This report summarizes the 8th Large-scale Video Object Segmentation (LSVOS) Challenge, held in conjunction with ECCV 2026. The challenge evaluates video segmentation in three complementary settings: complex semi-supervised video object segmentation on MOSEv2, text-guided referring video object segmentation on MeViSv2-Text, and audio-guided referring video object segmentation on MeViSv2-Audio. We describe the tasks and evaluation protocols and review the methods of the top three teams in each track. Across the nine leading solutions, foundation segmentation models are combined with target-aware memory, multimodal reasoning, explicit target-existence verification, agentic interaction, and corrective tracking. These systems illustrate a broader transition from single-model mask propagation toward modular pipelines that reason about object identity, query validity, and temporal reliability.
Figures & tables
Team
J&F˙
J
F˙
HITsz-Dragon
69.82
68.21
71.43
mmm
66.20
64.79
67.60
AISTAT
64.37
63.16
65.59
FudanSeg ∗
64.71
63.51
65.92
Baseline (SAM 3)
62.72
61.62
63.82
Table 1: MOSEv2 final test-set results (%). Bold indicates the best ranked score; FudanSeg is an organizer entry and does not participate in the ranking.
Team
J&F
N\mbox−acc.
T\mbox−acc.
Final
SSUPER
79.22
94.44
98.77
90.81
CUA Generalists
74.96
88.89
96.32
86.72
HITsz-Dragon
76.10
83.33
97.55
85.66
Baseline
41.26
100.00
65.69
68.98
Table 2: MeViSv2 final test-set leaderboard results (%). Bold indicates the best score in each track.
Figure 1: Method overviews of the first- and second-place MOSEv2 teams.
Figure 2: Representative pipelines from the MeViSv2-Text track.
Figure 3: Method overviews of the first- and second-place MeViSv2-Audio teams.
Department of AI Convergence Security, Soongsil University, Republic of Korea · Department of AI Convergence, Soongsil University, Republic of Korea · Department of Intelligent Semiconductors, Soongsil University, Republic of Korea