mlsanityData to 7 Oct 2026

SaSaSaSa2VA: 2nd Place of the 5th PVUW MeViS-Text Track

arXiv 2603.27241 ↗First posted 28 Mar 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Referring video object segmentation (RVOS) commonly grounds targets in videos based on static textual cues. MeViS benchmark extends this by incorporating motion-centric expressions (referring & reasoning motion expressions) and introducing no-target queries. Extending SaSaSa2VA, where increased input frames and [SEG] tokens already strengthen the Sa2VA backbone, we adopt a simple yet effective target existence-aware verification mechanism, leading to Still Awesome SaSaSa2VA (SaSaSaSa2VA). Despite its simplicity, the method achieves a final score of 89.19 in the 5th PVUW Challenge (MeViS-Text Track), securing 2nd place. Both quantitative results and ablations suggest that this existence-aware verification strategy is sufficient to unlock strong performance on motion-centric referring tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 40 of its 46 references that are in the map. First posted on arXiv 28 Mar 2026.

Builds on

40 of 46 references.

References · 40

  1. 2023Segment Anythingcited by 8,158
  2. 2023Visual Instruction Tuningcited by 7,792
  3. 2025Qwen2.5-VL Technical Reportcited by 5,418
  4. 2024Qwen2.5 Technical Reportcited by 4,713
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  6. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  7. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  8. 2025Qwen3-VL Technical Reportcited by 2,534
  9. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  10. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  11. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,573
  12. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
28 more
  1. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,033
  2. 2015Generation and Comprehension of Unambiguous Object Descriptionscited by 897
  3. 2025SAM 3: Segment Anything with Conceptscited by 835
  4. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 770
  5. 2019Video Instance Segmentationcited by 391
  6. 2024InternLM2 Technical Reportcited by 391
  7. 2023MOSE: A New Dataset for Video Object Segmentation in Complex Scenescited by 232
  8. 2023MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressionscited by 225
  9. 2021Mask2Former for Video Instance Segmentationcited by 169
  10. 2025Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videoscited by 154
  11. 2024OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understandingcited by 126
  12. 2024VISA: Reasoning Video Object Segmentation via Large Language Modelscited by 123
  13. 2023DVIS: Decoupled Video Instance Segmentation Frameworkcited by 77
  14. 2024OMG-Seg: Is One Model Good Enough For All Segmentation?cited by 73
  15. 2025MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenescited by 59
  16. 2023DVIS++: Improved Decoupled Framework for Universal Video Segmentationcited by 46
  17. 2025MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentationcited by 34
  18. 2023Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentationcited by 23
  19. 2024DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queriescited by 22
  20. 2024Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Modelcited by 18
  21. 2025Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMscited by 16
  22. 2026SAMTok: Representing Any Mask with Two Wordscited by 10
  23. 20231st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentationcited by 7
  24. 2025The 1st Solution for 7th LSVOS RVOS Track: SaSaSa2VAcited by 7
  25. 20231st Place Solution for the 5th LSVOS Challenge: Video Instance Segmentationcited by 6
  26. 2025LSVOS 2025 Challenge Report: Recent Advances in Complex Video Object Segmentationcited by 4
  27. 2025Beyond Appearance: Geometric Cues for Robust Video Instance Segmentationcited by 3
  28. 2025Enhancing Sa2VA for Referent Video Object Segmentation: 2nd Solution for 7th LSVOS RVOS Trackcited by 1

Built on by

Not cited yet.