CausalChapter: Improving Long-Video Chaptering with Interventional Dependency Modeling

• URL: http://arxiv.org/abs/2609.08686v1
• Date: Tue, 08 Sep 2026 12:54:57 GMT
• Title: CausalChapter: Improving Long-Video Chaptering with Interventional Dependency Modeling
• Abstract summary: Long-form instructional videos require automatic chaptering to support browsing, navigation, and knowledge access.<n>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.<n>A scalable segment-then-caption paradigm reduces this cost, but introduces two new challenges: boundary error propagation and fragmented cross-chapter context.<n>We propose textbfCausalChapter, an intervention-inspired framework for long-video chaptering that estimates prediction-level influence through lightweight masking and removal
• Score: 32.8404351380861
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Online Reasoning Video Object Segmentation [26.75863941739301]
  Reasoning video object segmentation predicts pixel-level masks in videos from natural-language queries.<n>We study Online Reasoning Video Object (ORVOS), where models incrementally interpret queries using only past and current frames.<n>We introduce ORVOSB, a benchmark with frame-level causal annotations and referent-shift labels, comprising 210 videos, 12,907 annotated frames, and 512 queries across five reasoning categories.
  arXiv  Detail & Related papers  (2026-04-13T12:55:56Z)
• Toward General Semantic Chunking: A Discriminative Framework for Ultra-Long Documents [10.682600460180174]
  Long-document topic segmentation plays an important role in information retrieval and document understanding.<n>Traditional discriminative models are constrained by fixed windows and cannot model document-level semantics.<n>generative large language models can output paragraph boundaries, but inference is expensive and long inputs are difficult to support.
  arXiv  Detail & Related papers  (2025-12-23T16:16:51Z)
• ARC-Chapter: Structuring Hour-Long Videos into Navigable Chapters and Hierarchical Summaries [77.41072125938636]
  ARC-Chapter is the first large-scale video chaptering model trained on over million-level long video chapters.<n>It unifies ASR transcripts, scene texts, visual captions into multi-level annotations, from short title to long summaries.<n>It establishes a new state-of-the-art by a significant margin, outperforming the previous best by 14.0% in F1 score and 11.3% in SODA score.
  arXiv  Detail & Related papers  (2025-11-18T10:53:14Z)
• Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding [56.45689495743107]
  Vgent is a graph-based retrieval-reasoning-augmented generation framework to enhance LVLMs for long video understanding.<n>We evaluate our framework with various open-source LVLMs on three long-video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-10-15T19:14:58Z)
• Mixture of Contexts for Long Video Generation [72.96361488755986]
  We recast long-context video generation as an internal information retrieval task.<n>We propose a simple, learnable sparse attention routing module, Mixture of Contexts (MoC), as an effective long-term memory retrieval engine.<n>As we scale the data and gradually sparsify the routing, the model allocates compute to salient history, preserving identities, actions, and scenes over minutes of content.
  arXiv  Detail & Related papers  (2025-08-28T17:57:55Z)
• Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs [59.854331104466254]
  We address the task of video chaptering, i.e., partitioning a long video timeline into semantic units and generating corresponding chapter titles.<n>We propose a lightweight speech-guided frame selection strategy based on speech transcript content, and experimentally demonstrate remarkable advantages.<n>Our results demonstrate substantial improvements over the state of the art on the recent VidChapters-7M benchmark.
  arXiv  Detail & Related papers  (2025-03-31T17:41:29Z)
• MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrieval [53.417646562344906]
  Video Moment Retrieval (VMR) aims to localize a specific temporal segment within an untrimmed long video given a natural language query. Existing methods often suffer from inadequate training annotations, i.e., the sentence typically matches with a fraction of the prominent video content in the foreground with limited wording diversity. This intrinsic modality imbalance leaves a considerable portion of visual information remaining unaligned with text. In this work, we take an MLLM as a video narrator to generate plausible textual descriptions of the video, thereby mitigating the modality imbalance and boosting the temporal localization.
  arXiv  Detail & Related papers  (2024-06-25T18:39:43Z)
• Contrastive Language-Action Pre-training for Temporal Localization [64.34349213254312]
  Long-form video understanding requires approaches that are able to temporally localize activities or language. These limitations can be addressed by pre-training on large datasets of temporally trimmed videos supervised by class annotations. We introduce a masked contrastive learning loss to capture visio-linguistic relations between activities, background video clips and language in the form of captions.
  arXiv  Detail & Related papers  (2022-04-26T13:17:50Z)
• ChapterBreak: A Challenge Dataset for Long-Range Language Models [36.54750186213335]
  We introduce ChapterBreak, a challenge dataset that provides an LRLM with a long segment from a narrative that ends at a chapter boundary. A fine-grained human annotation reveals that our dataset contains many complex types of chapter transitions. Experiments on ChapterBreak show that existing LRLMs fail to effectively leverage long-range context.
  arXiv  Detail & Related papers  (2022-04-22T18:20:23Z)
• Topical Change Detection in Documents via Embeddings of Long Sequences [4.13878392637062]
  We formulate the task of text segmentation as an independent supervised prediction task. By fine-tuning on paragraphs of similar sections, we are able to show that learned features encode topic information. Unlike previous approaches, which mostly operate on sentence-level, we consistently use a broader context.
  arXiv  Detail & Related papers  (2020-12-07T12:09:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.