Improving video chapter markers with smarter context and boundaries
CausalChapter: Improving Long-Video Chaptering with Interventional Dependency Modeling
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Long instructional videos are hard to navigate without clear chapter markers. The authors developed a method called CausalChapter that helps computers better find where chapters start and what they should be called. Their approach uses special techniques to see how different parts of the video influence each other, helping to avoid mistakes when splitting chapters and making chapter descriptions clearer. This leads to easier browsing in long, detailed videos like lectures.
long-form instructional videosvideo chapteringboundary localizationlanguage modelscontext modelingcausal inferenceinterventionscaptioning
Authors
Xinran Duan, Guozhang Li, Yaoyao Zhong, Mei Wang, Lizhi Wang, Hua Huang
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.