{"id":"https://openalex.org/W4405800334","doi":"https://doi.org/10.1109/lsp.2024.3522855","title":"Enhancing No-Reference Audio-Visual Quality Assessment via Joint Cross-Attention Fusion","display_name":"Enhancing No-Reference Audio-Visual Quality Assessment via Joint Cross-Attention Fusion","publication_year":2024,"publication_date":"2024-12-25","ids":{"openalex":"https://openalex.org/W4405800334","doi":"https://doi.org/10.1109/lsp.2024.3522855"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3522855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3522855","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011577651","display_name":"Zhaolin Wan","orcid":"https://orcid.org/0000-0003-0324-7116"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaolin Wan","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0003-0324-7116","affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017105489","display_name":"Xiguang Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiguang Hao","raw_affiliation_strings":["Department of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079412089","display_name":"Xiaopeng Fan","orcid":"https://orcid.org/0000-0002-9660-3636"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Fan","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-9660-3636","affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636655","display_name":"Wangmeng Zuo","orcid":"https://orcid.org/0000-0002-3330-783X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangmeng Zuo","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-3330-783X","affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100600353","display_name":"Debin Zhao","orcid":"https://orcid.org/0000-0003-3434-9967"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Debin Zhao","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0003-3434-9967","affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4323,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59915915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"556","last_page":"560"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9667999744415283,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9667999744415283,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9595999717712402,"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"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9150000214576721,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7269089818000793},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7225170731544495},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5314826965332031},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5103718638420105},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.480898380279541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4689972400665283},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.45625030994415283},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.45164793729782104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44462695717811584},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3147912323474884},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11198121309280396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269089818000793},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7225170731544495},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5314826965332031},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5103718638420105},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.480898380279541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4689972400665283},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.45625030994415283},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.45164793729782104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44462695717811584},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3147912323474884},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11198121309280396},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3522855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3522855","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G389757105","display_name":null,"funder_award_id":"62102059","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8517217640","display_name":null,"funder_award_id":"LH2024F018","funder_id":"https://openalex.org/F4320323085","funder_display_name":"Natural Science Foundation of Heilongjiang Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323085","display_name":"Natural Science Foundation of Heilongjiang Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1580389772","https://openalex.org/W1964859077","https://openalex.org/W2046119925","https://openalex.org/W2084397735","https://openalex.org/W2108598243","https://openalex.org/W2133665775","https://openalex.org/W2194775991","https://openalex.org/W2752782242","https://openalex.org/W2755560870","https://openalex.org/W2785586734","https://openalex.org/W2950635152","https://openalex.org/W3019533076","https://openalex.org/W3037192005","https://openalex.org/W3168989576","https://openalex.org/W3206086363","https://openalex.org/W4200316848","https://openalex.org/W4296425701","https://openalex.org/W4301184818","https://openalex.org/W4312929873","https://openalex.org/W4327662052","https://openalex.org/W4366493191","https://openalex.org/W4379743395","https://openalex.org/W4383750585","https://openalex.org/W4385245566","https://openalex.org/W4390204075","https://openalex.org/W4391488862","https://openalex.org/W4403601500","https://openalex.org/W6729831399","https://openalex.org/W6784333009","https://openalex.org/W6847343555"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2152662039"],"abstract_inverted_index":{"As":[0],"the":[1,25,37,74,125,148],"consumption":[2],"of":[3,77,97,127],"multimedia":[4],"content":[5],"continues":[6],"to":[7,15,35,72,82,135],"rise,":[8],"audio":[9,40,117],"and":[10,18,29,41,116,150],"video":[11],"have":[12],"become":[13],"central":[14],"everyday":[16],"entertainment":[17],"social":[19],"interactions.":[20],"This":[21],"growing":[22],"reliance":[23],"amplifies":[24],"demand":[26],"for":[27,64,141],"effective":[28],"objective":[30],"audio-visual":[31,65,98,164],"quality":[32,142,165],"assessment":[33],"(AVQA)":[34],"understand":[36],"interaction":[38],"between":[39],"visual":[42,114],"elements,":[43],"ultimately":[44],"enhancing":[45],"user":[46],"satisfaction.":[47],"However,":[48],"existing":[49],"state-of-the-art":[50,158],"AVQA":[51,90],"methods":[52],"often":[53],"rely":[54],"on":[55,147],"simplistic":[56],"machine":[57],"learning":[58],"models":[59],"or":[60],"fully":[61],"connected":[62],"networks":[63],"signal":[66],"fusion,":[67],"which":[68],"limits":[69],"their":[70],"ability":[71],"exploit":[73],"complementary":[75],"nature":[76],"these":[78],"modalities.":[79],"In":[80],"response":[81],"this":[83],"gap,":[84],"we":[85],"propose":[86],"a":[87,104,137],"novel":[88],"no-reference":[89],"method":[91],"that":[92,109,154],"utilizes":[93],"joint":[94],"cross-attention":[95],"fusion":[96,120],"perception.":[99],"Our":[100],"approach":[101],"begins":[102],"with":[103],"dual-stream":[105],"feature":[106],"extraction":[107],"process":[108],"simultaneously":[110],"captures":[111],"long-range":[112],"spatiotemporal":[113],"features":[115,128],"features.":[118],"The":[119],"model":[121,156],"then":[122],"dynamically":[123],"adjusts":[124],"contributions":[126],"from":[129],"both":[130],"modalities,":[131],"effectively":[132],"integrating":[133],"them":[134],"provide":[136],"more":[138],"comprehensive":[139],"perception":[140],"score":[143],"prediction.":[144],"Experimental":[145],"results":[146],"LIVE-SJTU":[149],"UnB-AVC":[151],"datasets":[152],"demonstrate":[153],"our":[155],"outperforms":[157],"methods,":[159],"achieving":[160],"superior":[161],"performance":[162],"in":[163],"assessment.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}
