_version_ 1866912644337762304
author Liu, Chang
Ding, Henghui
Ying, Kaining
Hong, Lingyi
Xu, Ning
Yang, Linjie
Fan, Yuchen
Gao, Mingqi
Chen, Jingkun
Miao, Yunqi
Wu, Gengshen
Qin, Zhijin
Han, Jungong
Zhang, Zhixiong
Ding, Shuangrui
Dong, Xiaoyi
Zang, Yuhang
Cao, Yuhang
Wang, Jiaqi
Lim, Chang Soo
Moon, Joonyoung
Cho, Donghyeon
Li, Tingmin
Li, Yixuan
Yang, Yang
Yan, An
Cao, Leilei
Lu, Feng
Hong, Ran
Jiang, Youhai
Zhu, Fengjie
Xie, Yujie
Zhang, Hongyang
Liu, Zhihui
Ruan, Shihai
Niu, Quanzhu
Gong, Dengxian
Chen, Shihao
Zhang, Tao
Zhou, Yikang
Yuan, Haobo
Qi, Lu
Li, Xiangtai
Ji, Shunping
Hong, Ran
Lu, Feng
Cao, Leilei
Yan, An
Nekrasov, Alexey
Athar, Ali
de Geus, Daan
Hermans, Alexander
Leibe, Bastian
author_facet Liu, Chang
Ding, Henghui
Ying, Kaining
Hong, Lingyi
Xu, Ning
Yang, Linjie
Fan, Yuchen
Gao, Mingqi
Chen, Jingkun
Miao, Yunqi
Wu, Gengshen
Qin, Zhijin
Han, Jungong
Zhang, Zhixiong
Ding, Shuangrui
Dong, Xiaoyi
Zang, Yuhang
Cao, Yuhang
Wang, Jiaqi
Lim, Chang Soo
Moon, Joonyoung
Cho, Donghyeon
Li, Tingmin
Li, Yixuan
Yang, Yang
Yan, An
Cao, Leilei
Lu, Feng
Hong, Ran
Jiang, Youhai
Zhu, Fengjie
Xie, Yujie
Zhang, Hongyang
Liu, Zhihui
Ruan, Shihai
Niu, Quanzhu
Gong, Dengxian
Chen, Shihao
Zhang, Tao
Zhou, Yikang
Yuan, Haobo
Qi, Lu
Li, Xiangtai
Ji, Shunping
Hong, Ran
Lu, Feng
Cao, Leilei
Yan, An
Nekrasov, Alexey
Athar, Ali
de Geus, Daan
Hermans, Alexander
Leibe, Bastian
contents This report presents an overview of the 7th Large-scale Video Object Segmentation (LSVOS) Challenge held in conjunction with ICCV 2025. Besides the two traditional tracks of LSVOS that jointly target robustness in realistic video scenarios: Classic VOS (VOS), and Referring VOS (RVOS), the 2025 edition features a newly introduced track, Complex VOS (MOSEv2). Building upon prior insights, MOSEv2 substantially increases difficulty, introducing more challenging but realistic scenarios including denser small objects, frequent disappear/reappear events, severe occlusions, adverse weather and lighting, etc., pushing long-term consistency and generalization beyond curated benchmarks. The challenge retains standard ${J}$, $F$, and ${J\&F}$ metrics for VOS and RVOS, while MOSEv2 adopts ${J\&\dot{F}}$ as the primary ranking metric to better evaluate objects across scales and disappearance cases. We summarize datasets and protocols, highlight top-performing solutions, and distill emerging trends, such as the growing role of LLM/MLLM components and memory-aware propagation, aiming to chart future directions for resilient, language-aware video segmentation in the wild.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11063
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LSVOS 2025 Challenge Report: Recent Advances in Complex Video Object Segmentation
Liu, Chang
Ding, Henghui
Ying, Kaining
Hong, Lingyi
Xu, Ning
Yang, Linjie
Fan, Yuchen
Gao, Mingqi
Chen, Jingkun
Miao, Yunqi
Wu, Gengshen
Qin, Zhijin
Han, Jungong
Zhang, Zhixiong
Ding, Shuangrui
Dong, Xiaoyi
Zang, Yuhang
Cao, Yuhang
Wang, Jiaqi
Lim, Chang Soo
Moon, Joonyoung
Cho, Donghyeon
Li, Tingmin
Li, Yixuan
Yang, Yang
Yan, An
Cao, Leilei
Lu, Feng
Hong, Ran
Jiang, Youhai
Zhu, Fengjie
Xie, Yujie
Zhang, Hongyang
Liu, Zhihui
Ruan, Shihai
Niu, Quanzhu
Gong, Dengxian
Chen, Shihao
Zhang, Tao
Zhou, Yikang
Yuan, Haobo
Qi, Lu
Li, Xiangtai
Ji, Shunping
Hong, Ran
Lu, Feng
Cao, Leilei
Yan, An
Nekrasov, Alexey
Athar, Ali
de Geus, Daan
Hermans, Alexander
Leibe, Bastian
Computer Vision and Pattern Recognition
This report presents an overview of the 7th Large-scale Video Object Segmentation (LSVOS) Challenge held in conjunction with ICCV 2025. Besides the two traditional tracks of LSVOS that jointly target robustness in realistic video scenarios: Classic VOS (VOS), and Referring VOS (RVOS), the 2025 edition features a newly introduced track, Complex VOS (MOSEv2). Building upon prior insights, MOSEv2 substantially increases difficulty, introducing more challenging but realistic scenarios including denser small objects, frequent disappear/reappear events, severe occlusions, adverse weather and lighting, etc., pushing long-term consistency and generalization beyond curated benchmarks. The challenge retains standard ${J}$, $F$, and ${J\&F}$ metrics for VOS and RVOS, while MOSEv2 adopts ${J\&\dot{F}}$ as the primary ranking metric to better evaluate objects across scales and disappearance cases. We summarize datasets and protocols, highlight top-performing solutions, and distill emerging trends, such as the growing role of LLM/MLLM components and memory-aware propagation, aiming to chart future directions for resilient, language-aware video segmentation in the wild.
title LSVOS 2025 Challenge Report: Recent Advances in Complex Video Object Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.11063