{"id":"https://openalex.org/W2546875627","doi":"https://doi.org/10.1145/2993148.2997632","title":"Video-based emotion recognition using CNN-RNN and C3D hybrid networks","display_name":"Video-based emotion recognition using CNN-RNN and C3D hybrid networks","publication_year":2016,"publication_date":"2016-10-31","ids":{"openalex":"https://openalex.org/W2546875627","doi":"https://doi.org/10.1145/2993148.2997632","mag":"2546875627"},"language":"en","primary_location":{"id":"doi:10.1145/2993148.2997632","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2993148.2997632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM International Conference on Multimodal Interaction","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/A5053347296","display_name":"Fan Yin","orcid":"https://orcid.org/0000-0002-8028-2217"},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yin Fan","raw_affiliation_strings":["iQiyi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iQiyi, China","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080066452","display_name":"Xiangju Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangju Lu","raw_affiliation_strings":["iQiyi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iQiyi, China","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675450","display_name":"Dian Li","orcid":"https://orcid.org/0000-0002-7183-0090"},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dian Li","raw_affiliation_strings":["iQiyi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iQiyi, China","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073987006","display_name":"Yuanliu Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanliu Liu","raw_affiliation_strings":["iQiyi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iQiyi, China","institution_ids":["https://openalex.org/I4210115040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053347296"],"corresponding_institution_ids":["https://openalex.org/I4210115040"],"apc_list":null,"apc_paid":null,"fwci":27.0366,"has_fulltext":false,"cited_by_count":557,"citation_normalized_percentile":{"value":0.99677202,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"445","last_page":"450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9997000098228455,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9994999766349792,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8503627181053162},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8410112261772156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.692879855632782},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5838170647621155},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5649387240409851},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5583773255348206},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4869304895401001},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4712021052837372},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4601593017578125},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.43986740708351135},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.28192275762557983}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8503627181053162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410112261772156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.692879855632782},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5838170647621155},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5649387240409851},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5583773255348206},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4869304895401001},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4712021052837372},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4601593017578125},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.43986740708351135},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28192275762557983},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2993148.2997632","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2993148.2997632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM International Conference on Multimodal Interaction","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":30,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1553469512","https://openalex.org/W1686810756","https://openalex.org/W1923404803","https://openalex.org/W1947481528","https://openalex.org/W1981918162","https://openalex.org/W1994215930","https://openalex.org/W2008887256","https://openalex.org/W2016053056","https://openalex.org/W2081835714","https://openalex.org/W2085662862","https://openalex.org/W2094637479","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2122585011","https://openalex.org/W2139501017","https://openalex.org/W2143612262","https://openalex.org/W2155893237","https://openalex.org/W2172806452","https://openalex.org/W2194775991","https://openalex.org/W2245421092","https://openalex.org/W2277498883","https://openalex.org/W2293634267","https://openalex.org/W2293804193","https://openalex.org/W2308045930","https://openalex.org/W2325939864","https://openalex.org/W2486769752","https://openalex.org/W2546649374","https://openalex.org/W2616400984","https://openalex.org/W4236965008"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384"],"abstract_inverted_index":{"In":[0],"this":[1,20],"paper,":[2],"we":[3],"present":[4],"a":[5,23,38,90],"video-based":[6,125],"emotion":[7,126],"recognition":[8,91,127],"system":[9,21,88],"submitted":[10],"to":[11,106],"the":[12,109],"EmotiW":[13,112],"2016":[14],"Challenge.":[15],"The":[16],"core":[17],"module":[18],"of":[19,79,93,108,111],"is":[22],"hybrid":[24],"network":[25,30,61],"that":[26,117],"combines":[27],"recurrent":[28],"neural":[29,60],"(RNN)":[31],"and":[32,42,46,69,77,120],"3D":[33],"convolutional":[34,59],"networks":[35],"(C3D)":[36],"in":[37,49,102],"late-fusion":[39],"fashion.":[40],"RNN":[41,53,119],"C3D":[43,74,121],"encode":[44],"appearance":[45,55,76],"motion":[47,71,78],"information":[48],"different":[50],"ways.":[51],"Specifically,":[52],"takes":[54],"features":[56],"extracted":[57],"by":[58],"(CNN)":[62],"over":[63],"individual":[64],"video":[65,80,100],"frames":[66],"as":[67],"input":[68],"encodes":[70],"later,":[72],"while":[73],"models":[75],"simultaneously.":[81],"Combined":[82],"with":[83],"an":[84],"audio":[85],"module,":[86],"our":[87],"achieved":[89],"accuracy":[92],"59.02%":[94],"without":[95],"using":[96],"any":[97],"additional":[98],"emotion-labeled":[99],"clips":[101],"training":[103],"set,":[104],"compared":[105],"53.8%":[107],"winner":[110],"2015.":[113],"Extensive":[114],"experiments":[115],"show":[116],"combining":[118],"together":[122],"can":[123],"improve":[124],"noticeably.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":64},{"year":2023,"cited_by_count":70},{"year":2022,"cited_by_count":52},{"year":2021,"cited_by_count":87},{"year":2020,"cited_by_count":90},{"year":2019,"cited_by_count":78},{"year":2018,"cited_by_count":57},{"year":2017,"cited_by_count":24},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}