CVPR - arXivDaily 期刊&会议

2206.09585 2022-06-22 cs.CV cs.AI

5th Place Solution for YouTube-VOS Challenge 2022: Video Object Segmentation

Wangwang Yang, Jinming Su, Yiting Duan, Tingyi Guo, Junfeng Luo

Comments 5th Place Solution for Video Object Segmentation in the 4th Large-scale Video Object Segmentation Challenge, CVPR 2022 Workshop

2206.09553 2022-06-22 cs.CV

Capturing and Inferring Dense Full-Body Human-Scene Contact

Chun-Hao P. Huang, Hongwei Yi, Markus Höschle, Matvey Safroshkin, Tsvetelina Alexiadis, Senya Polikovsky, Daniel Scharstein, Michael J. Black

Comments CVPR 2022

2206.09293 2022-06-22 cs.CV

Rethinking Bayesian Deep Learning Methods for Semi-Supervised Volumetric Medical Image Segmentation

Jianfeng Wang, Thomas Lukasiewicz

Comments To appear at CVPR 2022, and the supplementary material can be found at the official site. The source codes are at https://github.com/Jianf-Wang/GBDL

2206.09242 2022-06-22 cs.CV cs.LG

GaLeNet: Multimodal Learning for Disaster Prediction, Management and Relief

Rohit Saha, Mengyi Fang, Angeline Yasodhara, Kyryl Truskovskyi, Azin Asgarian, Daniel Homola, Raahil Shah, Frederik Dieleman, Jack Weatheritt, Thomas Rogers

Comments Accepted to CVPR 2022 Workshop on Multimodal Learning for Earth and Environment

2206.09178 2022-06-22 cs.CV cs.AI

REVECA -- Rich Encoder-decoder framework for Video Event CAptioner

Jaehyuk Heo, YongGi Jeong, Sunwoo Kim, Jaehee Kim, Pilsung Kang

Comments The IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR). LOng-form VidEo Understanding (LOVEU) workshop

2206.09082 2022-06-22 cs.CV

Context-aware Proposal Network for Temporal Action Detection

Xiang Wang, Huaxin Zhang, Shiwei Zhang, Changxin Gao, Yuanjie Shao, Nong Sang

Comments First place winning solution for temporal action detection task in CVPR-2022 AcitivityNet Challenge. arXiv admin note: substantial text overlap with arXiv:2106.11812

2204.13101 2022-06-22 cs.CV

Self-Supervised Learning of Object Parts for Semantic Segmentation

Adrian Ziegler, Yuki M. Asano

Comments Accepted at CVPR 2022

2203.15536 2022-06-22 cs.CV cs.AI cs.LG

BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information

Nadine Rueegg, Silvia Zuffi, Konrad Schindler, Michael J. Black

Comments accepted for publication at CVPR 2022

2201.02609 2022-06-22 cs.CV cs.LG

Generalized Category Discovery

Sagar Vaze, Kai Han, Andrea Vedaldi, Andrew Zisserman

Comments CVPR 22. Changes from pre-print highlighted in GitHub repo

2111.15143 2022-06-22 cs.CV

HEAT: Holistic Edge Attention Transformer for Structured Reconstruction

Jiacheng Chen, Yiming Qian, Yasutaka Furukawa

Comments CVPR 2022 camera-ready

2111.13196 2022-06-22 cs.CV

SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning

Kevin Lin, Linjie Li, Chung-Ching Lin, Faisal Ahmed, Zhe Gan, Zicheng Liu, Yumao Lu, Lijuan Wang

Comments CVPR 2022

2108.01975 2022-06-22 cs.CV

Deep Anomaly Discovery From Unlabeled Videos via Normality Advantage and Self-Paced Refinement

Guang Yu, Siqi Wang, Zhiping Cai, Xinwang Liu, Chuanfu Xu, Chengkun Wu

Comments Accepted by CVPR 2022

2106.05237 2022-06-22 cs.CV cs.AI cs.LG

Knowledge distillation: A good teacher is patient and consistent

Lucas Beyer, Xiaohua Zhai, Amélie Royer, Larisa Markeeva, Rohan Anil, Alexander Kolesnikov

Comments Lucas, Xiaohua, Amélie, Larisa, and Alex contributed equally; CVPR 2022

2106.04560 2022-06-22 cs.CV cs.AI cs.LG

Scaling Vision Transformers

Xiaohua Zhai, Alexander Kolesnikov, Neil Houlsby, Lucas Beyer

Comments Xiaohua, Alex, and Lucas contributed equally; CVPR 2022

2105.08825 2022-06-22 cs.CV

Multi-Person Extreme Motion Prediction

Wen Guo, Xiaoyu Bie, Xavier Alameda-Pineda, Francesc Moreno-Noguer

Comments CVPR 2022, update results of MSR in Table 3

2008.11600 2022-06-22 cs.CV cs.LG

Estimating Example Difficulty Using Variance of Gradients

Chirag Agarwal, Daniel D'souza, Sara Hooker

Comments Accepted to CVPR 2022

2206.08970 2022-06-22 cs.CV

MultiEarth 2022 -- The Champion Solution for the Matrix Completion Challenge via Multimodal Regression and Generation

Bo Peng, Hongchen Liu, Hang Zhou, Yuchuan Gou, Jui-Hsin Lai

Comments CVPR 2022, MultiEarth 2022, Matrix Completion Challenge

2206.08948 2022-06-22 cs.CV

CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation

Qihang Yu, Huiyu Wang, Dahun Kim, Siyuan Qiao, Maxwell Collins, Yukun Zhu, Hartwig Adam, Alan Yuille, Liang-Chieh Chen

Comments CVPR 2022 Oral

2206.08792 2022-06-20 cs.CV

FD-CAM: Improving Faithfulness and Discriminability of Visual Explanation for CNNs

Hui Li, Zihao Li, Rui Ma, Tieru Wu

Comments Accepted by ICPR 2022 and also accepted by CVPR 2022 Explainable Artificial Intelligence for Computer Vision (XAI4CV) Workshop

2206.08500 2022-06-20 cs.CV cs.LG cs.RO

What do navigation agents learn about their environment?

Kshitij Dwivedi, Gemma Roig, Aniruddha Kembhavi, Roozbeh Mottaghi

Comments CVPR 2022

2206.08423 2022-06-20 cs.CV

IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes

Rui Zhu, Zhengqin Li, Janarbek Matai, Fatih Porikli, Manmohan Chandraker

Comments CVPR 22 camera ready version with supplementary

2201.10990 2022-06-20 cs.CV

Learning To Recognize Procedural Activities with Distant Supervision

Xudong Lin, Fabio Petroni, Gedas Bertasius, Marcus Rohrbach, Shih-Fu Chang, Lorenzo Torresani

Comments CVPR 2022. Code will be released here https://github.com/facebookresearch/video-distant-supervision

2201.10029 2022-06-20 cs.CV cs.AI

PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning

Santhosh Kumar Ramakrishnan, Devendra Singh Chaplot, Ziad Al-Halah, Jitendra Malik, Kristen Grauman

Comments 8 pages + supplementary. Accepted in CVPR 2022

2112.03857 2022-06-20 cs.CV cs.AI cs.CL cs.LG cs.MM

Grounded Language-Image Pre-training

Liunian Harold Li, Pengchuan Zhang, Haotian Zhang, Jianwei Yang, Chunyuan Li, Yiwu Zhong, Lijuan Wang, Lu Yuan, Lei Zhang, Jenq-Neng Hwang, Kai-Wei Chang, Jianfeng Gao

Comments CVPR 2022; updated visualizations; fixed hyper-parameters in Appendix C.1

2111.14813 2022-06-20 cs.CV

TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions

Jeya Maria Jose Valanarasu, Rajeev Yasarla, Vishal M. Patel

Comments CVPR 2022

2206.08367 2022-06-17 cs.CV cs.LG

SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation

Tao Sun, Mattia Segu, Janis Postels, Yuxuan Wang, Luc Van Gool, Bernt Schiele, Federico Tombari, Fisher Yu

Comments Published at IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022

2206.08365 2022-06-17 cs.CV cs.RO

Virtual Correspondence: Humans as a Cue for Extreme-View Geometry

Wei-Chiu Ma, Anqi Joyce Yang, Shenlong Wang, Raquel Urtasun, Antonio Torralba

Comments CVPR 2022. Project page: https://people.csail.mit.edu/weichium/virtual-correspondence/

2206.08357 2022-06-17 cs.CV cs.GR cs.LG

Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing

Gaurav Parmar, Yijun Li, Jingwan Lu, Richard Zhang, Jun-Yan Zhu, Krishna Kumar Singh

Comments CVPR 2022. Github: https://github.com/adobe-research/sam_inversion Website: https://www.cs.cmu.edu/~SAMInversion

2206.08347 2022-06-17 cs.CV

Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning

Matthew Gwilliam, Abhinav Shrivastava

Comments CVPR 2022, project page: https://mgwillia.github.io/exploring-unsupervised/

2206.08236 2022-06-17 cs.CV cs.LG eess.IV

Simple and Efficient Architectures for Semantic Segmentation

Dushyant Mehta, Andrii Skliar, Haitam Ben Yahia, Shubhankar Borse, Fatih Porikli, Amirhossein Habibian, Tijmen Blankevoort

Comments To be presented at Efficient Deep Learning for Computer Vision Workshop at CVPR 2022