Saved in:
Bibliographic Details
Main Authors: Xie, Yuan, Chen, Tianshui, Ge, Zheng, Ni, Lionel
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.20478
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917545477406720
author Xie, Yuan
Chen, Tianshui
Ge, Zheng
Ni, Lionel
author_facet Xie, Yuan
Chen, Tianshui
Ge, Zheng
Ni, Lionel
contents Long-form video understanding, characterized by long-range temporal dependencies and multiple events, remains a challenge. Existing methods often rely on static reasoning or external visual-language models (VLMs), which face issues like complexity and sub-optimal performance due to the lack of end-to-end training. In this paper, we propose Video-MTR, a reinforced multi-turn reasoning framework designed to enable iterative key video segment selection and question comprehension. Unlike traditional video reasoning pipeline, which generate predictions in a single turn, Video-MTR performs reasoning in multiple turns, selecting video segments progressively based on the evolving understanding of previously processed segments and the current question. This iterative process allows for a more refined and contextually aware analysis of the video. To ensure intermediate reasoning process, we introduce a novel gated bi-level reward system, combining trajectory-level rewards based on answer correctness and turn-level rewards emphasizing frame-query relevance. This system optimizes both video segment selection and question comprehension, eliminating the need for external VLMs and allowing end-to-end training. Extensive experiments on benchmarks like VideoMME, MLVU, and EgoSchema demonstrate that Video-MTR outperforms existing methods in both accuracy and efficiency, advancing the state-of-the-art in long video understanding.
format Preprint
id arxiv_https___arxiv_org_abs_2508_20478
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding
Xie, Yuan
Chen, Tianshui
Ge, Zheng
Ni, Lionel
Computer Vision and Pattern Recognition
Long-form video understanding, characterized by long-range temporal dependencies and multiple events, remains a challenge. Existing methods often rely on static reasoning or external visual-language models (VLMs), which face issues like complexity and sub-optimal performance due to the lack of end-to-end training. In this paper, we propose Video-MTR, a reinforced multi-turn reasoning framework designed to enable iterative key video segment selection and question comprehension. Unlike traditional video reasoning pipeline, which generate predictions in a single turn, Video-MTR performs reasoning in multiple turns, selecting video segments progressively based on the evolving understanding of previously processed segments and the current question. This iterative process allows for a more refined and contextually aware analysis of the video. To ensure intermediate reasoning process, we introduce a novel gated bi-level reward system, combining trajectory-level rewards based on answer correctness and turn-level rewards emphasizing frame-query relevance. This system optimizes both video segment selection and question comprehension, eliminating the need for external VLMs and allowing end-to-end training. Extensive experiments on benchmarks like VideoMME, MLVU, and EgoSchema demonstrate that Video-MTR outperforms existing methods in both accuracy and efficiency, advancing the state-of-the-art in long video understanding.
title Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.20478