PVUW 2024 Challenge on Complex Video Understanding: Methods and Results
Abstract
Pixel-level Video Understanding in the Wild (PVUW) Challenge 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.
Cite
Text
Ding et al. "PVUW 2024 Challenge on Complex Video Understanding: Methods and Results." European Conference on Computer Vision Workshops, 2024. doi:10.1007/978-3-031-91856-8_21Markdown
[Ding et al. "PVUW 2024 Challenge on Complex Video Understanding: Methods and Results." European Conference on Computer Vision Workshops, 2024.](https://mlanthology.org/eccvw/2024/ding2024eccvw-pvuw/) doi:10.1007/978-3-031-91856-8_21BibTeX
@inproceedings{ding2024eccvw-pvuw,
title = {{PVUW 2024 Challenge on Complex Video Understanding: Methods and Results}},
author = {Ding, Henghui and Liu, Chang and Wei, Yunchao and Ravi, Nikhila and He, Shuting and Bai, Song and Torr, Philip and Miao, Deshui and Li, Xin and He, Zhenyu and Wang, Yaowei and Yang, Ming-Hsuan and Xu, Zhensong and Yao, Jiangtao and Wu, Chengjing and Liu, Ting and Liu, Luoqi and Liu, Xinyu and Zhang, Jing and Zhang, Kexin and Yang, Yuting and Jiao, Licheng and Yang, Shuyuan and Gao, Mingqi and Luo, Jingnan and Yang, Jinyu and Han, Jungong and Zheng, Feng and Cao, Bin and Zhang, Yisi and Lin, Xuanxu and He, Xingjian and Zhao, Bo and Liu, Jing and Pan, Feiyu and Fang, Hao and Lu, Xiankai},
booktitle = {European Conference on Computer Vision Workshops},
year = {2024},
pages = {361-377},
doi = {10.1007/978-3-031-91856-8_21},
url = {https://mlanthology.org/eccvw/2024/ding2024eccvw-pvuw/}
}