{"id":"https://openalex.org/W4401452744","doi":"https://doi.org/10.1109/taffc.2024.3440924","title":"AVES: An Audio-Visual Emotion Stream Dataset for Temporal Emotion Detection","display_name":"AVES: An Audio-Visual Emotion Stream Dataset for Temporal Emotion Detection","publication_year":2024,"publication_date":"2024-08-09","ids":{"openalex":"https://openalex.org/W4401452744","doi":"https://doi.org/10.1109/taffc.2024.3440924"},"language":"en","primary_location":{"id":"doi:10.1109/taffc.2024.3440924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2024.3440924","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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 Transactions on Affective Computing","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/A5054345670","display_name":"Yan Li","orcid":"https://orcid.org/0000-0002-5790-708X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Li","raw_affiliation_strings":["Shaanxi Key Laboratory on Speech and Image Information Processing, National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science, Northwestern Polytechnical University (NPU), Xi&#x2019;an, China","Shaanxi Key Laboratory on Speech and Image Information Processing, National Engineering Laboratory for Integrated Aero-SpaceGround-Ocean Big Data Application Technology, School of Computer Science, Northwestern Polytechnical University (NPU), Youyi Xilu 127, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0002-5790-708X","affiliations":[{"raw_affiliation_string":"Shaanxi Key Laboratory on Speech and Image Information Processing, National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science, Northwestern Polytechnical University (NPU), Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Shaanxi Key Laboratory on Speech and Image Information Processing, National Engineering Laboratory for Integrated Aero-SpaceGround-Ocean Big Data Application Technology, School of Computer Science, Northwestern Polytechnical University (NPU), Youyi Xilu 127, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102495226","display_name":"Wei Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Gan","raw_affiliation_strings":["School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072833759","display_name":"Ke L\u00fc","orcid":"https://orcid.org/0000-0003-0176-3088"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Lu","raw_affiliation_strings":["School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0176-3088","affiliations":[{"raw_affiliation_string":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dongmei Jiang","orcid":"https://orcid.org/0000-0002-6238-8499"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Jiang","raw_affiliation_strings":["Pengcheng Laboratory, Shenzhen, China","Peng Cheng Laboratory, Nanshan District, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6238-8499","affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Nanshan District, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010478919","display_name":"Ramesh Jain","orcid":"https://orcid.org/0000-0003-2373-4966"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramesh Jain","raw_affiliation_strings":["Department of Computer Science, University of California, Irvine, Irvine, CA, USA","Department of Computer Science, University of California, Irvine, USA"],"raw_orcid":"https://orcid.org/0000-0003-2373-4966","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Department of Computer Science, University of California, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.0816,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.95919811,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"16","issue":"1","first_page":"438","last_page":"450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9380000233650208,"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/emotion-detection","display_name":"Emotion detection","score":0.6627746820449829},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6393324136734009},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5238307118415833},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.4889132082462311},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.48290348052978516},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4768582284450531},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.474918931722641},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4535275101661682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3657935857772827},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.34548449516296387},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.18386277556419373}],"concepts":[{"id":"https://openalex.org/C2988148770","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion detection","level":3,"score":0.6627746820449829},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6393324136734009},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5238307118415833},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.4889132082462311},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.48290348052978516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4768582284450531},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.474918931722641},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4535275101661682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3657935857772827},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.34548449516296387},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.18386277556419373}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taffc.2024.3440924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2024.3440924","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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 Transactions on Affective Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6177969693","display_name":null,"funder_award_id":"2022ZDLGY06-03","funder_id":"https://openalex.org/F4320336350","funder_display_name":"Key Research and Development Projects of Shaanxi Province"},{"id":"https://openalex.org/G7148651236","display_name":null,"funder_award_id":"62236006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336350","display_name":"Key Research and Development Projects of Shaanxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1677182931","https://openalex.org/W1981918162","https://openalex.org/W1983014650","https://openalex.org/W2007661522","https://openalex.org/W2044106642","https://openalex.org/W2066064791","https://openalex.org/W2072038603","https://openalex.org/W2108598243","https://openalex.org/W2146334809","https://openalex.org/W2150922105","https://openalex.org/W2168692779","https://openalex.org/W2177696193","https://openalex.org/W2188687388","https://openalex.org/W2546649374","https://openalex.org/W2571743746","https://openalex.org/W2587585332","https://openalex.org/W2769949010","https://openalex.org/W2883409523","https://openalex.org/W2963351448","https://openalex.org/W2963686995","https://openalex.org/W2964121718","https://openalex.org/W2964300796","https://openalex.org/W2975349519","https://openalex.org/W2981677410","https://openalex.org/W2981948106","https://openalex.org/W2985882473","https://openalex.org/W3005450949","https://openalex.org/W3093370878","https://openalex.org/W3112640015","https://openalex.org/W3117692248","https://openalex.org/W3134059694","https://openalex.org/W3141819983","https://openalex.org/W3194570764","https://openalex.org/W3209058072","https://openalex.org/W4206326349","https://openalex.org/W4225568094","https://openalex.org/W4230277160","https://openalex.org/W4280528148","https://openalex.org/W4285128513","https://openalex.org/W4292829032","https://openalex.org/W4304013820","https://openalex.org/W4304014238","https://openalex.org/W4304014864","https://openalex.org/W4304091719","https://openalex.org/W4380320096","https://openalex.org/W4385245566","https://openalex.org/W4387272106","https://openalex.org/W4387967961","https://openalex.org/W4387968197","https://openalex.org/W4390871873","https://openalex.org/W4395064954","https://openalex.org/W4399541205","https://openalex.org/W4402754037","https://openalex.org/W6631190155","https://openalex.org/W6719667659","https://openalex.org/W6756778981","https://openalex.org/W6810007534","https://openalex.org/W6810133556","https://openalex.org/W6810265253","https://openalex.org/W6843114795"],"related_works":["https://openalex.org/W4391307871","https://openalex.org/W4392502551","https://openalex.org/W2336827033","https://openalex.org/W2505228240","https://openalex.org/W4319430321","https://openalex.org/W3047499479","https://openalex.org/W4389296211","https://openalex.org/W2922915988","https://openalex.org/W2787157782","https://openalex.org/W1876223856"],"abstract_inverted_index":{"Human":[0],"emotions":[1],"vary":[2],"over":[3],"time,":[4],"which":[5,65,105,158],"can":[6,125,210],"be":[7,199],"vividly":[8],"described":[9],"as":[10,127],"a":[11,47,54,128,149],"stream":[12,18,216],"of":[13,61,72,144,169],"emotions.":[14],"Observing":[15],"the":[16,59,70,110,121,138,167,175,202,212],"emotion":[17,34,44,63,73,114,118,133,145,156,170,177,215,219],"in":[19,33,81,92,120],"daily":[20],"life":[21],"provides":[22],"valuable":[23],"insights":[24],"into":[25],"an":[26,43,98],"individual's":[27],"mental":[28],"state.":[29],"However,":[30],"existing":[31],"research":[32,91,203,213],"understanding":[35],"has":[36,84],"mainly":[37],"focused":[38],"on":[39,182,214],"classification":[40],"tasks,":[41],"assigning":[42],"category":[45,115],"to":[46,164,201],"well-trimmed":[48],"segment":[49,119],"or":[50],"each":[51,117],"frame":[52],"within":[53],"continuous":[55],"signal.":[56],"In":[57],"contrast,":[58],"task":[60],"temporal":[62,132,155,161,218],"detection,":[64,157],"involves":[66],"<italic":[67,76],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[68,77],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">locating</i>":[69],"boundaries":[71,112,140,168],"segments":[74,171],"and":[75,113,141,172,186,217],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">recognizing</i>":[78],"their":[79],"categories":[80],"untrimmed":[82],"signals,":[83],"not":[85],"been":[86],"fully":[87],"explored.":[88],"To":[89],"advance":[90,211],"this":[93,95,208],"area,":[94],"paper":[96,209],"introduces":[97],"in-the-wild":[99],"Audio-Visual":[100],"Emotion":[101],"Stream":[102],"(AVES)":[103],"dataset,":[104],"is":[106],"reliably":[107],"annotated":[108],"with":[109],"time":[111],"for":[116,131,154],"videos.":[122],"Thus,":[123],"AVES":[124,196],"serve":[126],"solid":[129],"benchmark":[130],"detection":[134],"tasks.":[135],"Moreover,":[136],"considering":[137],"flexible":[139],"varying":[142],"durations":[143],"segments,":[146],"we":[147],"propose":[148],"Boundary":[150],"Combination":[151],"Network":[152],"(BoCoNet)":[153],"leverages":[159],"short-term":[160],"context":[162],"information":[163],"first":[165],"predict":[166],"then":[173],"locate":[174],"entire":[176],"segments.":[178],"Extensive":[179],"experiments":[180],"conducted":[181],"various":[183],"representative":[184],"unimodal":[185],"multimodal":[187],"representations":[188],"demonstrate":[189],"that":[190,207],"BoCoNet":[191],"achieves":[192],"state-of-the-art":[193],"results.":[194],"The":[195],"dataset":[197],"will":[198],"released":[200],"community.":[204],"We":[205],"expect":[206],"detection.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}