{"id":"https://openalex.org/W4394593115","doi":"https://doi.org/10.1109/wacv57701.2024.00552","title":"Rethink Cross-Modal Fusion in Weakly-Supervised Audio-Visual Video Parsing","display_name":"Rethink Cross-Modal Fusion in Weakly-Supervised Audio-Visual Video Parsing","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4394593115","doi":"https://doi.org/10.1109/wacv57701.2024.00552"},"language":"en","primary_location":{"id":"doi:10.1109/wacv57701.2024.00552","doi":"https://doi.org/10.1109/wacv57701.2024.00552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv57701.2024.00552","pdf_url":null,"source":{"id":"https://openalex.org/S4393918690","display_name":"IEEE Winter Conference on Applications of Computer Vision","issn_l":"2472-6737","issn":["2472-6737"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2311.08151","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113110224","display_name":"Yating Xu","orcid":"https://orcid.org/0009-0004-2809-6355","observed_orcids":["https://orcid.org/0009-0004-2809-6355"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yating Xu","raw_affiliation_strings":["National University of Singapore,Department of Computer Science","Department of Computer Science, National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Computer Science","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Computer Science, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088444991","display_name":"Conghui Hu","orcid":"https://orcid.org/0000-0002-4984-3960","observed_orcids":["https://orcid.org/0000-0002-4984-3960"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Conghui Hu","raw_affiliation_strings":["National University of Singapore,Department of Computer Science","Department of Computer Science, National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Computer Science","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Computer Science, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071967339","display_name":"Gim Hee Lee","orcid":"https://orcid.org/0000-0002-1583-0475","observed_orcids":["https://orcid.org/0000-0002-1583-0475"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Gim Hee Lee","raw_affiliation_strings":["National University of Singapore,Department of Computer Science","Department of Computer Science, National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Computer Science","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Computer Science, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.0136,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83618491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5603","last_page":"5612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9110999703407288,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9110999703407288,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.03500000014901161,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.023600000888109207,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cross-modal-fusion","display_name":"cross-modal fusion","score":0.9800000190734863},{"id":"https://openalex.org/keywords/mid-level-fusion","display_name":"mid-level fusion","score":0.6589999794960022},{"id":"https://openalex.org/keywords/audio-visual-alignment","display_name":"audio-visual alignment","score":0.6039999723434448},{"id":"https://openalex.org/keywords/hybrid-attention-network","display_name":"hybrid attention network","score":0.6890000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7601871490478516},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7583011388778687},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6657669544219971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5984588861465454},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5749840140342712},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46914592385292053},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4357073903083801},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4297049045562744},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3205663859844208},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.17145249247550964},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0626344382762909},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv57701.2024.00552","doi":"https://doi.org/10.1109/wacv57701.2024.00552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv57701.2024.00552","pdf_url":null,"source":{"id":"https://openalex.org/S4393918690","display_name":"IEEE Winter Conference on Applications of Computer Vision","issn_l":"2472-6737","issn":["2472-6737"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2311.08151","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.08151","pdf_url":"https://arxiv.org/pdf/2311.08151","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2311.08151","doi":"https://doi.org/10.48550/arxiv.2311.08151","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.08151","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.08151","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.08151","pdf_url":"https://arxiv.org/pdf/2311.08151","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7533772255","display_name":null,"funder_award_id":"AISG2-RP-2021-024","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394593115.pdf","grobid_xml":"https://content.openalex.org/works/W4394593115.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W2026012689","https://openalex.org/W2129068307","https://openalex.org/W2194775991","https://openalex.org/W2526050071","https://openalex.org/W2544224704","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2626778328","https://openalex.org/W2796992393","https://openalex.org/W2890052321","https://openalex.org/W2931433835","https://openalex.org/W2935917634","https://openalex.org/W2943865428","https://openalex.org/W2963115079","https://openalex.org/W2963155035","https://openalex.org/W2963504927","https://openalex.org/W2964109005","https://openalex.org/W2970608575","https://openalex.org/W2981851635","https://openalex.org/W3017343282","https://openalex.org/W3020933450","https://openalex.org/W3034658206","https://openalex.org/W3034742263","https://openalex.org/W3043840704","https://openalex.org/W3048065599","https://openalex.org/W3089682612","https://openalex.org/W3094502228","https://openalex.org/W3095687795","https://openalex.org/W3099570996","https://openalex.org/W3108655859","https://openalex.org/W3112385539","https://openalex.org/W3118120400","https://openalex.org/W3134144764","https://openalex.org/W3145224227","https://openalex.org/W3147387781","https://openalex.org/W3175335326","https://openalex.org/W3206570195","https://openalex.org/W3212014628","https://openalex.org/W3214328324","https://openalex.org/W4312372834","https://openalex.org/W4312864739","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W4416255765","https://openalex.org/W3175335326","https://openalex.org/W4387969709","https://openalex.org/W4225473241","https://openalex.org/W3155372489","https://openalex.org/W3118120400","https://openalex.org/W4404135833","https://openalex.org/W4394863057","https://openalex.org/W4372260201","https://openalex.org/W4403947222"],"abstract_inverted_index":{"Existing":[0],"works":[1],"on":[2,154],"weakly-supervised":[3],"audio-visual":[4],"video":[5],"parsing":[6],"adopt":[7],"hybrid":[8],"attention":[9],"network":[10],"(HAN)":[11],"as":[12],"the":[13,18,23,33,38,48,69,75,80,85,102,148,161],"multi-modal":[14],"embedding":[15],"to":[16,55,73,93,101,146,168],"capture":[17,106],"cross-modal":[19,77,87,97,132],"context.":[20],"It":[21],"embeds":[22],"audio":[24,107,135,152],"and":[25,53],"visual":[26,116,137,155],"modalities":[27,52],"with":[28,64],"a":[29,90,119,126],"shared":[30],"network,":[31],"where":[32],"cross-attention":[34],"is":[35,125],"performed":[36],"at":[37],"input.":[39],"However,":[40],"such":[41],"an":[42],"early":[43],"fusion":[44],"method":[45],"highly":[46],"entangles":[47],"two":[49],"non-fully":[50],"correlated":[51],"leads":[54],"sub-optimal":[56],"performance":[57,163],"in":[58,79],"detecting":[59],"single-modality":[60],"events.":[61],"To":[62],"deal":[63],"this":[65],"problem,":[66],"we":[67],"propose":[68,142],"messenger-guided":[70],"mid-fusion":[71],"transformer":[72],"reduce":[74],"uncorrelated":[76],"context":[78,88,133],"fusion.":[81],"The":[82],"messengers":[83],"condense":[84],"full":[86],"into":[89],"compact":[91],"representation":[92],"only":[94,114],"preserve":[95],"useful":[96],"information.":[98],"Furthermore,":[99],"due":[100],"fact":[103],"that":[104],"microphones":[105],"events":[108,117],"from":[109,134],"all":[110],"directions,":[111],"while":[112],"cameras":[113],"record":[115],"within":[118],"restricted":[120],"field":[121],"of":[122,130,150,164],"view,":[123],"there":[124],"more":[127],"frequent":[128],"occurrence":[129],"unaligned":[131],"for":[136],"event":[138,156],"predictions.":[139],"We":[140],"thus":[141],"cross-audio":[143],"prediction":[144],"consistency":[145],"suppress":[147],"impact":[149],"irrelevant":[151],"information":[153],"prediction.":[157],"Experiments":[158],"consistently":[159],"illustrate":[160],"superior":[162],"our":[165],"framework":[166],"compared":[167],"existing":[169],"state-of-the-art":[170],"methods.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2024-04-10T00:00:00"}