# The 1st Winner for 5th PVUW MeViS-Text Challenge: Strong MLLMs Meet SAM3 for Referring Video Object Segmentation

arXiv: https://arxiv.org/abs/2604.00404 · HTML: https://mlsanity.com/paper/2604.00404/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 26 references that are in the map.
- First posted on arXiv 1 Apr 2026.

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

- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark](https://mlsanity.com/paper/1809.03327/) (2018)
- [MOSE: A New Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2302.01872/) (2023)
- [MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions](https://mlsanity.com/paper/2308.08544/) (2023)
- [Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos](https://mlsanity.com/paper/2501.04001/) (2025)
- [Expectation-Maximization Attention Networks for Semantic Segmentation](https://mlsanity.com/paper/1907.13426/) (2019)
- [Ovis2.5 Technical Report](https://mlsanity.com/paper/2508.11737/) (2025)
- [One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos](https://mlsanity.com/paper/2409.19603/) (2024)
- [LVOS: A Benchmark for Long-term Video Object Segmentation](https://mlsanity.com/paper/2211.10181/) (2022)
- [MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2508.05630/) (2025)
- [MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation](https://mlsanity.com/paper/2512.10945/) (2025)
- [A Survey on Video Temporal Grounding with Multimodal Large Language Model](https://mlsanity.com/paper/2508.10922/) (2025)
- [ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation](https://mlsanity.com/paper/2412.09754/) (2024)
- [PVUW 2024 Challenge on Complex Video Understanding: Methods and Results](https://mlsanity.com/paper/2406.17005/) (2024)
- [Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation](https://mlsanity.com/paper/2602.03595/) (2026)
- [Long-RVOS: A Comprehensive Benchmark for Long-term Referring Video Object Segmentation](https://mlsanity.com/paper/2505.12702/) (2025)
- [R2-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations](https://mlsanity.com/paper/2403.04924/) (2024)
- [PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wild](https://mlsanity.com/paper/2504.11326/) (2025)
- [ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning](https://mlsanity.com/paper/2512.02835/) (2025)
- [Training-Free Spatio-temporal Decoupled Reasoning Video Segmentation with Adaptive Object Memory](https://mlsanity.com/paper/2603.01545/) (2026)

## Built on by (most cited first, 1 of 1)

- [Multi-Agent Target-Existence Verification and Learned Mask Geometry Refinement: Winning Report of the MeViS-Text Track at the 8th LSVOS Challenge 2026](https://mlsanity.com/paper/2608.11458/) (2026)

## Abstract (arXiv)

This report presents our winning solution to the 5th PVUW MeViS-Text Challenge. The track studies referring video object segmentation under motion-centric language expressions, where the model must jointly understand appearance, temporal behavior, and object interactions. To address this problem, we build a fully training-free pipeline that combines strong multimodal large language models with SAM3. Our method contains three stages. First, Gemini-3.1 Pro decomposes each target event into instance-level grounding targets, selects the frame where the target is most clearly visible, and generates a discriminative description. Second, SAM3-agent produces a precise seed mask on the selected frame, and the official SAM3 tracker propagates the mask through the whole video. Third, a refinement stage uses Qwen3.5-Plus and behavior-level verification to correct ambiguous or semantically inconsistent predictions. Without task-specific fine-tuning, our method ranks first on the PVUW 2026 MeViS-Text test set, achieving a Final score of 0.909064 and a J&F score of 0.7897. The code is available at https://github.com/Moujuruo/MeViSv2_Track_Solution_2026.