LSVOS 2025 Challenge Report: Recent Advances in Complex Video Object Segmentation
By: Chang Liu , Henghui Ding , Kaining Ying and more
Potential Business Impact:
Helps computers track many moving things in videos.
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.
Similar Papers
MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes
CV and Pattern Recognition
Helps computers track objects in tricky videos.
MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes
CV and Pattern Recognition
Teaches computers to track objects in tricky videos.
Pseudo-Label Enhanced Cascaded Framework: 2nd Technical Report for LSVOS 2025 VOS Track
CV and Pattern Recognition
Tracks moving things in videos better.