{"id":"https://openalex.org/W4372269197","doi":"https://doi.org/10.1109/icassp49357.2023.10095728","title":"Contextually-Rich Human Affect Perception Using Multimodal Scene Information","display_name":"Contextually-Rich Human Affect Perception Using Multimodal Scene Information","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372269197","doi":"https://doi.org/10.1109/icassp49357.2023.10095728"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5059652479","display_name":"Digbalay Bose","orcid":"https://orcid.org/0000-0002-5281-1695"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Digbalay Bose","raw_affiliation_strings":["University of Southern,Signal Analysis and Interpretation Laboratory,California,CA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern,Signal Analysis and Interpretation Laboratory,California,CA,90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085315115","display_name":"Rajat Hebbar","orcid":"https://orcid.org/0000-0002-0904-0573"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajat Hebbar","raw_affiliation_strings":["University of Southern,Signal Analysis and Interpretation Laboratory,California,CA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern,Signal Analysis and Interpretation Laboratory,California,CA,90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008305849","display_name":"Krishna Somandepalli","orcid":"https://orcid.org/0000-0002-2845-1079"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna Somandepalli","raw_affiliation_strings":["University of Southern,Signal Analysis and Interpretation Laboratory,California,CA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern,Signal Analysis and Interpretation Laboratory,California,CA,90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104114055","display_name":"Shrikanth Narayanan","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern,Signal Analysis and Interpretation Laboratory,California,CA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern,Signal Analysis and Interpretation Laboratory,California,CA,90089","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":2.1129,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88839725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9987000226974487,"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":0.9987000226974487,"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/T11448","display_name":"Face recognition and analysis","score":0.9926000237464905,"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":0.9922000169754028,"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":0.7037566900253296},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6404169201850891},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6273989081382751},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.6264728307723999},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.622124195098877},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48657381534576416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47566503286361694},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3277819752693176},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21783125400543213},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.14203864336013794}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7037566900253296},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6404169201850891},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6273989081382751},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.6264728307723999},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.622124195098877},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48657381534576416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47566503286361694},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3277819752693176},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21783125400543213},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.14203864336013794},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2103153725","https://openalex.org/W2134927309","https://openalex.org/W2143350951","https://openalex.org/W2145048054","https://openalex.org/W2160827508","https://openalex.org/W2194775991","https://openalex.org/W2341528187","https://openalex.org/W2418269718","https://openalex.org/W2481681431","https://openalex.org/W2732026016","https://openalex.org/W2745497104","https://openalex.org/W2771498260","https://openalex.org/W2946410230","https://openalex.org/W2964751875","https://openalex.org/W2966683369","https://openalex.org/W2979826702","https://openalex.org/W2996233743","https://openalex.org/W3001529617","https://openalex.org/W3034520808","https://openalex.org/W3093370878","https://openalex.org/W3094502228","https://openalex.org/W3101998545","https://openalex.org/W3122081138","https://openalex.org/W3160357885","https://openalex.org/W3162758083","https://openalex.org/W3174134652","https://openalex.org/W3199964822","https://openalex.org/W4281633595","https://openalex.org/W4285250231","https://openalex.org/W4295312788","https://openalex.org/W6631190155","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6766978945","https://openalex.org/W6784333009","https://openalex.org/W6789909235","https://openalex.org/W6798805250","https://openalex.org/W6839015040"],"related_works":["https://openalex.org/W2329500892","https://openalex.org/W28991112","https://openalex.org/W2370726991","https://openalex.org/W2560936962","https://openalex.org/W2788727012","https://openalex.org/W4388203630","https://openalex.org/W2369710579","https://openalex.org/W2526386912","https://openalex.org/W4327728159","https://openalex.org/W4394266730"],"abstract_inverted_index":{"The":[0],"process":[1],"of":[2,68,101],"human":[3],"affect":[4],"understanding":[5],"involves":[6],"the":[7,87,99],"ability":[8],"to":[9,65,82],"infer":[10],"person":[11],"specific":[12],"emotional":[13],"states":[14],"from":[15,25,33,71],"various":[16],"sources":[17],"including":[18,47],"images,":[19],"speech,":[20],"and":[21,52,90,113],"language.":[22],"Affect":[23],"perception":[24],"images":[26],"has":[27],"predominantly":[28],"focused":[29],"on":[30,43,106],"expressions":[31],"extracted":[32],"salient":[34],"face":[35],"crops.":[36],"However,":[37],"emotions":[38],"perceived":[39],"by":[40],"humans":[41],"rely":[42],"multiple":[44],"contextual":[45,92],"cues":[46,85],"social":[48],"settings,":[49],"foreground":[50,69,84],"interactions,":[51],"ambient":[53],"visual":[54,88],"scenes.":[55],"In":[56],"this":[57],"work,":[58],"we":[59,74],"leverage":[60],"pretrained":[61],"vision-language":[62],"(VLN)":[63],"models":[64],"extract":[66],"descriptions":[67],"context":[70,78],"images.":[72],"Further,":[73],"propose":[75],"a":[76],"multimodal":[77],"fusion":[79],"(MCF)":[80],"module":[81],"combine":[83],"with":[86,110],"scene":[89],"person-based":[91],"information":[93],"for":[94],"emotion":[95],"prediction.":[96],"We":[97],"show":[98],"effectiveness":[100],"our":[102],"proposed":[103],"modular":[104],"design":[105],"two":[107],"datasets":[108],"associated":[109],"natural":[111],"scenes":[112],"TV":[114],"shows.":[115]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}