MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Luo, Fuwen, Lou, Shengfeng, Chen, Chi, Wang, Ziyue, Li, Chenliang, Shen, Weizhou, Guo, Jiyue, Li, Peng, Yan, Ming, Zhang, Ji, Huang, Fei, Liu, Yang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911602211553280
author Luo, Fuwen
Lou, Shengfeng
Chen, Chi
Wang, Ziyue
Li, Chenliang
Shen, Weizhou
Guo, Jiyue
Li, Peng
Yan, Ming
Zhang, Ji
Huang, Fei
Liu, Yang
author_facet Luo, Fuwen
Lou, Shengfeng
Chen, Chi
Wang, Ziyue
Li, Chenliang
Shen, Weizhou
Guo, Jiyue
Li, Peng
Yan, Ming
Zhang, Ji
Huang, Fei
Liu, Yang
contents Video temporal understanding is crucial for multimodal large language models (MLLMs) to reason over events in videos. Despite recent advances in general video understanding, current MLLMs still struggle with fine-grained temporal reasoning. While reinforcement learning (RL) has been explored to address this issue recently, existing RL approaches remain limited in performance on time-sensitive tasks. In this work, we propose MUSEG, a novel RL-based method that enhances temporal understanding by introducing timestamp-aware multi-segment grounding. MUSEG enables MLLMs to align queries with multiple relevant video segments, promoting more comprehensive temporal reasoning. To facilitate effective learning, we design a customized RL training recipe with phased rewards that progressively guides the model toward temporally grounded reasoning. Extensive experiments on temporal grounding and time-sensitive video question answering (QA) tasks demonstrate that MUSEG significantly outperforms existing methods and generalizes well across diverse temporal understanding scenarios. View our project at https://github.com/THUNLP-MT/MUSEG.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20715
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding
Luo, Fuwen
Lou, Shengfeng
Chen, Chi
Wang, Ziyue
Li, Chenliang
Shen, Weizhou
Guo, Jiyue
Li, Peng
Yan, Ming
Zhang, Ji
Huang, Fei
Liu, Yang
Computer Vision and Pattern Recognition
Computation and Language
Video temporal understanding is crucial for multimodal large language models (MLLMs) to reason over events in videos. Despite recent advances in general video understanding, current MLLMs still struggle with fine-grained temporal reasoning. While reinforcement learning (RL) has been explored to address this issue recently, existing RL approaches remain limited in performance on time-sensitive tasks. In this work, we propose MUSEG, a novel RL-based method that enhances temporal understanding by introducing timestamp-aware multi-segment grounding. MUSEG enables MLLMs to align queries with multiple relevant video segments, promoting more comprehensive temporal reasoning. To facilitate effective learning, we design a customized RL training recipe with phased rewards that progressively guides the model toward temporally grounded reasoning. Extensive experiments on temporal grounding and time-sensitive video question answering (QA) tasks demonstrate that MUSEG significantly outperforms existing methods and generalizes well across diverse temporal understanding scenarios. View our project at https://github.com/THUNLP-MT/MUSEG.
title MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2505.20715