VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Meng, Yiran, Ye, Junhong, Zhou, Wei, Yue, Guanghui, Mao, Xudong, Wang, Ruomei, Zhao, Baoquan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911092154826752
author Meng, Yiran
Ye, Junhong
Zhou, Wei
Yue, Guanghui
Mao, Xudong
Wang, Ruomei
Zhao, Baoquan
author_facet Meng, Yiran
Ye, Junhong
Zhou, Wei
Yue, Guanghui
Mao, Xudong
Wang, Ruomei
Zhao, Baoquan
contents Cross-video question answering presents significant challenges beyond traditional single-video understanding, particularly in establishing meaningful connections across video streams and managing the complexity of multi-source information retrieval. We introduce VideoForest, a novel framework that addresses these challenges through person-anchored hierarchical reasoning. Our approach leverages person-level features as natural bridge points between videos, enabling effective cross-video understanding without requiring end-to-end training. VideoForest integrates three key innovations: 1) a human-anchored feature extraction mechanism that employs ReID and tracking algorithms to establish robust spatiotemporal relationships across multiple video sources; 2) a multi-granularity spanning tree structure that hierarchically organizes visual content around person-level trajectories; and 3) a multi-agent reasoning framework that efficiently traverses this hierarchical structure to answer complex cross-video queries. To evaluate our approach, we develop CrossVideoQA, a comprehensive benchmark dataset specifically designed for person-centric cross-video analysis. Experimental results demonstrate VideoForest's superior performance in cross-video reasoning tasks, achieving 71.93% accuracy in person recognition, 83.75% in behavior analysis, and 51.67% in summarization and reasoning, significantly outperforming existing methods. Our work establishes a new paradigm for cross-video understanding by unifying multiple video streams through person-level features, enabling sophisticated reasoning across distributed visual information while maintaining computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03039
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering
Meng, Yiran
Ye, Junhong
Zhou, Wei
Yue, Guanghui
Mao, Xudong
Wang, Ruomei
Zhao, Baoquan
Computer Vision and Pattern Recognition
Multimedia
Cross-video question answering presents significant challenges beyond traditional single-video understanding, particularly in establishing meaningful connections across video streams and managing the complexity of multi-source information retrieval. We introduce VideoForest, a novel framework that addresses these challenges through person-anchored hierarchical reasoning. Our approach leverages person-level features as natural bridge points between videos, enabling effective cross-video understanding without requiring end-to-end training. VideoForest integrates three key innovations: 1) a human-anchored feature extraction mechanism that employs ReID and tracking algorithms to establish robust spatiotemporal relationships across multiple video sources; 2) a multi-granularity spanning tree structure that hierarchically organizes visual content around person-level trajectories; and 3) a multi-agent reasoning framework that efficiently traverses this hierarchical structure to answer complex cross-video queries. To evaluate our approach, we develop CrossVideoQA, a comprehensive benchmark dataset specifically designed for person-centric cross-video analysis. Experimental results demonstrate VideoForest's superior performance in cross-video reasoning tasks, achieving 71.93% accuracy in person recognition, 83.75% in behavior analysis, and 51.67% in summarization and reasoning, significantly outperforming existing methods. Our work establishes a new paradigm for cross-video understanding by unifying multiple video streams through person-level features, enabling sophisticated reasoning across distributed visual information while maintaining computational efficiency.
title VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering
topic Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2508.03039