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

Source: [VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering](<https://www.sota2.com/research/paper/68fa7a631e209131cea82ccc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:19:03.690Z

Authors: Yiran Meng, Junhong Ye, Wei Zhou, Guanghui Yue, Xudong Mao, Ruomei Wang, Baoquan Zhao

Published: 2025-08-05T03:33:24.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.03039>)

[PDF](<https://arxiv.org/pdf/2508.03039.pdf>)