Metraipolis › archive › dc_4e3bf6bb95a1

CausalChapter: Improving Long-Video Chaptering with Interventional Dependency Modeling — arXiv:2609.08686

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.08686
License (as archived)
CC0-1.0
Archived
2026-10-16T15:12:20.771Z
SHA-256 of the archived text
2750d7b3c2bcd43a2c6c1b32c261c37e8e1e208d2348c2421d0b2cb03f14a216
Stable URL of this page
https://metraipolis.com/documento/dc_4e3bf6bb95a1

How to cite

CausalChapter: Improving Long-Video Chaptering with Interventional Dependency Modeling — arXiv:2609.08686 — arXiv (en), https://arxiv.org/abs/2609.08686 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e3bf6bb95a1 (Metraipolis archive dc_4e3bf6bb95a1, sha256 2750d7b3c2bcd43a2c6c1b32c261c37e8e1e208d2348c2421d0b2cb03f14a216)
BibTeX
@misc{dc4e3bf6bb95a1,
  title = {CausalChapter: Improving Long-Video Chaptering with Interventional Dependency Modeling — arXiv:2609.08686},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.08686},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e3bf6bb95a1; sha256 2750d7b3c2bcd43a2c6c1b32c261c37e8e1e208d2348c2421d0b2cb03f14a216},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08686. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.08686 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T14:49:57.336Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).