Multi-Resolution Audio-Visual Feature Fusion for Temporal Action Localization
Temporal Action Localization (TAL) aims to identify actions' start, end, and class labels in untrimmed videos. While recent advancements using transformer networks and Feature Pyramid Networks (FPN) have enhanced visual feature recognition in TAL tasks, less progress has been made in the integr...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2023-10 |
---|---|
Hauptverfasser: | , , |
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 | Fish, Edward Weinbren, Jon Gilbert, Andrew |
description | Temporal Action Localization (TAL) aims to identify actions' start, end, and class labels in untrimmed videos. While recent advancements using transformer networks and Feature Pyramid Networks (FPN) have enhanced visual feature recognition in TAL tasks, less progress has been made in the integration of audio features into such frameworks. This paper introduces the Multi-Resolution Audio-Visual Feature Fusion (MRAV-FF), an innovative method to merge audio-visual data across different temporal resolutions. Central to our approach is a hierarchical gated cross-attention mechanism, which discerningly weighs the importance of audio information at diverse temporal scales. Such a technique not only refines the precision of regression boundaries but also bolsters classification confidence. Importantly, MRAV-FF is versatile, making it compatible with existing FPN TAL architectures and offering a significant enhancement in performance when audio data is available. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2873634230</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2873634230</sourcerecordid><originalsourceid>FETCH-proquest_journals_28736342303</originalsourceid><addsrcrecordid>eNqNyr0KwjAYheEgCBbtPQScAzHp31rE4mAXKa4ltCmkxH41ybd49bbiBTgdDs-7IZGQ8sSKRIgdib0fOeciy0WayojUNdpg2F17sBgMTLTE3gB7GI_K0kqrgE7TCv1qAzja6OcMbrGy-_Y36JQ1b7WeA9kOynod_3ZPjtWlOV_Z7OCF2od2BHTTQq0ocpnJREgu_6s-rlI-Dw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2873634230</pqid></control><display><type>article</type><title>Multi-Resolution Audio-Visual Feature Fusion for Temporal Action Localization</title><source>Free E- Journals</source><creator>Fish, Edward ; Weinbren, Jon ; Gilbert, Andrew</creator><creatorcontrib>Fish, Edward ; Weinbren, Jon ; Gilbert, Andrew</creatorcontrib><description>Temporal Action Localization (TAL) aims to identify actions' start, end, and class labels in untrimmed videos. While recent advancements using transformer networks and Feature Pyramid Networks (FPN) have enhanced visual feature recognition in TAL tasks, less progress has been made in the integration of audio features into such frameworks. This paper introduces the Multi-Resolution Audio-Visual Feature Fusion (MRAV-FF), an innovative method to merge audio-visual data across different temporal resolutions. Central to our approach is a hierarchical gated cross-attention mechanism, which discerningly weighs the importance of audio information at diverse temporal scales. Such a technique not only refines the precision of regression boundaries but also bolsters classification confidence. Importantly, MRAV-FF is versatile, making it compatible with existing FPN TAL architectures and offering a significant enhancement in performance when audio data is available.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Audio data ; Feature recognition ; Localization</subject><ispartof>arXiv.org, 2023-10</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>776,780</link.rule.ids></links><search><creatorcontrib>Fish, Edward</creatorcontrib><creatorcontrib>Weinbren, Jon</creatorcontrib><creatorcontrib>Gilbert, Andrew</creatorcontrib><title>Multi-Resolution Audio-Visual Feature Fusion for Temporal Action Localization</title><title>arXiv.org</title><description>Temporal Action Localization (TAL) aims to identify actions' start, end, and class labels in untrimmed videos. While recent advancements using transformer networks and Feature Pyramid Networks (FPN) have enhanced visual feature recognition in TAL tasks, less progress has been made in the integration of audio features into such frameworks. This paper introduces the Multi-Resolution Audio-Visual Feature Fusion (MRAV-FF), an innovative method to merge audio-visual data across different temporal resolutions. Central to our approach is a hierarchical gated cross-attention mechanism, which discerningly weighs the importance of audio information at diverse temporal scales. Such a technique not only refines the precision of regression boundaries but also bolsters classification confidence. Importantly, MRAV-FF is versatile, making it compatible with existing FPN TAL architectures and offering a significant enhancement in performance when audio data is available.</description><subject>Audio data</subject><subject>Feature recognition</subject><subject>Localization</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNyr0KwjAYheEgCBbtPQScAzHp31rE4mAXKa4ltCmkxH41ybd49bbiBTgdDs-7IZGQ8sSKRIgdib0fOeciy0WayojUNdpg2F17sBgMTLTE3gB7GI_K0kqrgE7TCv1qAzja6OcMbrGy-_Y36JQ1b7WeA9kOynod_3ZPjtWlOV_Z7OCF2od2BHTTQq0ocpnJREgu_6s-rlI-Dw</recordid><startdate>20231005</startdate><enddate>20231005</enddate><creator>Fish, Edward</creator><creator>Weinbren, Jon</creator><creator>Gilbert, Andrew</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>20231005</creationdate><title>Multi-Resolution Audio-Visual Feature Fusion for Temporal Action Localization</title><author>Fish, Edward ; Weinbren, Jon ; Gilbert, Andrew</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28736342303</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Audio data</topic><topic>Feature recognition</topic><topic>Localization</topic><toplevel>online_resources</toplevel><creatorcontrib>Fish, Edward</creatorcontrib><creatorcontrib>Weinbren, Jon</creatorcontrib><creatorcontrib>Gilbert, Andrew</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & 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>Fish, Edward</au><au>Weinbren, Jon</au><au>Gilbert, Andrew</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Multi-Resolution Audio-Visual Feature Fusion for Temporal Action Localization</atitle><jtitle>arXiv.org</jtitle><date>2023-10-05</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Temporal Action Localization (TAL) aims to identify actions' start, end, and class labels in untrimmed videos. While recent advancements using transformer networks and Feature Pyramid Networks (FPN) have enhanced visual feature recognition in TAL tasks, less progress has been made in the integration of audio features into such frameworks. This paper introduces the Multi-Resolution Audio-Visual Feature Fusion (MRAV-FF), an innovative method to merge audio-visual data across different temporal resolutions. Central to our approach is a hierarchical gated cross-attention mechanism, which discerningly weighs the importance of audio information at diverse temporal scales. Such a technique not only refines the precision of regression boundaries but also bolsters classification confidence. Importantly, MRAV-FF is versatile, making it compatible with existing FPN TAL architectures and offering a significant enhancement in performance when audio data is available.</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, 2023-10 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2873634230 |
source | Free E- Journals |
subjects | Audio data Feature recognition Localization |
title | Multi-Resolution Audio-Visual Feature Fusion for Temporal Action Localization |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T09%3A36%3A27IST&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=Multi-Resolution%20Audio-Visual%20Feature%20Fusion%20for%20Temporal%20Action%20Localization&rft.jtitle=arXiv.org&rft.au=Fish,%20Edward&rft.date=2023-10-05&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2873634230%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2873634230&rft_id=info:pmid/&rfr_iscdi=true |