@inproceedings{jeon-etal-2025-sali4vid,
title = "{S}ali4{V}id: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning",
author = "Jeon, MinJu and
Kim, Si-Woo and
Kim, Ye-Chan and
Kim, HyunGee and
Kim, Dong-Jin",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1308/",
pages = "25788--25801",
ISBN = "979-8-89176-332-6",
abstract = "Dense video captioning aims to temporally localize events in video and generate captions for each event. While recent works propose end-to-end models, they suffer from two limitations: (1) applying timestamp supervision only to text while treating all video frames equally, and (2) retrieving captions from fixed-size video chunks, overlooking scene transitions. To address these, we propose **Sali4Vid**, a simple yet effective saliency-aware framework. We introduce Saliency-aware Video Reweighting, which converts timestamp annotations into sigmoid-based frame importance weights, and Semantic-based Adaptive Caption Retrieval, which segments videos by frame similarity to capture scene transitions and improve caption retrieval. Sali4Vid achieves state-of-the-art results on YouCook2 and ViTT, demonstrating the benefit of jointly improving video weighting and retrieval for dense video captioning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jeon-etal-2025-sali4vid">
<titleInfo>
<title>Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning</title>
</titleInfo>
<name type="personal">
<namePart type="given">MinJu</namePart>
<namePart type="family">Jeon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Si-Woo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ye-Chan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">HyunGee</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dong-Jin</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Dense video captioning aims to temporally localize events in video and generate captions for each event. While recent works propose end-to-end models, they suffer from two limitations: (1) applying timestamp supervision only to text while treating all video frames equally, and (2) retrieving captions from fixed-size video chunks, overlooking scene transitions. To address these, we propose **Sali4Vid**, a simple yet effective saliency-aware framework. We introduce Saliency-aware Video Reweighting, which converts timestamp annotations into sigmoid-based frame importance weights, and Semantic-based Adaptive Caption Retrieval, which segments videos by frame similarity to capture scene transitions and improve caption retrieval. Sali4Vid achieves state-of-the-art results on YouCook2 and ViTT, demonstrating the benefit of jointly improving video weighting and retrieval for dense video captioning.</abstract>
<identifier type="citekey">jeon-etal-2025-sali4vid</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1308/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>25788</start>
<end>25801</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning
%A Jeon, MinJu
%A Kim, Si-Woo
%A Kim, Ye-Chan
%A Kim, HyunGee
%A Kim, Dong-Jin
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F jeon-etal-2025-sali4vid
%X Dense video captioning aims to temporally localize events in video and generate captions for each event. While recent works propose end-to-end models, they suffer from two limitations: (1) applying timestamp supervision only to text while treating all video frames equally, and (2) retrieving captions from fixed-size video chunks, overlooking scene transitions. To address these, we propose **Sali4Vid**, a simple yet effective saliency-aware framework. We introduce Saliency-aware Video Reweighting, which converts timestamp annotations into sigmoid-based frame importance weights, and Semantic-based Adaptive Caption Retrieval, which segments videos by frame similarity to capture scene transitions and improve caption retrieval. Sali4Vid achieves state-of-the-art results on YouCook2 and ViTT, demonstrating the benefit of jointly improving video weighting and retrieval for dense video captioning.
%U https://aclanthology.org/2025.emnlp-main.1308/
%P 25788-25801
Markdown (Informal)
[Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning](https://aclanthology.org/2025.emnlp-main.1308/) (Jeon et al., EMNLP 2025)
ACL