Pixel-level Video Understanding in the Wild Challenge (PVUW) focus on complex video understanding. In this CVPR 2024 workshop, we add two new tracks, Complex Video Object Segmentation Track based on MOSE dataset and Motion Expression guided Video Segmentation track based on MeViS dataset. In the two new tracks, we provide additional videos and annotations that feature challenging elements, such as the disappearance and reappearance of objects, inconspicuous small objects, heavy occlusions, and crowded environments in MOSE. Moreover, we provide a new motion expression guided video segmentation dataset MeViS to study the natural language-guided video understanding in complex environments. These new videos, sentences, and annotations enable us to foster the development of a more comprehensive and robust pixel-level understanding of video scenes in complex environments and realistic scenarios. The MOSE challenge had 140 registered teams in total, 65 teams participated the validation phase and 12 teams made valid submissions in the final challenge phase. The MeViS challenge had 225 registered teams in total, 50 teams participated the validation phase and 5 teams made valid submissions in the final challenge phase.
@article{arxiv.2406.17005,
title = {PVUW 2024 Challenge on Complex Video Understanding: Methods and Results},
author = {Henghui Ding and Chang Liu and Yunchao Wei and Nikhila Ravi and Shuting He and Song Bai and Philip Torr and Deshui Miao and Xin Li and Zhenyu He and Yaowei Wang and Ming-Hsuan Yang and Zhensong Xu and Jiangtao Yao and Chengjing Wu and Ting Liu and Luoqi Liu and Xinyu Liu and Jing Zhang and Kexin Zhang and Yuting Yang and Licheng Jiao and Shuyuan Yang and Mingqi Gao and Jingnan Luo and Jinyu Yang and Jungong Han and Feng Zheng and Bin Cao and Yisi Zhang and Xuanxu Lin and Xingjian He and Bo Zhao and Jing Liu and Feiyu Pan and Hao Fang and Xiankai Lu},
journal= {arXiv preprint arXiv:2406.17005},
year = {2024}
}