# The 1st Solution for 4th PVUW MeViS Challenge: Unleashing the Potential of Large Multimodal Models for Referring Video Segmentation

arXiv: https://arxiv.org/abs/2504.05178 · HTML: https://mlsanity.com/paper/2504.05178/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 25 of its 27 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 25 of 25)

- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [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)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [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)
- [PixelLM: Pixel Reasoning with Large Multimodal Model](https://mlsanity.com/paper/2312.02228/) (2023)
- [Universal Instance Perception as Object Discovery and Retrieval](https://mlsanity.com/paper/2303.06674/) (2023)
- [Putting the Object Back into Video Object Segmentation](https://mlsanity.com/paper/2310.12982/) (2023)
- [Language as Queries for Referring Video Object Segmentation](https://mlsanity.com/paper/2201.00487/) (2022)
- [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)
- [End-to-End Referring Video Object Segmentation with Multimodal Transformers](https://mlsanity.com/paper/2111.14821/) (2021)
- [VISA: Reasoning Video Object Segmentation via Large Language Models](https://mlsanity.com/paper/2407.11325/) (2024)
- [VITA: Video Instance Segmentation via Object Token Association](https://mlsanity.com/paper/2206.04403/) (2022)
- [SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation](https://mlsanity.com/paper/2305.17011/) (2023)
- [Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation](https://mlsanity.com/paper/2404.03645/) (2024)
- [Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation](https://mlsanity.com/paper/2305.16318/) (2023)
- [Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation](https://mlsanity.com/paper/2106.01061/) (2021)
- [Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation](https://mlsanity.com/paper/2407.07427/) (2024)
- [PVUW 2024 Challenge on Complex Video Understanding: Methods and Results](https://mlsanity.com/paper/2406.17005/) (2024)
- [LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation](https://mlsanity.com/paper/2409.05847/) (2024)
- [Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track](https://mlsanity.com/paper/2408.10125/) (2024)
- [UNINEXT-Cutie: The 1st Solution for LSVOS Challenge RVOS Track](https://mlsanity.com/paper/2408.10129/) (2024)

## Built on by (most cited first, 3 of 3)

- [The 1st Solution for 7th LSVOS RVOS Track: SaSaSa2VA](https://mlsanity.com/paper/2509.16972/) (2025)
- [LSVOS 2025 Challenge Report: Recent Advances in Complex Video Object Segmentation](https://mlsanity.com/paper/2510.11063/) (2025)
- [Mathematical Reasoning via Intervention-Based Time-Series Causal Discovery Using LLMs as Concept Mastery Simulators](https://mlsanity.com/paper/2605.07600/) (2026)

## Abstract (arXiv)

Motion expression video segmentation is designed to segment objects in accordance with the input motion expressions. In contrast to the conventional Referring Video Object Segmentation (RVOS), it places emphasis on motion as well as multi-object expressions, making it more arduous. Recently, Large Multimodal Models (LMMs) have begun to shine in RVOS due to their powerful vision-language perception capabilities. In this work, we propose a simple and effective inference optimization method to fully unleash the potential of LMMs in referring video segmentation. Firstly, we use Sa2VA as our baseline, which is a unified LMM for dense grounded understanding of both images and videos. Secondly, we uniformly sample the video frames during the inference process to enhance the model's understanding of the entire video. Finally, we integrate the results of multiple expert models to mitigate the erroneous predictions of a single model. Our solution achieved 61.98% J&F on the MeViS test set and ranked 1st place in the 4th PVUW Challenge MeViS Track at CVPR 2025.