{"id":"https://openalex.org/W3199452768","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533473","title":"Context-Aware Based Visual-Audio Feature Fusion for Emotion Recognition","display_name":"Context-Aware Based Visual-Audio Feature Fusion for Emotion Recognition","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3199452768","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533473","mag":"3199452768"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5011197060","display_name":"Huijie Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huijie Cheng","raw_affiliation_strings":["School of Information Engineering Zhengzhou University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101112071","display_name":"Yun Tie","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Tie","raw_affiliation_strings":["School of Information Engineering Zhengzhou University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326349","display_name":"Lin Qi","orcid":"https://orcid.org/0000-0002-4558-6741"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Qi","raw_affiliation_strings":["School of Information Engineering Zhengzhou University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068772612","display_name":"Cong Jin","orcid":"https://orcid.org/0000-0003-0464-9862"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Jin","raw_affiliation_strings":["Information and communication engineering school Communication university of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Information and communication engineering school Communication university of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011197060"],"corresponding_institution_ids":["https://openalex.org/I38877650"],"apc_list":null,"apc_paid":null,"fwci":0.3843,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.60960784,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998999834060669,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9998999834060669,"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":0.9980000257492065,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9976999759674072,"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":0.8339533805847168},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6814954280853271},{"id":"https://openalex.org/keywords/key-frame","display_name":"Key frame","score":0.49045583605766296},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4745545983314514},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4318167567253113},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4311460554599762},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42916980385780334},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4240868091583252},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4041399359703064},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32815760374069214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8339533805847168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6814954280853271},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.49045583605766296},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4745545983314514},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4318167567253113},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4311460554599762},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42916980385780334},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4240868091583252},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4041399359703064},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32815760374069214},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G1689820939","display_name":null,"funder_award_id":"61631016,61901421","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W1930223417","https://openalex.org/W2048783874","https://openalex.org/W2106229755","https://openalex.org/W2109152179","https://openalex.org/W2156516654","https://openalex.org/W2177696193","https://openalex.org/W2188687388","https://openalex.org/W2321563513","https://openalex.org/W2325078646","https://openalex.org/W2339343773","https://openalex.org/W2414501075","https://openalex.org/W2524923107","https://openalex.org/W2529272619","https://openalex.org/W2552391307","https://openalex.org/W2587372848","https://openalex.org/W2613718673","https://openalex.org/W2617750261","https://openalex.org/W2701359982","https://openalex.org/W2739474071","https://openalex.org/W2740550900","https://openalex.org/W2766630207","https://openalex.org/W2770804203","https://openalex.org/W2787104312","https://openalex.org/W2798970487","https://openalex.org/W2799215407","https://openalex.org/W2805516822","https://openalex.org/W2806331055","https://openalex.org/W2951529591","https://openalex.org/W2952915411","https://openalex.org/W2962779575","https://openalex.org/W2962835968","https://openalex.org/W2963150697","https://openalex.org/W2963452792","https://openalex.org/W2963858333","https://openalex.org/W2963919999","https://openalex.org/W2964015378","https://openalex.org/W2964751875","https://openalex.org/W2983481102","https://openalex.org/W2996799978","https://openalex.org/W3000279895","https://openalex.org/W3001529617","https://openalex.org/W3099153556","https://openalex.org/W4234200325","https://openalex.org/W4285723986","https://openalex.org/W6620707391","https://openalex.org/W6631456553","https://openalex.org/W6637373629","https://openalex.org/W6675954300","https://openalex.org/W6676302953","https://openalex.org/W6686906722","https://openalex.org/W6726873649","https://openalex.org/W6729508183","https://openalex.org/W6745537798","https://openalex.org/W6751796012","https://openalex.org/W6753232330"],"related_works":["https://openalex.org/W2810201907","https://openalex.org/W1614340030","https://openalex.org/W2386640596","https://openalex.org/W2356908413","https://openalex.org/W2912576419","https://openalex.org/W2036745083","https://openalex.org/W2394559091","https://openalex.org/W855007925","https://openalex.org/W2557342721","https://openalex.org/W2349938628"],"abstract_inverted_index":{"Video":[0,192],"emotion":[1,11,42,186],"recognition":[2,15],"is":[3,86,146],"a":[4,36],"significant":[5],"branch":[6],"in":[7,70,117],"the":[8,23,52,79,105,122,128,141,151,157,161,167,173],"field":[9],"of":[10,26,51,63,114,160],"computing.":[12],"However,":[13],"traditional":[14],"works":[16],"mainly":[17],"focus":[18],"on":[19,191],"human":[20],"features,":[21],"ignoring":[22],"contextual":[24],"clues":[25],"video":[27,41,54,71,90,100,118,185],"scenes":[28,72,91],"and":[29,60,73,92,120,175,194],"objects.":[30,74],"In":[31],"our":[32,202],"work,":[33],"we":[34,56,103,171],"propose":[35],"context-aware":[37],"framework":[38],"for":[39,76,184],"bi-modal":[40],"recognition.":[43],"Unlike":[44],"existing":[45],"methods":[46],"that":[47,96,201],"directly":[48],"extract":[49,57,111],"features":[50,113,177],"entire":[53],"frame,":[55],"key":[58,61,94,154],"frames":[59,95,119],"regions":[62,116],"videos":[64],"to":[65,88,99,110,133,138,148],"obtain":[66],"emotional":[67,123],"cues":[68],"contained":[69],"Specifically,":[75],"visual":[77,168,174],"stream,":[78],"hierarchical":[80],"Bidirectional":[81],"Long-Short":[82],"Term":[83],"Memory":[84],"(Bi-LSTM)":[85],"applied":[87],"summarize":[89],"find":[93],"mostly":[97],"contribute":[98],"emotion;":[101],"Meantime,":[102],"introduce":[104],"Region":[106],"Proposal":[107],"Network":[108,131,144],"(RPN)":[109],"corresponding":[112],"object":[115],"construct":[121],"similarity":[124],"graph.":[125],"After":[126],"using":[127],"Feedforward":[129],"Neural":[130],"(FNN)":[132],"assign":[134],"different":[135,139],"weight":[136],"coefficients":[137],"regions,":[140],"Graph":[142],"Convolutional":[143],"(GCN)":[145],"used":[147],"reason":[149],"about":[150],"connections":[152],"between":[153],"regions.":[155],"Moreover,":[156],"context":[158],"information":[159],"frame-level":[162],"Log-Mel":[163],"spectrum":[164],"fragments":[165],"supplement":[166],"information.":[169],"Finally,":[170],"fuse":[172],"acoustics":[176],"by":[178],"adaptive":[179],"gated":[180],"multimodal":[181],"fusion":[182],"module":[183],"classification.":[187],"We":[188],"conduct":[189],"experiments":[190],"Emotion-8":[193],"Ekman-6":[195],"datasets.":[196],"The":[197],"experimental":[198],"results":[199],"demonstrate":[200],"model":[203],"achieves":[204],"better":[205],"classification":[206],"accuracy":[207],"than":[208],"several":[209],"baseline":[210],"models.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}