用干预机制提升长视频分章准确率，解决边界错传与上下文断裂问题。
CausalChapter: Improving Long-Video Chaptering with Interventional Dependency Modeling
- 通过轻量掩码和移除干预，评估预测影响以定位章节边界。
- 在多个基准上实现更精准的章节划分与更连贯的描述生成。
- 适合需要高质量分章的课程视频、讲座等长内容场景。
长视频教学内容需自动分章以支持浏览与知识检索。现有基于长上下文语言模型的方法虽能处理文本化视频输入，但在内容密集、主题过渡平滑、输出要求详细的讲座类视频中仍存在成本高、鲁棒性差的问题。采用‘分段再摘要’范式可降低成本，但引入边界误差传播与跨章节上下文断裂新挑战。本文提出CausalChapter，一种受干预启发的长视频分章框架，通过轻量级掩码与移除干预，估算预测层级的影响。局部依赖变化模块检测相邻时间窗口间预测依赖下降，用于边界定位；跨段支持选择模块根据历史上下文对当前预测的支持度重新排序，提升章节描述质量。在多个长视频分章基准上，CausalChapter显著提升边界定位精度、章节描述质量和跨章节连贯性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。