CVPR

Woodscape Fisheye Object Detection for Autonomous Driving -- CVPR 2022 OmniCV Workshop Challenge

Saravanabalagi Ramachandran, Ganesh Sistu, Varun Ravi Kumar, John McDonald, Senthil Yogamani

Comments Workshop on Omnidirectional Computer Vision (OmniCV) at Conference on Computer Vision and Pattern Recognition (CVPR) 2021

Defending Multimodal Fusion Models against Single-Source Adversaries

Karren Yang, Wan-Yi Lin, Manash Barman, Filipe Condessa, Zico Kolter

Comments CVPR 2021

SC-Transformer++: Structured Context Transformer for Generic Event Boundary Detection

Dexiang Hong, Xiaoqi Ma, Xinyao Wang, Congcong Li, Yufei Wang, Longyin Wen

Comments winner method at LOVEU@CVPR'22 Generic Event Boundary Detection Challenge

BokehMe: When Neural Rendering Meets Classical Rendering

Juewen Peng, Zhiguo Cao, Xianrui Luo, Hao Lu, Ke Xian, Jianming Zhang

Comments Accepted by CVPR 2022 (Oral); Project: https://juewenpeng.github.io/BokehMe/

Recurrent Transformer Variational Autoencoders for Multi-Action Motion Synthesis

Rania Briq, Chuhang Zou, Leonid Pishchulin, Chris Broaddus, Juergen Gall

Comments accepted at Transformers for Vision workshop at CVPR 2022

Learning to Anticipate Future with Dynamic Context Removal

Xinyu Xu, Yong-Lu Li, Cewu Lu

Comments CVPR 2022

Proper Reuse of Image Classification Features Improves Object Detection

Cristina Vasconcelos, Vighnesh Birodkar, Vincent Dumoulin

Journal ref CVPR 2022

Generating High Fidelity Data from Low-density Regions using Diffusion Models

Vikash Sehwag, Caner Hazirbas, Albert Gordo, Firat Ozgenel, Cristian Canton Ferrer

Comments CVPR 2022 (fixed some discrepancies in notation - v2)

One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestones

Chan Hee Song, Jihyung Kil, Tai-Yu Pan, Brian M. Sadler, Wei-Lun Chao, Yu Su

Comments 10 pages, 5 figures. Accepted to CVPR 2022

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 15482-15491

A Hybrid Quantum-Classical Algorithm for Robust Fitting

Anh-Dzung Doan, Michele Sasdelli, David Suter, Tat-Jun Chin

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

RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairs

Zhouxia Wang, Jiawei Zhang, Runjian Chen, Wenping Wang, Ping Luo

Comments Accepted by CVPR 2022

LidarMultiNet: Unifying LiDAR Semantic Segmentation, 3D Object Detection, and Panoptic Segmentation in a Single Multi-task Network

Dongqiangzi Ye, Weijia Chen, Zixiang Zhou, Yufei Xie, Yu Wang, Panqu Wang, Hassan Foroosh

Comments Official 1st Place Solution for the Waymo Open Dataset Challenges 2022 - 3D Semantic Segmentation. Official leaderboard: https://waymo.com/open/challenges/2022/3d-semantic-segmentation/. CVPR 2022 Workshop on Autonomous Driving: http://cvpr2022.wad.vision/

Towards Optimizing OCR for Accessibility

Peya Mowar, Tanuja Ganu, Saikat Guha

Journal ref Extended Abstract for Poster Session at Accessibility, Vision, and Autonomy Meet (CVPR 2022 Workshop)

Document Navigability: A Need for Print-Impaired

Anukriti Kumar, Tanuja Ganu, Saikat Guha

Comments Published at Accessibility, Vision, and Autonomy Meet, CVPR 2022 Workshop

Journal ref Extended Abstract for Poster Session at Accessibility, Vision, and Autonomy Meet (CVPR 2022 Workshop)

Agriculture-Vision Challenge 2022 -- The Runner-Up Solution for Agricultural Pattern Recognition via Transformer-based Models

Zhicheng Yang, Jui-Hsin Lai, Jun Zhou, Hang Zhou, Chen Du, Zhongcheng Lai

Comments CVPR 2022, Agriculture-Vision Challenge, Remote Sensing

NTIRE 2022 Challenge on Perceptual Image Quality Assessment

Jinjin Gu, Haoming Cai, Chao Dong, Jimmy S. Ren, Radu Timofte

Comments This report has been published in CVPR 2022 NTIRE workshop. arXiv admin note: text overlap with arXiv:2105.03072

BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimation

Ivan Grishchenko, Valentin Bazarevsky, Andrei Zanfir, Eduard Gabriel Bazavan, Mihai Zanfir, Richard Yee, Karthik Raveendran, Matsvei Zhdanovich, Matthias Grundmann, Cristian Sminchisescu

Comments 4 pages, 4 figures; CVPR Workshop on Computer Vision for Augmented and Virtual Reality, New Orleans, LA, 2022

Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization

Kun Xia, Le Wang, Sanping Zhou, Nanning Zheng, Wei Tang

Comments Accepted by CVPR 2022

Broken News: Making Newspapers Accessible to Print-Impaired

Vishal Agarwal, Tanuja Ganu, Saikat Guha

Journal ref Extended Abstract at Accessibility, Vision, and Autonomy Meet (CVPR 2022 Workshop)

Attention Concatenation Volume for Accurate and Efficient Stereo Matching

Gangwei Xu, Junda Cheng, Peng Guo, Xin Yang

Comments Accepted to CVPR 2022

Modulating Bottom-Up and Top-Down Visual Processing via Language-Conditional Filters

İlker Kesen, Ozan Arkan Can, Erkut Erdem, Aykut Erdem, Deniz Yuret

Comments 13 pages, 6 figures, 6 tables. Appeared in MULA Workshop at CVPR 2022

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 4610-4620

Symmetric Network with Spatial Relationship Modeling for Natural Language-based Vehicle Retrieval

Chuyang Zhao, Haobo Chen, Wenyuan Zhang, Junru Chen, Sipeng Zhang, Yadong Li, Boxun Li

Comments 8 pages, 3 figures, publised to CVPRW

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 3226-3233

UniCon+: ICTCAS-UCAS Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2022

Yuanhang Zhang, Susan Liang, Shuang Yang, Shiguang Shan

Comments 5 pages, 3 figures; technical report for AVA Challenge (see https://research.google.com/ava/challenge.html) at the International Challenge on Activity Recognition (ActivityNet), CVPR 2022

Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation

Ming Li, Jie Wu, Jinhang Cai, Jie Qin, Yuxi Ren, Xuefeng Xiao, Min Zheng, Rui Wang, Xin Pan

Comments The solution of 1st Place in AVA Accessibility Vision and Autonomy Challenge on CVPR 2022 workshop. Website: https://accessibility-cv.github.io/

MultiEarth 2022 Deforestation Challenge -- ForestGump

Dongoo Lee, Yeonju Choi

Comments CVPR 2022, MultiEarth 2022, Deforestation Estimation Challenge

Edge-enhanced Feature Distillation Network for Efficient Super-Resolution

Yan Wang

Comments Accepted to NTIRE workshop at CVPR 2022

LiT: Zero-Shot Transfer with Locked-image text Tuning

Xiaohua Zhai, Xiao Wang, Basil Mustafa, Andreas Steiner, Daniel Keysers, Alexander Kolesnikov, Lucas Beyer

Comments Xiaohua, Xiao, Basil, Andreas and Lucas contributed equally; CVPR 2022

Robust fine-tuning of zero-shot models

Mitchell Wortsman, Gabriel Ilharco, Jong Wook Kim, Mike Li, Simon Kornblith, Rebecca Roelofs, Raphael Gontijo-Lopes, Hannaneh Hajishirzi, Ali Farhadi, Hongseok Namkoong, Ludwig Schmidt

Comments CVPR 2022

RendNet: Unified 2D/3D Recognizer With Latent Space Rendering

Ruoxi Shi, Xinyang Jiang, Caihua Shan, Yansen Wang, Dongsheng Li

Comments CVPR 2022 Oral

MPA: MultiPath++ Based Architecture for Motion Prediction

Stepan Konev

Comments CVPR 2022, Workshop on Autonomous Driving