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

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

URL: http://arxiv.org/abs/2603.27241v1
Date: Sat, 28 Mar 2026 11:31:55 GMT
Title: SaSaSaSa2VA: 2nd Place of the 5th PVUW MeViS-Text Track
Abstract summary: MeViS benchmark extends this by incorporating motion-centric expressions and introducing no-target queries.<n>We adopt a simple yet effective target existence-aware verification mechanism, leading to Still Awesome SaSaSa2VA (SaSaSa2VA)<n>Despite its simplicity, the method achieves a final score of 89.19 in the 5th PVUW Challenge (MeViS-Text Track)
Score: 30.33008093410309
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: 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.

Related papers

Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking [81.34609950921023]
Recent vision foundation models, exemplified by SAM 2, learn strong video understanding priors from large-scale pretraining.<n>We propose SAMOSA, a new tracking framework that adapts SAM 2 to complex VOT scenarios by explicitly leveraging motion, geometry, and semantic cues.
arXiv Detail & Related papers (2026-05-21T14:25:28Z)
Nüwa: Mending the Spatial Integrity Torn by VLM Token Pruning [82.39668822222386]
Vision token pruning has proven to be an effective acceleration technique for the efficient Vision Language Model (VLM)<n>We propose $textNwa$, a two-stage token pruning framework that enables efficient feature aggregation while maintaining spatial integrity.<n>Experiments demonstrate that $textNwa$ achieves SOTA performance on multiple VQA benchmarks (from 94% to 95%) and yields substantial improvements on visual grounding tasks (from 7% to 47%)
arXiv Detail & Related papers (2026-02-03T00:51:03Z)
3rd Place Report of LSVOS 2025 MeViS Track: Sa2VA-i: Improving Sa2VA Results with Consistent Training and Inference [59.989927043461364]
We find that Sa2VA does not perform according to its full potential for referring video object segmentation tasks.<n>We propose an improved version of Sa2VA, Sa2VA-i, that rectifies these issues and improves the results.<n>With our fixes, the Sa2VA-i-1B model even performs on par with the original Sa2VA-26B model on the MeViS benchmark.
arXiv Detail & Related papers (2025-09-23T14:38:25Z)
The 1st Solution for 7th LSVOS RVOS Track: SaSaSa2VA [57.26038712231443]
Referring video object segmentation (RVOS) requires segmenting and tracking objects in videos conditioned on natural-language expressions.<n>We propose Augmented and Selective Averaged Sa2VA (SaSa2VA) to address these issues.<n>SaSa2VA achieves a $mathcalJ&F$ of 67.45, ranking first and surpassing the runner-up by 2.80 points.
arXiv Detail & Related papers (2025-09-21T08:08:17Z)
Enhancing Sa2VA for Referent Video Object Segmentation: 2nd Solution for 7th LSVOS RVOS Track [11.068687286561177]
Referential Video Object (RVOS) aims to segment all objects in a video that match a given natural language description.<n>We present a training-free framework that substantially improves Sa2VA's performance on the RVOS task.
arXiv Detail & Related papers (2025-09-19T03:01:27Z)
4th PVUW MeViS 3rd Place Report: Sa2VA [105.88675577642204]
We show that with a simple modification to the test time inference method on stronger MLLMs, we can lead to stronger results on MeVIS.<n>In particular, we adopt the recent method Sa2VA, a unified model for dense grounded understanding of both images and videos.
arXiv Detail & Related papers (2025-04-01T07:06:47Z)
SAM 2 in Robotic Surgery: An Empirical Evaluation for Robustness and Generalization in Surgical Video Segmentation [13.609341065893739]
This study explores the zero-shot segmentation performance of SAM 2 in robot-assisted surgery based on prompts. We employ two forms of prompts: 1-point and bounding box, while for video sequences, the 1-point prompt is applied to the initial frame. The results with point prompts also exhibit a substantial enhancement over SAM's capabilities, nearing or even surpassing existing unprompted SOTA methods.
arXiv Detail & Related papers (2024-08-08T17:08:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.