun Zha

Comments Accepted by CVPR 2021

2103.12204 2021-03-24 cs.CV cs.AI cs.CL cs.MM

Human-like Controllable Image Captioning with Verb-specific Semantic Roles

Long Chen, Zhihong Jiang, Jun Xiao, Wei Liu

Comments Accepted by CVPR 2021. The code is available at: https://github.com/mad-red/VSR-guided-CIC

2007.08558 2021-03-24 cs.CV cs.LG

On Robustness and Transferability of Convolutional Neural Networks

Josip Djolonga, Jessica Yung, Michael Tschannen, Rob Romijnders, Lucas Beyer, Alexander Kolesnikov, Joan Puigcerver, Matthias Minderer, Alexander D'Amour, Dan Moldovan, Sylvain Gelly, Neil Houlsby, Xiaohua Zhai, Mario Lucic

Comments Accepted at CVPR 2021

2103.11897 2021-03-23 cs.CV

Context-Aware Layout to Image Generation with Enhanced Object Appearance

Sen He, Wentong Liao, Michael Ying Yang, Yongxin Yang, Yi-Zhe Song, Bodo Rosenhahn, Tao Xiang

Comments CVPR 2021

2103.11781 2021-03-23 cs.CV

Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales

Yifan Sun, Yuke Zhu, Yuhan Zhang, Pengkun Zheng, Xi Qiu, Chi Zhang, Yichen Wei

Comments 8pages, accepted by CVPR 2021

2103.11555 2021-03-23 cs.CV

Context-aware Biaffine Localizing Network for Temporal Sentence Grounding

Daizong Liu, Xiaoye Qu, Jianfeng Dong, Pan Zhou, Yu Cheng, Wei Wei, Zichuan Xu, Yulai Xie

Comments Accepted by CVPR 2021

2103.07941 2021-03-23 cs.CV

Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion

Ho Kei Cheng, Yu-Wing Tai, Chi-Keung Tang

Comments Accepted to CVPR 2021. Project page: https://hkchengrex.github.io/MiVOS/

2103.01903 2021-03-23 cs.CV

Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection

Chenchen Zhu, Fangyi Chen, Uzair Ahmed, Zhiqiang Shen, Marios Savvides

Comments CVPR 2021

2012.00321 2021-03-23 cs.CV cs.LG

Disentangling Label Distribution for Long-tailed Visual Recognition

Youngkyu Hong, Seungju Han, Kwanghee Choi, Seokjun Seo, Beomsu Kim, Buru Chang

Comments CVPR 2021

2011.12172 2021-03-23 cs.CV cs.AI

VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval

Sijie Zhu, Taojiannan Yang, Chen Chen

Comments CVPR 2021

2002.12655 2021-03-23 cs.CV cs.LG eess.IV

A U-Net Based Discriminator for Generative Adversarial Networks

Edgar Schönfeld, Bernt Schiele, Anna Khoreva

Comments CVPR 2020 (Main Conference). Code repository: https://github.com/boschresearch/unetgan

2103.10895 2021-03-22 cs.CV

Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark

Joakim Bruslund Haurum, Thomas B. Moeslund

Comments CVPR 2021. Project webpage: https://vap.aau.dk/sewer-ml/