Let Me Finish My Sentence: Video Temporal Grounding with Holistic Text Understanding

Video Temporal Grounding (VTG) aims to identify visual frames in a video clip that match text queries. Recent studies in VTG employ cross-attention to correlate visual frames and text queries as individual token sequences. However, these approaches overlook a crucial aspect of the problem: a holisti...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-10
Hauptverfasser: Woo, Jongbhin, Ryu, Hyeonggon, Jang, Youngjoon, Cho, Jae Won, Joon Son Chung
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Woo, Jongbhin
Ryu, Hyeonggon
Jang, Youngjoon
Cho, Jae Won
Joon Son Chung
description Video Temporal Grounding (VTG) aims to identify visual frames in a video clip that match text queries. Recent studies in VTG employ cross-attention to correlate visual frames and text queries as individual token sequences. However, these approaches overlook a crucial aspect of the problem: a holistic understanding of the query sentence. A model may capture correlations between individual word tokens and arbitrary visual frames while possibly missing out on the global meaning. To address this, we introduce two primary contributions: (1) a visual frame-level gate mechanism that incorporates holistic textual information, (2) cross-modal alignment loss to learn the fine-grained correlation between query and relevant frames. As a result, we regularize the effect of individual word tokens and suppress irrelevant visual frames. We demonstrate that our method outperforms state-of-the-art approaches in VTG benchmarks, indicating that holistic text understanding guides the model to focus on the semantically important parts within the video.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3118116184</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3118116184</sourcerecordid><originalsourceid>FETCH-proquest_journals_31181161843</originalsourceid><addsrcrecordid>eNqNys0KgkAUQOEhCJLyHS60FpwZNWkbmYtcZW1F9JYjNmPzQ_X2SfQArc7ifDPiMc5pkEaMLYhvTB-GIUs2LI65R8ojWigQMiGF6aB4wwmlRdngFi6iRQUl3kel6wEOWjnZCnmDp7Ad5GoQxopmAi8LZ9miNrb-ghWZX-vBoP_rkqyzfbnLg1Grh0Njq145LadVcUpTShOaRvw_9QH_7z_I</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3118116184</pqid></control><display><type>article</type><title>Let Me Finish My Sentence: Video Temporal Grounding with Holistic Text Understanding</title><source>Free E- Journals</source><creator>Woo, Jongbhin ; Ryu, Hyeonggon ; Jang, Youngjoon ; Cho, Jae Won ; Joon Son Chung</creator><creatorcontrib>Woo, Jongbhin ; Ryu, Hyeonggon ; Jang, Youngjoon ; Cho, Jae Won ; Joon Son Chung</creatorcontrib><description>Video Temporal Grounding (VTG) aims to identify visual frames in a video clip that match text queries. Recent studies in VTG employ cross-attention to correlate visual frames and text queries as individual token sequences. However, these approaches overlook a crucial aspect of the problem: a holistic understanding of the query sentence. A model may capture correlations between individual word tokens and arbitrary visual frames while possibly missing out on the global meaning. To address this, we introduce two primary contributions: (1) a visual frame-level gate mechanism that incorporates holistic textual information, (2) cross-modal alignment loss to learn the fine-grained correlation between query and relevant frames. As a result, we regularize the effect of individual word tokens and suppress irrelevant visual frames. We demonstrate that our method outperforms state-of-the-art approaches in VTG benchmarks, indicating that holistic text understanding guides the model to focus on the semantically important parts within the video.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Correlation ; Frames (data processing) ; Queries ; Sentences ; Visual aspects ; Visual effects ; Words (language)</subject><ispartof>arXiv.org, 2024-10</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>781,785</link.rule.ids></links><search><creatorcontrib>Woo, Jongbhin</creatorcontrib><creatorcontrib>Ryu, Hyeonggon</creatorcontrib><creatorcontrib>Jang, Youngjoon</creatorcontrib><creatorcontrib>Cho, Jae Won</creatorcontrib><creatorcontrib>Joon Son Chung</creatorcontrib><title>Let Me Finish My Sentence: Video Temporal Grounding with Holistic Text Understanding</title><title>arXiv.org</title><description>Video Temporal Grounding (VTG) aims to identify visual frames in a video clip that match text queries. Recent studies in VTG employ cross-attention to correlate visual frames and text queries as individual token sequences. However, these approaches overlook a crucial aspect of the problem: a holistic understanding of the query sentence. A model may capture correlations between individual word tokens and arbitrary visual frames while possibly missing out on the global meaning. To address this, we introduce two primary contributions: (1) a visual frame-level gate mechanism that incorporates holistic textual information, (2) cross-modal alignment loss to learn the fine-grained correlation between query and relevant frames. As a result, we regularize the effect of individual word tokens and suppress irrelevant visual frames. We demonstrate that our method outperforms state-of-the-art approaches in VTG benchmarks, indicating that holistic text understanding guides the model to focus on the semantically important parts within the video.</description><subject>Correlation</subject><subject>Frames (data processing)</subject><subject>Queries</subject><subject>Sentences</subject><subject>Visual aspects</subject><subject>Visual effects</subject><subject>Words (language)</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNys0KgkAUQOEhCJLyHS60FpwZNWkbmYtcZW1F9JYjNmPzQ_X2SfQArc7ifDPiMc5pkEaMLYhvTB-GIUs2LI65R8ojWigQMiGF6aB4wwmlRdngFi6iRQUl3kel6wEOWjnZCnmDp7Ad5GoQxopmAi8LZ9miNrb-ghWZX-vBoP_rkqyzfbnLg1Grh0Njq145LadVcUpTShOaRvw_9QH_7z_I</recordid><startdate>20241017</startdate><enddate>20241017</enddate><creator>Woo, Jongbhin</creator><creator>Ryu, Hyeonggon</creator><creator>Jang, Youngjoon</creator><creator>Cho, Jae Won</creator><creator>Joon Son Chung</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20241017</creationdate><title>Let Me Finish My Sentence: Video Temporal Grounding with Holistic Text Understanding</title><author>Woo, Jongbhin ; Ryu, Hyeonggon ; Jang, Youngjoon ; Cho, Jae Won ; Joon Son Chung</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31181161843</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Correlation</topic><topic>Frames (data processing)</topic><topic>Queries</topic><topic>Sentences</topic><topic>Visual aspects</topic><topic>Visual effects</topic><topic>Words (language)</topic><toplevel>online_resources</toplevel><creatorcontrib>Woo, Jongbhin</creatorcontrib><creatorcontrib>Ryu, Hyeonggon</creatorcontrib><creatorcontrib>Jang, Youngjoon</creatorcontrib><creatorcontrib>Cho, Jae Won</creatorcontrib><creatorcontrib>Joon Son Chung</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Woo, Jongbhin</au><au>Ryu, Hyeonggon</au><au>Jang, Youngjoon</au><au>Cho, Jae Won</au><au>Joon Son Chung</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Let Me Finish My Sentence: Video Temporal Grounding with Holistic Text Understanding</atitle><jtitle>arXiv.org</jtitle><date>2024-10-17</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Video Temporal Grounding (VTG) aims to identify visual frames in a video clip that match text queries. Recent studies in VTG employ cross-attention to correlate visual frames and text queries as individual token sequences. However, these approaches overlook a crucial aspect of the problem: a holistic understanding of the query sentence. A model may capture correlations between individual word tokens and arbitrary visual frames while possibly missing out on the global meaning. To address this, we introduce two primary contributions: (1) a visual frame-level gate mechanism that incorporates holistic textual information, (2) cross-modal alignment loss to learn the fine-grained correlation between query and relevant frames. As a result, we regularize the effect of individual word tokens and suppress irrelevant visual frames. We demonstrate that our method outperforms state-of-the-art approaches in VTG benchmarks, indicating that holistic text understanding guides the model to focus on the semantically important parts within the video.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_3118116184
source Free E- Journals
subjects Correlation
Frames (data processing)
Queries
Sentences
Visual aspects
Visual effects
Words (language)
title Let Me Finish My Sentence: Video Temporal Grounding with Holistic Text Understanding
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-17T13%3A25%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Let%20Me%20Finish%20My%20Sentence:%20Video%20Temporal%20Grounding%20with%20Holistic%20Text%20Understanding&rft.jtitle=arXiv.org&rft.au=Woo,%20Jongbhin&rft.date=2024-10-17&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3118116184%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3118116184&rft_id=info:pmid/&rfr_iscdi=true