# 4th PVUW MeViS 3rd Place Report: Sa2VA

arXiv: https://arxiv.org/abs/2504.00476 · HTML: https://mlsanity.com/paper/2504.00476/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 24 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Builds on (most cited first, 23 of 23)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions](https://mlsanity.com/paper/2308.08544/) (2023)
- [Video Object Segmentation with Language Referring Expressions](https://mlsanity.com/paper/1803.08006/) (2018)
- [Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos](https://mlsanity.com/paper/2501.04001/) (2025)
- [OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding](https://mlsanity.com/paper/2406.19389/) (2024)
- [DVIS: Decoupled Video Instance Segmentation Framework](https://mlsanity.com/paper/2306.03413/) (2023)
- [OMG-Seg: Is One Model Good Enough For All Segmentation?](https://mlsanity.com/paper/2401.10229/) (2024)
- [DVIS++: Improved Decoupled Framework for Universal Video Segmentation](https://mlsanity.com/paper/2312.13305/) (2023)
- [Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation](https://mlsanity.com/paper/2303.12782/) (2023)
- [DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries](https://mlsanity.com/paper/2404.00086/) (2024)
- [Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model](https://mlsanity.com/paper/2406.19369/) (2024)
- [Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2501.04670/) (2025)
- [1st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation](https://mlsanity.com/paper/2306.04091/) (2023)
- [1st Place Solution for the 5th LSVOS Challenge: Video Instance Segmentation](https://mlsanity.com/paper/2308.14392/) (2023)

## Built on by (most cited first, 2 of 2)

- [Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding](https://mlsanity.com/paper/2504.10465/) (2025)
- [Dense360: Dense Understanding from Omnidirectional Panoramas](https://mlsanity.com/paper/2506.14471/) (2025)

## Abstract (arXiv)

Referring video object segmentation (RVOS) is a challenging task that requires the model to segment the object in a video given the language description. MeViS is a recently proposed dataset that contains motion expressions of the target objects, leading to a challenging benchmark, compared with existing RVOS benchmarks. On the other hand, for referring expression tasks, a new trend is to adopt multi-modal large language model (MLLM) to achieve better image and text alignment. In this report, we show that with a simple modification to the test time inference method on stronger MLLMs, we can lead to stronger results on MeVIS. In particular, we adopt the recent method Sa2VA, a unified model for dense grounded understanding of both images and videos. By enlarging the scope of key frames, without any further training, we can achieve the 3rd place in the 4th PVUW workshop.