SaSaSaSa2VA: 2nd Place of the 5th PVUW MeViS-Text Track
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908918978969600 |
|---|---|
| author | Gong, Dengxian Niu, Quanzhu Chen, Shihao Wu, Yuanzheng Zhou, Yikang Zhang, Tao Yuan, Haobo Qi, Lu Ji, Shunping |
| author_facet | Gong, Dengxian Niu, Quanzhu Chen, Shihao Wu, Yuanzheng Zhou, Yikang Zhang, Tao Yuan, Haobo Qi, Lu Ji, Shunping |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27241 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SaSaSaSa2VA: 2nd Place of the 5th PVUW MeViS-Text Track Gong, Dengxian Niu, Quanzhu Chen, Shihao Wu, Yuanzheng Zhou, Yikang Zhang, Tao Yuan, Haobo Qi, Lu Ji, Shunping Computer Vision and Pattern Recognition 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. |
| title | SaSaSaSa2VA: 2nd Place of the 5th PVUW MeViS-Text Track |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.27241 |