@inproceedings{pennec-etal-2026-minimal,
title = "Minimal Clips, Maximum Salience: Long Video Summarization via Key Moment Extraction",
author = "Pennec, Galann and
Liu, Zhengyuan and
Asher, Nicholas and
Muller, Philippe and
Chen, Nancy",
editor = "Riccardi, Giuseppe and
Mousavi, Seyed Mahed and
Torres, Maria Ines and
Yoshino, Koichiro and
Callejas, Zoraida and
Chowdhury, Shammur Absar and
Chen, Yun-Nung and
Bechet, Frederic and
Gustafson, Joakim and
Damnati, G{\'e}raldine and
Papangelis, Alex and
D{'}Haro, Luis Fernando and
Mendon{\c{c}}a, John and
Bernardi, Raffaella and
Hakkani-Tur, Dilek and
Di Fabbrizio, Giuseppe {''}Pino{''} and
Kawahara, Tatsuya and
Alam, Firoj and
Tur, Gokhan and
Johnston, Michael",
booktitle = "Proceedings of the 16th International Workshop on Spoken Dialogue System Technology",
month = feb,
year = "2026",
address = "Trento, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.iwsds-1.22/",
pages = "205--221",
abstract = "Vision-Language Models ({VLM}s) are able to process increasingly longer videos. Yet, important visual information is easily lost throughout the entire context and missed by {VLM}s. Also, it is important to design tools that enable cost-effective analysis of lengthy video content. In this paper, we propose a clip selection method that targets key video moments to be included in a multimodal summary. We divide the video into short clips and generate compact visual descriptions of each using a lightweight video captioning model. These are then passed to a large language model ({LLM}), which selects the K clips containing the most relevant visual information for a multimodal summary. We evaluate our approach on reference clips for the task, automatically derived from full human-annotated screenplays and summaries in the {M}ovie{S}um dataset. We further show that these reference clips (less than 6{\%} of the movie) are sufficient to build a complete multimodal summary of the movies in {M}ovie{S}um. Using our clip selection method, we achieve a summarization performance close to that of these reference clips while capturing substantially more relevant video information than random clip selection. Importantly, we maintain low computational cost by relying on a lightweight captioning model."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pennec-etal-2026-minimal">
<titleInfo>
<title>Minimal Clips, Maximum Salience: Long Video Summarization via Key Moment Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galann</namePart>
<namePart type="family">Pennec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Asher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Muller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-02</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Workshop on Spoken Dialogue System Technology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Riccardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seyed</namePart>
<namePart type="given">Mahed</namePart>
<namePart type="family">Mousavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Ines</namePart>
<namePart type="family">Torres</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koichiro</namePart>
<namePart type="family">Yoshino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zoraida</namePart>
<namePart type="family">Callejas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederic</namePart>
<namePart type="family">Bechet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Gustafson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Géraldine</namePart>
<namePart type="family">Damnati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="given">Fernando</namePart>
<namePart type="family">D’Haro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Mendonça</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raffaella</namePart>
<namePart type="family">Bernardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="given">”Pino”</namePart>
<namePart type="family">Di Fabbrizio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gokhan</namePart>
<namePart type="family">Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Johnston</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Trento, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Vision-Language Models (VLMs) are able to process increasingly longer videos. Yet, important visual information is easily lost throughout the entire context and missed by VLMs. Also, it is important to design tools that enable cost-effective analysis of lengthy video content. In this paper, we propose a clip selection method that targets key video moments to be included in a multimodal summary. We divide the video into short clips and generate compact visual descriptions of each using a lightweight video captioning model. These are then passed to a large language model (LLM), which selects the K clips containing the most relevant visual information for a multimodal summary. We evaluate our approach on reference clips for the task, automatically derived from full human-annotated screenplays and summaries in the MovieSum dataset. We further show that these reference clips (less than 6% of the movie) are sufficient to build a complete multimodal summary of the movies in MovieSum. Using our clip selection method, we achieve a summarization performance close to that of these reference clips while capturing substantially more relevant video information than random clip selection. Importantly, we maintain low computational cost by relying on a lightweight captioning model.</abstract>
<identifier type="citekey">pennec-etal-2026-minimal</identifier>
<location>
<url>https://aclanthology.org/2026.iwsds-1.22/</url>
</location>
<part>
<date>2026-02</date>
<extent unit="page">
<start>205</start>
<end>221</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Minimal Clips, Maximum Salience: Long Video Summarization via Key Moment Extraction
%A Pennec, Galann
%A Liu, Zhengyuan
%A Asher, Nicholas
%A Muller, Philippe
%A Chen, Nancy
%Y Riccardi, Giuseppe
%Y Mousavi, Seyed Mahed
%Y Torres, Maria Ines
%Y Yoshino, Koichiro
%Y Callejas, Zoraida
%Y Chowdhury, Shammur Absar
%Y Chen, Yun-Nung
%Y Bechet, Frederic
%Y Gustafson, Joakim
%Y Damnati, Géraldine
%Y Papangelis, Alex
%Y D’Haro, Luis Fernando
%Y Mendonça, John
%Y Bernardi, Raffaella
%Y Hakkani-Tur, Dilek
%Y Di Fabbrizio, Giuseppe ”Pino”
%Y Kawahara, Tatsuya
%Y Alam, Firoj
%Y Tur, Gokhan
%Y Johnston, Michael
%S Proceedings of the 16th International Workshop on Spoken Dialogue System Technology
%D 2026
%8 February
%I Association for Computational Linguistics
%C Trento, Italy
%F pennec-etal-2026-minimal
%X Vision-Language Models (VLMs) are able to process increasingly longer videos. Yet, important visual information is easily lost throughout the entire context and missed by VLMs. Also, it is important to design tools that enable cost-effective analysis of lengthy video content. In this paper, we propose a clip selection method that targets key video moments to be included in a multimodal summary. We divide the video into short clips and generate compact visual descriptions of each using a lightweight video captioning model. These are then passed to a large language model (LLM), which selects the K clips containing the most relevant visual information for a multimodal summary. We evaluate our approach on reference clips for the task, automatically derived from full human-annotated screenplays and summaries in the MovieSum dataset. We further show that these reference clips (less than 6% of the movie) are sufficient to build a complete multimodal summary of the movies in MovieSum. Using our clip selection method, we achieve a summarization performance close to that of these reference clips while capturing substantially more relevant video information than random clip selection. Importantly, we maintain low computational cost by relying on a lightweight captioning model.
%U https://aclanthology.org/2026.iwsds-1.22/
%P 205-221
Markdown (Informal)
[Minimal Clips, Maximum Salience: Long Video Summarization via Key Moment Extraction](https://aclanthology.org/2026.iwsds-1.22/) (Pennec et al., IWSDS 2026)
ACL