Video-QTR: Query-Driven Temporal Reasoning Framework for Lightweight Video Understanding

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhao, Xinkui, Wang, Zuxin, Zhang, Yifan, Cheng, Guanjie, Xu, Yueshen, Deng, Shuiguang, Liu, Chang, Wang, Naibo, Yin, Jianwei
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909953664483328
author Zhao, Xinkui
Wang, Zuxin
Zhang, Yifan
Cheng, Guanjie
Xu, Yueshen
Deng, Shuiguang
Liu, Chang
Wang, Naibo
Yin, Jianwei
author_facet Zhao, Xinkui
Wang, Zuxin
Zhang, Yifan
Cheng, Guanjie
Xu, Yueshen
Deng, Shuiguang
Liu, Chang
Wang, Naibo
Yin, Jianwei
contents The rapid development of multimodal large-language models (MLLMs) has significantly expanded the scope of visual language reasoning, enabling unified systems to interpret and describe complex visual content. However, applying these models to long-video understanding remains computationally intensive. Dense frame encoding generates excessive visual tokens, leading to high memory consumption, redundant computation, and limited scalability in real-world applications. This inefficiency highlights a key limitation of the traditional process-then-reason paradigm, which analyzes visual streams exhaustively before semantic reasoning. To address this challenge, we introduce Video-QTR (Query-Driven Temporal Reasoning), a lightweight framework that redefines video comprehension as a query-guided reasoning process. Instead of encoding every frame, Video-QTR dynamically allocates perceptual resources based on the semantic intent of the query, creating an adaptive feedback loop between reasoning and perception. Extensive experiments across five benchmarks: MSVD-QA, Activity Net-QA, Movie Chat, and Video MME demonstrate that Video-QTR achieves state-of-the-art performance while reducing input frame consumption by up to 73%. These results confirm that query-driven temporal reasoning provides an efficient and scalable solution for video understanding.
format Preprint
id arxiv_https___arxiv_org_abs_2512_09354
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Video-QTR: Query-Driven Temporal Reasoning Framework for Lightweight Video Understanding
Zhao, Xinkui
Wang, Zuxin
Zhang, Yifan
Cheng, Guanjie
Xu, Yueshen
Deng, Shuiguang
Liu, Chang
Wang, Naibo
Yin, Jianwei
Computer Vision and Pattern Recognition
The rapid development of multimodal large-language models (MLLMs) has significantly expanded the scope of visual language reasoning, enabling unified systems to interpret and describe complex visual content. However, applying these models to long-video understanding remains computationally intensive. Dense frame encoding generates excessive visual tokens, leading to high memory consumption, redundant computation, and limited scalability in real-world applications. This inefficiency highlights a key limitation of the traditional process-then-reason paradigm, which analyzes visual streams exhaustively before semantic reasoning. To address this challenge, we introduce Video-QTR (Query-Driven Temporal Reasoning), a lightweight framework that redefines video comprehension as a query-guided reasoning process. Instead of encoding every frame, Video-QTR dynamically allocates perceptual resources based on the semantic intent of the query, creating an adaptive feedback loop between reasoning and perception. Extensive experiments across five benchmarks: MSVD-QA, Activity Net-QA, Movie Chat, and Video MME demonstrate that Video-QTR achieves state-of-the-art performance while reducing input frame consumption by up to 73%. These results confirm that query-driven temporal reasoning provides an efficient and scalable solution for video understanding.
title Video-QTR: Query-Driven Temporal Reasoning Framework for Lightweight Video Understanding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.09354