Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Weiyu, Chen, Ziyang, Wang, Shaoguang, He, Jianxiang, Xu, Yijie, Ye, Jinhui, Sun, Ying, Xiong, Hui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915291252916224
author Guo, Weiyu
Chen, Ziyang
Wang, Shaoguang
He, Jianxiang
Xu, Yijie
Ye, Jinhui
Sun, Ying
Xiong, Hui
author_facet Guo, Weiyu
Chen, Ziyang
Wang, Shaoguang
He, Jianxiang
Xu, Yijie
Ye, Jinhui
Sun, Ying
Xiong, Hui
contents Understanding long video content is a complex endeavor that often relies on densely sampled frame captions or end-to-end feature selectors, yet these techniques commonly overlook the logical relationships between textual queries and visual elements. In practice, computational constraints necessitate coarse frame subsampling, a challenge analogous to "finding a needle in a haystack." To address this issue, we introduce a semantics-driven search framework that reformulates keyframe selection under the paradigm of Visual Semantic-Logical Search. Specifically, we systematically define four fundamental logical dependencies: 1) spatial co-occurrence, 2) temporal proximity, 3) attribute dependency, and 4) causal order. These relations dynamically update frame sampling distributions through an iterative refinement process, enabling context-aware identification of semantically critical frames tailored to specific query requirements. Our method establishes new SOTA performance on the manually annotated benchmark in key-frame selection metrics. Furthermore, when applied to downstream video question-answering tasks, the proposed approach demonstrates the best performance gains over existing methods on LongVideoBench and Video-MME, validating its effectiveness in bridging the logical gap between textual queries and visual-temporal reasoning. The code will be publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2503_13139
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding
Guo, Weiyu
Chen, Ziyang
Wang, Shaoguang
He, Jianxiang
Xu, Yijie
Ye, Jinhui
Sun, Ying
Xiong, Hui
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Image and Video Processing
Understanding long video content is a complex endeavor that often relies on densely sampled frame captions or end-to-end feature selectors, yet these techniques commonly overlook the logical relationships between textual queries and visual elements. In practice, computational constraints necessitate coarse frame subsampling, a challenge analogous to "finding a needle in a haystack." To address this issue, we introduce a semantics-driven search framework that reformulates keyframe selection under the paradigm of Visual Semantic-Logical Search. Specifically, we systematically define four fundamental logical dependencies: 1) spatial co-occurrence, 2) temporal proximity, 3) attribute dependency, and 4) causal order. These relations dynamically update frame sampling distributions through an iterative refinement process, enabling context-aware identification of semantically critical frames tailored to specific query requirements. Our method establishes new SOTA performance on the manually annotated benchmark in key-frame selection metrics. Furthermore, when applied to downstream video question-answering tasks, the proposed approach demonstrates the best performance gains over existing methods on LongVideoBench and Video-MME, validating its effectiveness in bridging the logical gap between textual queries and visual-temporal reasoning. The code will be publicly available.
title Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Image and Video Processing
url https://arxiv.org/abs/2503.13139