mlsanityData to 14 Oct 2026

LSVOS 2025 Challenge Report: Recent Advances in Complex Video Object Segmentation

arXiv 2510.11063 ↗First posted 13 Oct 2025cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

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&dotF 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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 37 of its 43 references that are in the map. First posted on arXiv 13 Oct 2025.

Builds on

37 of 43 references.

References · 37

  1. 2023Visual Instruction Tuningcited by 7,869
  2. 2024Qwen2.5 Technical Reportcited by 4,942
  3. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  4. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  5. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  6. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  7. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 957
  8. 2024InternLM2 Technical Reportcited by 397
  9. 2023Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistlescited by 290
  10. 2023GRES: Generalized Referring Expression Segmentationcited by 254
  11. 2021Vision-Language Transformer and Query Generation for Referring Segmentationcited by 240
  12. 2018YouTube-VOS: Sequence-to-Sequence Video Object Segmentationcited by 232
25 more
  1. 2023MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressionscited by 228
  2. 2023Towards Open Vocabulary Learning: A Surveycited by 166
  3. 2025Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videoscited by 159
  4. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  5. 2022VLT: Vision-Language Transformer and Query Generation for Referring Segmentationcited by 111
  6. 2024SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Treecited by 80
  7. 2025Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMscited by 80
  8. 2022LVOS: A Benchmark for Long-term Video Object Segmentationcited by 77
  9. 2021Codabench: Flexible, Easy-to-Use and Reproducible Benchmarking Platformcited by 66
  10. 2024A Distractor-Aware Memory for Visual Object Tracking with SAM2cited by 66
  11. 2025MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenescited by 62
  12. 2024A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Modelscited by 52
  13. 2022Towards Robust Referring Image Segmentationcited by 49
  14. 2022Instance-Specific Feature Propagation for Referring Segmentationcited by 45
  15. 2023GREC: Generalized Referring Expression Comprehensioncited by 42
  16. 2023Multi-Modal Mutual Attention and Iterative Interaction for Referring Image Segmentationcited by 36
  17. 2024SegPoint: Segment Any Point Cloud via Large Language Modelcited by 35
  18. 2025Advancing Complex Video Object Segmentation via Progressive Concept Constructioncited by 26
  19. 2024RefMask3D: Language-Guided Transformer for 3D Referring Segmentationcited by 25
  20. 20243D-GRES: Generalized 3D Referring Expression Segmentationcited by 18
  21. 2025Exploiting Temporal State Space Sharing for Video Semantic Segmentationcited by 15
  22. 2024PVUW 2024 Challenge on Complex Video Understanding: Methods and Resultscited by 12
  23. 2025Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehensioncited by 12
  24. 2024LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentationcited by 8
  25. 2025The 1st Solution for 4th PVUW MeViS Challenge: Unleashing the Potential of Large Multimodal Models for Referring Video Segmentationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understandingcited by 1
  2. 2026SaSaSaSa2VA: 2nd Place of the 5th PVUW MeViS-Text Trackcited by 0
  3. 2026Motion-Aware Reasoning from Speech to Mask Tracks: Runner-up Solution for the MeViS-Audio Track of the 8th LSVOS Challenge 2026cited by 0
  4. 2026MLLM-Assisted Audio VOS: A 3rd Place Report for the MeViS-Audio Track, 8th LSVOS Challengecited by 0