CausalChapter: Improving Long-Video Chaptering with Interventional Dependency Modeling

2026-09-08

AI Summary

本文提出CausalChapter框架，通过轻量级干预解决长视频自动分章中的边界误差传播和跨章节上下文碎片化问题，提高边界定位、章节描述质量和连贯性。

Abstract

Long-form instructional videos require automatic chaptering to support browsing, navigation, and knowledge access. Recent long-context language models can perform chaptering from textualized video inputs, but they remain costly and brittle for content-dense lecture videos with long transcripts, smooth topic transitions, and detailed chapter outputs. A scalable segment-then-caption paradigm reduces this cost, but introduces two new challenges: boundary error propagation and fragmented cross-chapter context. We propose \textbf{CausalChapter}, an intervention-inspired framework for long-video chaptering that estimates prediction-level influence through lightweight masking and removal interventions. For boundary localization, our Local Dependency Shift module detects drops in predictive dependency between adjacent temporal windows; for chapter description generation, our Cross-Segment Support Selection module reranks historical contexts according to their support for the current prediction. Experiments on long-video chaptering benchmarks show that CausalChapter improves boundary localization, chapter description quality, and cross-chapter coherence.

Problem

• long-video chaptering
• instructional videos
• boundary error propagation
• cross-chapter context

Innovation

• Interventional Dependency Modeling
• Local Dependency Shift
• Cross-Segment Support Selection