_version_ 1866910914986377216
author Ding, Henghui
Liu, Chang
Ravi, Nikhila
He, Shuting
Wei, Yunchao
Bai, Song
Torr, Philip
Song, Kehuan
Xie, Xinglin
Zhang, Kexin
Jiao, Licheng
Li, Lingling
Yang, Shuyuan
Cao, Xuqiang
Zhao, Linnan
Zhao, Jiaxuan
Liu, Fang
Wang, Mengjiao
Zhang, Junpei
Liu, Xu
Yang, Yuting
Ma, Mengru
Fang, Hao
Cong, Runmin
Lu, Xiankai
Chen, Zhiyang
Zhang, Wei
Liang, Tianming
Jiang, Haichao
Zheng, Wei-Shi
Hu, Jian-Fang
Yuan, Haobo
Li, Xiangtai
Zhang, Tao
Qi, Lu
Yang, Ming-Hsuan
author_facet Ding, Henghui
Liu, Chang
Ravi, Nikhila
He, Shuting
Wei, Yunchao
Bai, Song
Torr, Philip
Song, Kehuan
Xie, Xinglin
Zhang, Kexin
Jiao, Licheng
Li, Lingling
Yang, Shuyuan
Cao, Xuqiang
Zhao, Linnan
Zhao, Jiaxuan
Liu, Fang
Wang, Mengjiao
Zhang, Junpei
Liu, Xu
Yang, Yuting
Ma, Mengru
Fang, Hao
Cong, Runmin
Lu, Xiankai
Chen, Zhiyang
Zhang, Wei
Liang, Tianming
Jiang, Haichao
Zheng, Wei-Shi
Hu, Jian-Fang
Yuan, Haobo
Li, Xiangtai
Zhang, Tao
Qi, Lu
Yang, Ming-Hsuan
contents This report provides a comprehensive overview of the 4th Pixel-level Video Understanding in the Wild (PVUW) Challenge, held in conjunction with CVPR 2025. It summarizes the challenge outcomes, participating methodologies, and future research directions. The challenge features two tracks: MOSE, which focuses on complex scene video object segmentation, and MeViS, which targets motion-guided, language-based video segmentation. Both tracks introduce new, more challenging datasets designed to better reflect real-world scenarios. Through detailed evaluation and analysis, the challenge offers valuable insights into the current state-of-the-art and emerging trends in complex video segmentation. More information can be found on the workshop website: https://pvuw.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2504_11326
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wild
Ding, Henghui
Liu, Chang
Ravi, Nikhila
He, Shuting
Wei, Yunchao
Bai, Song
Torr, Philip
Song, Kehuan
Xie, Xinglin
Zhang, Kexin
Jiao, Licheng
Li, Lingling
Yang, Shuyuan
Cao, Xuqiang
Zhao, Linnan
Zhao, Jiaxuan
Liu, Fang
Wang, Mengjiao
Zhang, Junpei
Liu, Xu
Yang, Yuting
Ma, Mengru
Fang, Hao
Cong, Runmin
Lu, Xiankai
Chen, Zhiyang
Zhang, Wei
Liang, Tianming
Jiang, Haichao
Zheng, Wei-Shi
Hu, Jian-Fang
Yuan, Haobo
Li, Xiangtai
Zhang, Tao
Qi, Lu
Yang, Ming-Hsuan
Computer Vision and Pattern Recognition
This report provides a comprehensive overview of the 4th Pixel-level Video Understanding in the Wild (PVUW) Challenge, held in conjunction with CVPR 2025. It summarizes the challenge outcomes, participating methodologies, and future research directions. The challenge features two tracks: MOSE, which focuses on complex scene video object segmentation, and MeViS, which targets motion-guided, language-based video segmentation. Both tracks introduce new, more challenging datasets designed to better reflect real-world scenarios. Through detailed evaluation and analysis, the challenge offers valuable insights into the current state-of-the-art and emerging trends in complex video segmentation. More information can be found on the workshop website: https://pvuw.github.io/.
title PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wild
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.11326