mlsanityData to 14 Oct 2026

The 1st Solution for 7th LSVOS RVOS Track: SaSaSa2VA

arXiv 2509.16972 ↗First posted 21 Sep 2025cs.CV cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Referring video object segmentation (RVOS) requires segmenting and tracking objects in videos conditioned on natural-language expressions, demanding fine-grained understanding of both appearance and motion. Building on Sa2VA, which couples a Multi-modal Large Language Model (MLLM) with the video segmentation model SAM2, we identify two key bottlenecks that limit segmentation performance: sparse frame sampling and reliance on a single [SEG] token for an entire video. We propose Segmentation Augmented and Selective Averaged Sa2VA (SaSaSa2VA) to address these issues. On the 7th LSVOS Challenge (RVOS track), SaSaSa2VA achieves a J&F of 67.45, ranking first and surpassing the runner-up by 2.80 points. This result and ablation studies demonstrate that efficient segmentation augmentation and test-time ensembling substantially enhance grounded MLLMs for RVOS. The code is released in Sa2VA repository: https://github.com/bytedance/Sa2VA.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 33 of its 38 references that are in the map. First posted on arXiv 21 Sep 2025.

Builds on

33 of 38 references.

References · 33

  1. 2023Segment Anythingcited by 8,234
  2. 2023Visual Instruction Tuningcited by 7,869
  3. 2025Qwen2.5-VL Technical Reportcited by 5,587
  4. 2024Qwen2.5 Technical Reportcited by 4,942
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  6. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  7. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  8. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  9. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  10. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  11. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,510
  12. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,050
21 more
  1. 2015Generation and Comprehension of Unambiguous Object Descriptionscited by 904
  2. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 776
  3. 2024InternLM2 Technical Reportcited by 397
  4. 2023MOSE: A New Dataset for Video Object Segmentation in Complex Scenescited by 234
  5. 2018Video Object Segmentation with Language Referring Expressionscited by 162
  6. 2025Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videoscited by 159
  7. 2024OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understandingcited by 127
  8. 2024VISA: Reasoning Video Object Segmentation via Large Language Modelscited by 127
  9. 2025Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMscited by 80
  10. 2023DVIS: Decoupled Video Instance Segmentation Frameworkcited by 77
  11. 2024OMG-Seg: Is One Model Good Enough For All Segmentation?cited by 75
  12. 2025MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenescited by 62
  13. 2023DVIS++: Improved Decoupled Framework for Universal Video Segmentationcited by 46
  14. 2023Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentationcited by 23
  15. 2024DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queriescited by 22
  16. 2024Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Modelcited by 18
  17. 2025Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMscited by 16
  18. 20231st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentationcited by 7
  19. 20231st Place Solution for the 5th LSVOS Challenge: Video Instance Segmentationcited by 6
  20. 2025The 1st Solution for 4th PVUW MeViS Challenge: Unleashing the Potential of Large Multimodal Models for Referring Video Segmentationcited by 3
  21. 2025Beyond Appearance: Geometric Cues for Robust Video Instance Segmentationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 20262nd of the 5th PVUW MeViS-Audio Track: ASR-SaSaSa2VAcited by 1
  2. 2026Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understandingcited by 1
  3. 2026SaSaSaSa2VA: 2nd Place of the 5th PVUW MeViS-Text Trackcited by 0
  4. 2026AgentRVOS for MeViS-Text Track of 5th PVUW Challenge: 3rd Methodcited by 0
  5. 2026Agreement-Based Audio-Visual Segmentation:Champion Report for the MeViS-Audio Track in the 8th LSVOS Challengecited by 0
  6. 2026Motion-Aware Reasoning from Speech to Mask Tracks: Runner-up Solution for the MeViS-Audio Track of the 8th LSVOS Challenge 2026cited by 0
  7. 2026Report of the 8th LSVOS Challenge: Complex and Multimodal Video Object Segmentationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Enhancing Sa2VA for Referent Video Object Segmentation: 2nd Solution for 7th LSVOS RVOS Track
  2. 2024LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation
  3. 2025SVAC: Scaling Is All You Need For Referring Video Object Segmentation
  4. 2026AgentRVOS: Reasoning over Object Tracks for Zero-Shot Referring Video Object Segmentation
  5. 20254th PVUW MeViS 3rd Place Report: Sa2VA
  6. 2026Weakly-Supervised Referring Video Object Segmentation through Text Supervision
  7. 2025Deforming Videos to Masks: Flow Matching for Referring Video Segmentation
  8. 2025Temporal-Conditional Referring Video Object Segmentation with Noise-Free Text-to-Video Diffusion Model