LSVOS Challenge Report: Large-Scale Complex and Long Video Object Segmentation
Abstract
Despite the promising performance of current video segmentation models on existing benchmarks, these models still struggle with complex scenes. In this paper, we introduce the 6th Large-scale Video Object Segmentation (LSVOS) challenge in conjunction with ECCV 2025 workshop. This year’s challenge includes two tasks: Video Object Segmentation (VOS) and Referring Video Object Segmentation (RVOS). In this year, we replace the classic YouTube-VOS and YouTube-RVOS benchmark with latest datasets MOSE, LVOS, and MeViS to assess VOS under more challenging complex environments. This year’s challenge attracted 129 registered teams from more than 20 institutes across over 8 countries. This report includes the challenge and dataset introduction, and the methods used by top 7 teams in two tracks. More details can be found in our homepage .
Cite
Text
Ding et al. "LSVOS Challenge Report: Large-Scale Complex and Long Video Object Segmentation." European Conference on Computer Vision Workshops, 2024. doi:10.1007/978-3-031-91856-8_22Markdown
[Ding et al. "LSVOS Challenge Report: Large-Scale Complex and Long Video Object Segmentation." European Conference on Computer Vision Workshops, 2024.](https://mlanthology.org/eccvw/2024/ding2024eccvw-lsvos/) doi:10.1007/978-3-031-91856-8_22BibTeX
@inproceedings{ding2024eccvw-lsvos,
title = {{LSVOS Challenge Report: Large-Scale Complex and Long Video Object Segmentation}},
author = {Ding, Henghui and Hong, Lingyi and Liu, Chang and Xu, Ning and Yang, Linjie and Fan, Yuchen and Miao, Deshui and Gu, Yameng and Li, Xin and He, Zhenyu and Wang, Yaowei and Yang, Ming-Hsuan and Chai, Jinming and Ma, Qin and Zhang, Junpei and Jiao, Licheng and Liu, Fang and Liu, Xinyu and Zhang, Jing and Zhang, Kexin and Liu, Xu and Li, Lingling and Fang, Hao and Pan, Feiyu and Lu, Xiankai and Zhang, Wei and Cong, Runmin and Tran, Tuyen and Cao, Bin and Zhang, Yisi and Wang, Hanyi and He, Xingjian and Liu, Jing},
booktitle = {European Conference on Computer Vision Workshops},
year = {2024},
pages = {378-394},
doi = {10.1007/978-3-031-91856-8_22},
url = {https://mlanthology.org/eccvw/2024/ding2024eccvw-lsvos/}
}