Traffic-Domain Video Question Answering with Automatic Captioning

Traffic-Domain Video Question Answering with Automatic Captioning

Video Question Answering (VidQA) exhibits remarkable potential in facilitating advanced machine reasoning capabilities within the domains of Intelligent Traffic Monitoring and Intelligent Transportation Systems. Nevertheless, the integration of urban traffic scene knowledge into VidQA systems has re...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-07
Hauptverfasser: Qasemi, Ehsan, Francis, Jonathan M, Oltramari, Alessandro
Format: Artikel
Sprache:eng
Schlagworte:
Intelligent transportation systems
Questions
Traffic models
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 Qasemi, Ehsan
Francis, Jonathan M
Oltramari, Alessandro
description Video Question Answering (VidQA) exhibits remarkable potential in facilitating advanced machine reasoning capabilities within the domains of Intelligent Traffic Monitoring and Intelligent Transportation Systems. Nevertheless, the integration of urban traffic scene knowledge into VidQA systems has received limited attention in previous research endeavors. In this work, we present a novel approach termed Traffic-domain Video Question Answering with Automatic Captioning (TRIVIA), which serves as a weak-supervision technique for infusing traffic-domain knowledge into large video-language models. Empirical findings obtained from the SUTD-TrafficQA task highlight the substantial enhancements achieved by TRIVIA, elevating the accuracy of representative video-language models by a remarkable 6.5 points (19.88%) compared to baseline settings. This pioneering methodology holds great promise for driving advancements in the field, inspiring researchers and practitioners alike to unlock the full potential of emerging video-language models in traffic-related applications.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2840072245</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2840072245</sourcerecordid><originalsourceid>FETCH-proquest_journals_28400722453</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRwDClKTEvLTNZ1yc9NzMxTCMtMSc1XCCxNLS7JzM9TcMwrLk8tysxLVyjPLMlQcCwtASoryUxWcE4sACkAyvAwsKYl5hSn8kJpbgZlN9cQZw_dgqL8QpA58Vn5pUV5QKl4IwsTAwNzIyMTU2PiVAEAe4U5eg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2840072245</pqid></control><display><type>article</type><title>Traffic-Domain Video Question Answering with Automatic Captioning</title><source>Free E- Journals</source><creator>Qasemi, Ehsan ; Francis, Jonathan M ; Oltramari, Alessandro</creator><creatorcontrib>Qasemi, Ehsan ; Francis, Jonathan M ; Oltramari, Alessandro</creatorcontrib><description>Video Question Answering (VidQA) exhibits remarkable potential in facilitating advanced machine reasoning capabilities within the domains of Intelligent Traffic Monitoring and Intelligent Transportation Systems. Nevertheless, the integration of urban traffic scene knowledge into VidQA systems has received limited attention in previous research endeavors. In this work, we present a novel approach termed Traffic-domain Video Question Answering with Automatic Captioning (TRIVIA), which serves as a weak-supervision technique for infusing traffic-domain knowledge into large video-language models. Empirical findings obtained from the SUTD-TrafficQA task highlight the substantial enhancements achieved by TRIVIA, elevating the accuracy of representative video-language models by a remarkable 6.5 points (19.88%) compared to baseline settings. This pioneering methodology holds great promise for driving advancements in the field, inspiring researchers and practitioners alike to unlock the full potential of emerging video-language models in traffic-related applications.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Intelligent transportation systems ; Questions ; Traffic models</subject><ispartof>arXiv.org, 2023-07</ispartof><rights>2023. 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>780,784</link.rule.ids></links><search><creatorcontrib>Qasemi, Ehsan</creatorcontrib><creatorcontrib>Francis, Jonathan M</creatorcontrib><creatorcontrib>Oltramari, Alessandro</creatorcontrib><title>Traffic-Domain Video Question Answering with Automatic Captioning</title><title>arXiv.org</title><description>Video Question Answering (VidQA) exhibits remarkable potential in facilitating advanced machine reasoning capabilities within the domains of Intelligent Traffic Monitoring and Intelligent Transportation Systems. Nevertheless, the integration of urban traffic scene knowledge into VidQA systems has received limited attention in previous research endeavors. In this work, we present a novel approach termed Traffic-domain Video Question Answering with Automatic Captioning (TRIVIA), which serves as a weak-supervision technique for infusing traffic-domain knowledge into large video-language models. Empirical findings obtained from the SUTD-TrafficQA task highlight the substantial enhancements achieved by TRIVIA, elevating the accuracy of representative video-language models by a remarkable 6.5 points (19.88%) compared to baseline settings. This pioneering methodology holds great promise for driving advancements in the field, inspiring researchers and practitioners alike to unlock the full potential of emerging video-language models in traffic-related applications.</description><subject>Intelligent transportation systems</subject><subject>Questions</subject><subject>Traffic models</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRwDClKTEvLTNZ1yc9NzMxTCMtMSc1XCCxNLS7JzM9TcMwrLk8tysxLVyjPLMlQcCwtASoryUxWcE4sACkAyvAwsKYl5hSn8kJpbgZlN9cQZw_dgqL8QpA58Vn5pUV5QKl4IwsTAwNzIyMTU2PiVAEAe4U5eg</recordid><startdate>20230718</startdate><enddate>20230718</enddate><creator>Qasemi, Ehsan</creator><creator>Francis, Jonathan M</creator><creator>Oltramari, Alessandro</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>20230718</creationdate><title>Traffic-Domain Video Question Answering with Automatic Captioning</title><author>Qasemi, Ehsan ; Francis, Jonathan M ; Oltramari, Alessandro</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28400722453</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Intelligent transportation systems</topic><topic>Questions</topic><topic>Traffic models</topic><toplevel>online_resources</toplevel><creatorcontrib>Qasemi, Ehsan</creatorcontrib><creatorcontrib>Francis, Jonathan M</creatorcontrib><creatorcontrib>Oltramari, Alessandro</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>Publicly Available Content Database</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>Qasemi, Ehsan</au><au>Francis, Jonathan M</au><au>Oltramari, Alessandro</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Traffic-Domain Video Question Answering with Automatic Captioning</atitle><jtitle>arXiv.org</jtitle><date>2023-07-18</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Video Question Answering (VidQA) exhibits remarkable potential in facilitating advanced machine reasoning capabilities within the domains of Intelligent Traffic Monitoring and Intelligent Transportation Systems. Nevertheless, the integration of urban traffic scene knowledge into VidQA systems has received limited attention in previous research endeavors. In this work, we present a novel approach termed Traffic-domain Video Question Answering with Automatic Captioning (TRIVIA), which serves as a weak-supervision technique for infusing traffic-domain knowledge into large video-language models. Empirical findings obtained from the SUTD-TrafficQA task highlight the substantial enhancements achieved by TRIVIA, elevating the accuracy of representative video-language models by a remarkable 6.5 points (19.88%) compared to baseline settings. This pioneering methodology holds great promise for driving advancements in the field, inspiring researchers and practitioners alike to unlock the full potential of emerging video-language models in traffic-related applications.</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, 2023-07
issn 2331-8422
language eng
recordid cdi_proquest_journals_2840072245
source Free E- Journals
subjects Intelligent transportation systems
Questions
Traffic models
title Traffic-Domain Video Question Answering with Automatic Captioning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T07%3A47%3A17IST&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=Traffic-Domain%20Video%20Question%20Answering%20with%20Automatic%20Captioning&rft.jtitle=arXiv.org&rft.au=Qasemi,%20Ehsan&rft.date=2023-07-18&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2840072245%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2840072245&rft_id=info:pmid/&rfr_iscdi=true