CVPR

Revisiting Weakly Supervised Pre-Training of Visual Perception Models

Mannat Singh, Laura Gustafson, Aaron Adcock, Vinicius de Freitas Reis, Bugra Gedik, Raj Prateek Kosaraju, Dhruv Mahajan, Ross Girshick, Piotr Dollár, Laurens van der Maaten

Comments CVPR 2022

Parameter-free Online Test-time Adaptation

Malik Boudiaf, Romain Mueller, Ismail Ben Ayed, Luca Bertinetto

Comments CVPR 2022 (oral). Code available at https://github.com/fiveai/LAME

MAXIM: Multi-Axis MLP for Image Processing

Zhengzhong Tu, Hossein Talebi, Han Zhang, Feng Yang, Peyman Milanfar, Alan Bovik, Yinxiao Li

Comments CVPR 2022 Oral; Code: \url{https://github.com/google-research/maxim}

Relieving Long-tailed Instance Segmentation via Pairwise Class Balance

Yin-Yin He, Peizhen Zhang, Xiu-Shen Wei, Xiangyu Zhang, Jian Sun

Comments Accepted to CVPR 2022

Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesis

Tianhan Xu, Yasuhiro Fujita, Eiichi Matsumoto

Comments CVPR 2022. Project page: https://pfnet-research.github.io/surface-aligned-nerf/

UnweaveNet: Unweaving Activity Stories

Will Price, Carl Vondrick, Dima Damen

Comments Accepted at IEEE/CVF Computer Vision and Pattern Recognition (CVPR) 2022

Improving Subgraph Recognition with Variational Graph Information Bottleneck

Junchi Yu, Jie Cao, Ran He

Comments to appear in CVPR 2022

Contextualized Spatio-Temporal Contrastive Learning with Self-Supervision

Liangzhe Yuan, Rui Qian, Yin Cui, Boqing Gong, Florian Schroff, Ming-Hsuan Yang, Hartwig Adam, Ting Liu

Comments CVPR 2022

Fast Point Transformer

Chunghyun Park, Yoonwoo Jeong, Minsu Cho, Jaesik Park

Comments Accepted to CVPR 2022

OW-DETR: Open-world Detection Transformer

Akshita Gupta, Sanath Narayan, K J Joseph, Salman Khan, Fahad Shahbaz Khan, Mubarak Shah

Comments 16 pages, CVPR 2022 accepted

HyperInverter: Improving StyleGAN Inversion via Hypernetwork

Tan M. Dinh, Anh Tuan Tran, Rang Nguyen, Binh-Son Hua

Comments Accepted to CVPR 2022; Project page is located at https://di-mi-ta.github.io/HyperInverter/

Background Activation Suppression for Weakly Supervised Object Localization

Pingyu Wu, Wei Zhai, Yang Cao

Comments Accepted by CVPR 2022. Code: https://github.com/wpy1999/BAS

End-to-End Referring Video Object Segmentation with Multimodal Transformers

Adam Botach, Evgenii Zheltonozhskii, Chaim Baskin

Comments Accepted to CVPR 2022

Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation

Arushi Goel, Basura Fernando, Frank Keller, Hakan Bilen

Comments 16 pages

Journal ref CVPR 2022

Optical Flow Estimation for Spiking Camera

Liwen Hu, Rui Zhao, Ziluo Ding, Lei Ma, Boxin Shi, Ruiqin Xiong, Tiejun Huang

Comments The first two authors contributed equally. Accepted to CVPR 2022

Semi-Supervised Wide-Angle Portraits Correction by Multi-Scale Transformer

Fushun Zhu, Shan Zhao, Peng Wang, Hao Wang, Hua Yan, Shuaicheng Liu

Comments Accepted by CVPR 2022

Patch Slimming for Efficient Vision Transformers

Yehui Tang, Kai Han, Yunhe Wang, Chang Xu, Jianyuan Guo, Chao Xu, Dacheng Tao

Comments This paper is accepted by CVPR 2022

When Does Contrastive Visual Representation Learning Work?

Elijah Cole, Xuan Yang, Kimberly Wilber, Oisin Mac Aodha, Serge Belongie

Comments CVPR 2022

Revisiting Skeleton-based Action Recognition

Haodong Duan, Yue Zhao, Kai Chen, Dahua Lin, Bo Dai

Comments CVPR 2022 Oral

Sparse Object-level Supervision for Instance Segmentation with Pixel Embeddings

Adrian Wolny, Qin Yu, Constantin Pape, Anna Kreshuk

Comments CVPR 2022 camera-ready

Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehicles

Qing Liu, Adam Kortylewski, Zhishuai Zhang, Zizhang Li, Mengqi Guo, Qihao Liu, Xiaoding Yuan, Jiteng Mu, Weichao Qiu, Alan Yuille

Comments CVPR 2022 (Oral)

On the Importance of Asymmetry for Siamese Representation Learning

Xiao Wang, Haoqi Fan, Yuandong Tian, Daisuke Kihara, Xinlei Chen

Comments 11 pages, CVPR 2022

Marginal Contrastive Correspondence for Guided Image Generation

Fangneng Zhan, Yingchen Yu, Rongliang Wu, Jiahui Zhang, Shijian Lu, Changgong Zhang

Comments Accepted to CVPR 2022 (Oral Presentation)

Learning to Deblur using Light Field Generated and Real Defocus Images

Lingyan Ruan, Bin Chen, Jizhou Li, Miuling Lam

Comments CVPR 2022 Oral

DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow

Zihua Zheng, Ni Nie, Zhi Ling, Pengfei Xiong, Jiangyu Liu, Hao Wang, Jiankun Li

Comments CVPR 2022

Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression

Qiang Li, Jingjing Wang, Zhaoliang Yao, Yachun Li, Pengju Yang, Jingwei Yan, Chunmao Wang, Shiliang Pu

Comments The first two authors contributed equally to this work. Accepted to CVPR 2022

Perception Prioritized Training of Diffusion Models

Jooyoung Choi, Jungbeom Lee, Chaehun Shin, Sungwon Kim, Hyunwoo Kim, Sungroh Yoon

Comments CVPR 2022 Code: https://github.com/jychoi118/P2-weighting

Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization

Eunji Kim, Siwon Kim, Jungbeom Lee, Hyunwoo Kim, Sungroh Yoon

Comments CVPR 2022

GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Feature

Biyang Liu, Huimin Yu, Guodong Qi

Comments Accepted by CVPR 2022

It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher

Kanghyun Choi, Hye Yoon Lee, Deokki Hong, Joonsang Yu, Noseong Park, Youngsok Kim, Jinho Lee

Comments selected for an oral presentation at CVPR 2022