{"id":"https://openalex.org/W2548899748","doi":"https://doi.org/10.1145/2993148.2997639","title":"HoloNet: towards robust emotion recognition in the wild","display_name":"HoloNet: towards robust emotion recognition in the wild","publication_year":2016,"publication_date":"2016-10-31","ids":{"openalex":"https://openalex.org/W2548899748","doi":"https://doi.org/10.1145/2993148.2997639","mag":"2548899748"},"language":"en","primary_location":{"id":"doi:10.1145/2993148.2997639","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2993148.2997639","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/A5025017745","display_name":"Anbang Yao","orcid":"https://orcid.org/0000-0002-3878-8679"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Anbang Yao","raw_affiliation_strings":["Intel Labs, China"],"affiliations":[{"raw_affiliation_string":"Intel Labs, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070424477","display_name":"Dongqi Cai","orcid":"https://orcid.org/0000-0003-2751-2500"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongqi Cai","raw_affiliation_strings":["Intel Labs, China"],"affiliations":[{"raw_affiliation_string":"Intel Labs, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424734","display_name":"Ping Hu","orcid":"https://orcid.org/0000-0003-1122-4395"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Hu","raw_affiliation_strings":["Intel Labs, China"],"affiliations":[{"raw_affiliation_string":"Intel Labs, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087453468","display_name":"Shandong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shandong Wang","raw_affiliation_strings":["Intel Labs, China"],"affiliations":[{"raw_affiliation_string":"Intel Labs, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075455465","display_name":"Sha Liang","orcid":"https://orcid.org/0000-0003-4949-7620"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Sha","raw_affiliation_strings":["Beihang University, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100652865","display_name":"Yurong Chen","orcid":"https://orcid.org/0000-0001-9333-1746"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yurong Chen","raw_affiliation_strings":["Intel Labs, China"],"affiliations":[{"raw_affiliation_string":"Intel Labs, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5025017745"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.0044,"has_fulltext":false,"cited_by_count":111,"citation_normalized_percentile":{"value":0.98974433,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"472","last_page":"478"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9987000226974487,"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":0.7658586502075195},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7126860022544861},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.7008040547370911},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5919881463050842},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5905216336250305},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5406389832496643},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4833907186985016},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46309590339660645},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45409318804740906},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.446646511554718},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4142299294471741},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28217822313308716},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2520415782928467}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7658586502075195},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7126860022544861},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7008040547370911},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5919881463050842},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5905216336250305},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5406389832496643},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4833907186985016},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46309590339660645},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45409318804740906},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.446646511554718},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4142299294471741},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28217822313308716},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2520415782928467},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2993148.2997639","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2993148.2997639","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":32,"referenced_works":["https://openalex.org/W1595717062","https://openalex.org/W1916406603","https://openalex.org/W1950412479","https://openalex.org/W1964920275","https://openalex.org/W1992227055","https://openalex.org/W2008887256","https://openalex.org/W2068611653","https://openalex.org/W2081835714","https://openalex.org/W2085662862","https://openalex.org/W2097117768","https://openalex.org/W2105101328","https://openalex.org/W2114588272","https://openalex.org/W2142704643","https://openalex.org/W2145287260","https://openalex.org/W2145310492","https://openalex.org/W2153597356","https://openalex.org/W2153720647","https://openalex.org/W2156503193","https://openalex.org/W2157285372","https://openalex.org/W2161969291","https://openalex.org/W2163352848","https://openalex.org/W2164598857","https://openalex.org/W2194775991","https://openalex.org/W2243226955","https://openalex.org/W2274287116","https://openalex.org/W2293804193","https://openalex.org/W2300805302","https://openalex.org/W2546649374","https://openalex.org/W2618530766","https://openalex.org/W2914584698","https://openalex.org/W2962835968","https://openalex.org/W4234552385"],"related_works":["https://openalex.org/W2610482638","https://openalex.org/W2811390910","https://openalex.org/W2146076056","https://openalex.org/W4312376745","https://openalex.org/W2767090503","https://openalex.org/W2913302899","https://openalex.org/W2767651786","https://openalex.org/W2319888919","https://openalex.org/W2144059113","https://openalex.org/W2546942002"],"abstract_inverted_index":{"In":[0,31],"this":[1,196],"paper,":[2],"we":[3,76,102,216],"present":[4],"HoloNet,":[5],"a":[6,78,130,218,254,264],"well-designed":[7],"Convolutional":[8],"Neural":[9],"Network":[10],"(CNN)":[11],"architecture":[12],"regarding":[13],"our":[14,52,250],"submissions":[15],"to":[16,33,47,108,241,271],"the":[17,22,26,68,72,91,110,124,143,156,225,242],"video":[18,198],"based":[19,199],"sub-challenge":[20,202],"of":[21,86,132,138,206,222,232,244,256,259],"Emotion":[23],"Recognition":[24],"in":[25,58,71,155,163,195],"Wild":[27],"(EmotiW)":[28],"2016":[29],"challenge.":[30],"contrast":[32],"previous":[34],"related":[35],"methods":[36],"that":[37,146],"usually":[38],"adopt":[39],"relatively":[40],"simple":[41],"and":[42,66,99,106,118,149,182,234],"shallow":[43],"neural":[44],"network":[45,59,97,116],"architectures":[46],"address":[48],"emotion":[49,172,200],"recognition":[50,201,220],"task,":[51],"HoloNet":[53,144,208],"has":[54],"three":[55],"critical":[56],"considerations":[57],"design.":[60],"(1)":[61],"To":[62,89,114],"reduce":[63],"redundant":[64],"filters":[65],"enhance":[67],"non-saturated":[69],"non-linearity":[70],"lower":[73],"convolutional":[74],"layers,":[75,181],"use":[77],"modified":[79],"Concatenated":[80],"Rectified":[81],"Linear":[82],"Unit":[83],"(CReLU)":[84],"instead":[85],"ReLU.":[87],"(2)":[88],"enjoy":[90],"accuracy":[92,227,238],"gain":[93,239],"from":[94,178],"considerably":[95],"increased":[96],"depth":[98],"maintain":[100],"efficiency,":[101],"combine":[103],"residual":[104],"structure":[105],"CReLU":[107],"construct":[109],"middle":[111],"layers.":[112],"(3)":[113],"broaden":[115],"width":[117],"introduce":[119],"multi-scale":[120,168],"feature":[121],"extraction":[122],"property,":[123],"topper":[125],"layers":[126],"are":[127],"designed":[128],"as":[129],"variant":[131],"inception-residual":[133],"structure.":[134],"The":[135],"main":[136],"benefit":[137],"grouping":[139],"these":[140],"modules":[141],"into":[142],"is":[145,268],"both":[147],"negative":[148],"positive":[150],"phase":[151],"information":[152],"implicitly":[153],"contained":[154],"input":[157],"data":[158,213],"can":[159,174,184],"flow":[160],"over":[161],"it":[162,267],"multiple":[164],"paths,":[165],"thus":[166,266],"deep":[167],"features":[169],"explicitly":[170],"capturing":[171],"variation":[173],"be":[175,185],"well":[176,269],"extracted":[177],"multi-path":[179],"sibling":[180],"then":[183],"further":[186],"concatenated":[187],"for":[188],"robust":[189],"recognition.":[190],"We":[191],"obtain":[192,217],"competitive":[193],"results":[194],"year\u2019s":[197,246],"using":[203],"an":[204,229],"ensemble":[205],"two":[207],"models":[209],"trained":[210],"with":[211,228,253],"given":[212],"only.":[214],"Specifically,":[215],"mean":[219],"rate":[221],"57.84%,":[223],"outperforming":[224],"baseline":[226],"absolute":[230,237],"margin":[231],"17.37%,":[233],"yielding":[235],"4.04%":[236],"compared":[240],"result":[243],"last":[245],"winner":[247],"team.":[248],"Meanwhile,":[249],"method":[251],"runs":[252],"speed":[255],"several":[257],"thousands":[258],"frames":[260],"per":[261],"second":[262],"on":[263],"GPU,":[265],"applicable":[270],"real-time":[272],"scenarios.":[273]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}