@inproceedings{duan-etal-2026-causalchapter,
title = "{C}ausal{C}hapter: Improving Long-Form Video Chaptering with Interventional Dependency Modeling",
author = "Duan, Xinran and
Li, Guozhang and
Zhong, Yaoyao and
Wang, Mei and
Wang, Lizhi and
Huang, Hua",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.635/",
pages = "14616--14632",
ISBN = "979-8-89176-459-0",
abstract = "Long-form instructional videos require automatic chaptering for efficient organization and navigation. While long-context language models can predict chapters from textualized video representations, they become costly for content-dense videos with long transcripts, smooth topic transitions, and detailed chapter descriptions. A scalable segment-then-caption paradigm reduces this cost but suffers from boundary error propagation and fragmented cross-chapter context. We propose $\textbf{CausalChapter}$, a causal-inspired interventional dependency enhancement framework for long-video chaptering. Our method estimates the observable influence of semantic units and context segments through lightweight masking and removal interventions. For boundary localization, it detects dependency changes between adjacent temporal windows via masking-based feature reconstruction; for chapter description generation, it selects cross-chapter contexts according to their influence on generated descriptions. Experiments on long-video chaptering benchmarks show consistent improvements in boundary localization, description quality, and cross-chapter coherence."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="duan-etal-2026-causalchapter">
<titleInfo>
<title>CausalChapter: Improving Long-Form Video Chaptering with Interventional Dependency Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinran</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guozhang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaoyao</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizhi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Long-form instructional videos require automatic chaptering for efficient organization and navigation. While long-context language models can predict chapters from textualized video representations, they become costly for content-dense videos with long transcripts, smooth topic transitions, and detailed chapter descriptions. A scalable segment-then-caption paradigm reduces this cost but suffers from boundary error propagation and fragmented cross-chapter context. We propose CausalChapter, a causal-inspired interventional dependency enhancement framework for long-video chaptering. Our method estimates the observable influence of semantic units and context segments through lightweight masking and removal interventions. For boundary localization, it detects dependency changes between adjacent temporal windows via masking-based feature reconstruction; for chapter description generation, it selects cross-chapter contexts according to their influence on generated descriptions. Experiments on long-video chaptering benchmarks show consistent improvements in boundary localization, description quality, and cross-chapter coherence.</abstract>
<identifier type="citekey">duan-etal-2026-causalchapter</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.635/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>14616</start>
<end>14632</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CausalChapter: Improving Long-Form Video Chaptering with Interventional Dependency Modeling
%A Duan, Xinran
%A Li, Guozhang
%A Zhong, Yaoyao
%A Wang, Mei
%A Wang, Lizhi
%A Huang, Hua
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F duan-etal-2026-causalchapter
%X Long-form instructional videos require automatic chaptering for efficient organization and navigation. While long-context language models can predict chapters from textualized video representations, they become costly for content-dense videos with long transcripts, smooth topic transitions, and detailed chapter descriptions. A scalable segment-then-caption paradigm reduces this cost but suffers from boundary error propagation and fragmented cross-chapter context. We propose CausalChapter, a causal-inspired interventional dependency enhancement framework for long-video chaptering. Our method estimates the observable influence of semantic units and context segments through lightweight masking and removal interventions. For boundary localization, it detects dependency changes between adjacent temporal windows via masking-based feature reconstruction; for chapter description generation, it selects cross-chapter contexts according to their influence on generated descriptions. Experiments on long-video chaptering benchmarks show consistent improvements in boundary localization, description quality, and cross-chapter coherence.
%U https://aclanthology.org/2026.emnlp-main.635/
%P 14616-14632
Markdown (Informal)
[CausalChapter: Improving Long-Form Video Chaptering with Interventional Dependency Modeling](https://aclanthology.org/2026.emnlp-main.635/) (Duan et al., EMNLP 2026)
ACL