{"id":"https://openalex.org/W4403791238","doi":"https://doi.org/10.1145/3664647.3681583","title":"Open-Set Video-based Facial Expression Recognition with Human Expression-sensitive Prompting","display_name":"Open-Set Video-based Facial Expression Recognition with Human Expression-sensitive Prompting","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791238","doi":"https://doi.org/10.1145/3664647.3681583"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681583","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5079420533","display_name":"Yuanyuan Liu","orcid":"https://orcid.org/0000-0002-1913-0089"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Liu","raw_affiliation_strings":["School of Computer Science, China University of Geosciences (Wuhan), Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-1913-0089","affiliations":[{"raw_affiliation_string":"School of Computer Science, China University of Geosciences (Wuhan), Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404215","display_name":"Yuxuan Huang","orcid":"https://orcid.org/0009-0007-1094-934X"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Huang","raw_affiliation_strings":["School of Computer Science, China University of Geosciences (Wuhan), Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0007-1094-934X","affiliations":[{"raw_affiliation_string":"School of Computer Science, China University of Geosciences (Wuhan), Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031319556","display_name":"Shuyang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyang Liu","raw_affiliation_strings":["School of Computer Science, China University of Geosciences (Wuhan), Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0005-1360-7631","affiliations":[{"raw_affiliation_string":"School of Computer Science, China University of Geosciences (Wuhan), Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074672983","display_name":"Yibing Zhan","orcid":"https://orcid.org/0000-0003-3180-0484"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibing Zhan","raw_affiliation_strings":["JD Explore Academy, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3180-0484","affiliations":[{"raw_affiliation_string":"JD Explore Academy, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043602166","display_name":"Zijing Chen","orcid":"https://orcid.org/0009-0008-2518-9977"},"institutions":[{"id":"https://openalex.org/I196829312","display_name":"La Trobe University","ror":"https://ror.org/01rxfrp27","country_code":"AU","type":"education","lineage":["https://openalex.org/I196829312"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zijing Chen","raw_affiliation_strings":["Cisco - La Trobe Centre for Artificial Intelligence and Internet of Things, La Trobe University, Flora Hill, Australia"],"raw_orcid":"https://orcid.org/0009-0008-2518-9977","affiliations":[{"raw_affiliation_string":"Cisco - La Trobe Centre for Artificial Intelligence and Internet of Things, La Trobe University, Flora Hill, Australia","institution_ids":["https://openalex.org/I196829312"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100457637","display_name":"Zhe Chen","orcid":"https://orcid.org/0000-0001-5004-8975"},"institutions":[{"id":"https://openalex.org/I196829312","display_name":"La Trobe University","ror":"https://ror.org/01rxfrp27","country_code":"AU","type":"education","lineage":["https://openalex.org/I196829312"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhe Chen","raw_affiliation_strings":["Cisco - La Trobe Centre for Artificial Intelligence and Internet of Things, La Trobe University, Flora Hill, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5004-8975","affiliations":[{"raw_affiliation_string":"Cisco - La Trobe Centre for Artificial Intelligence and Internet of Things, La Trobe University, Flora Hill, Australia","institution_ids":["https://openalex.org/I196829312"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.2219,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.98731769,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5722","last_page":"5731"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9990000128746033,"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":0.9990000128746033,"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/T10057","display_name":"Face and Expression Recognition","score":0.9951000213623047,"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":0.9926000237464905,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.7029693126678467},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6771867871284485},{"id":"https://openalex.org/keywords/facial-expression-recognition","display_name":"Facial expression recognition","score":0.6264281868934631},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5191589593887329},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4868471026420593},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48342788219451904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4676997661590576},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4002545475959778},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.3992483615875244},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.26626765727996826}],"concepts":[{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.7029693126678467},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6771867871284485},{"id":"https://openalex.org/C2987714656","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Facial expression recognition","level":4,"score":0.6264281868934631},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5191589593887329},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4868471026420593},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48342788219451904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4676997661590576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4002545475959778},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3992483615875244},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26626765727996826},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681583","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2243226955","https://openalex.org/W2295107390","https://openalex.org/W2606933083","https://openalex.org/W2895006884","https://openalex.org/W2895752198","https://openalex.org/W2914911817","https://openalex.org/W2957123975","https://openalex.org/W2963149653","https://openalex.org/W3034552680","https://openalex.org/W3037439697","https://openalex.org/W3093370878","https://openalex.org/W3128420506","https://openalex.org/W3134961575","https://openalex.org/W3177174258","https://openalex.org/W3198377975","https://openalex.org/W3206349670","https://openalex.org/W4205166102","https://openalex.org/W4214751560","https://openalex.org/W4214756262","https://openalex.org/W4221042956","https://openalex.org/W4284713852","https://openalex.org/W4287113019","https://openalex.org/W4304092183","https://openalex.org/W4304099179","https://openalex.org/W4312447943","https://openalex.org/W4312651322","https://openalex.org/W4318980730","https://openalex.org/W4323065172","https://openalex.org/W4386065871","https://openalex.org/W4386076274","https://openalex.org/W4386076497","https://openalex.org/W4386076609","https://openalex.org/W4388186454","https://openalex.org/W4391128821","https://openalex.org/W4391451889"],"related_works":["https://openalex.org/W2642127892","https://openalex.org/W4205986151","https://openalex.org/W2355913164","https://openalex.org/W2162992774","https://openalex.org/W1153638794","https://openalex.org/W2168968280","https://openalex.org/W2116055069","https://openalex.org/W2901126000","https://openalex.org/W4323520705","https://openalex.org/W2356663679"],"abstract_inverted_index":{"In":[0,31],"Video-based":[1,39],"Facial":[2,40],"Expression":[3,41],"Recognition":[4,42],"(V-FER),":[5],"models":[6,22,61],"are":[7],"typically":[8],"trained":[9],"on":[10,191,209,213],"closed-set":[11],"datasets":[12],"with":[13,24,120,152],"a":[14,36,90,116,135,153,224],"fixed":[15],"number":[16],"of":[17,128,181,207],"known":[18,49,130],"classes.":[19],"However,":[20],"these":[21,71],"struggle":[23],"unknown":[25,132],"classes":[26],"common":[27],"in":[28,185],"real-world":[29],"scenarios.":[30],"this":[32,86],"paper,":[33],"we":[34,68,88],"introduce":[35],"challenging":[37],"Open-set":[38],"(OV-FER)":[43],"task,":[44],"aiming":[45],"to":[46,64,97,102,123,158],"identify":[47,65],"both":[48,129],"and":[50,131,162,175,211,215],"new,":[51],"unseen":[52,66],"facial":[53,105],"expressions.":[54],"While":[55],"existing":[56],"approaches":[57],"use":[58],"large-scale":[59],"vision-language":[60],"like":[62],"CLIP":[63,151],"classes,":[67],"argue":[69],"that":[70,139,169,197],"methods":[72,222],"may":[73],"not":[74],"adequately":[75],"capture":[76],"the":[77,173,179],"subtle":[78],"human":[79,183],"expressions":[80],"needed":[81],"for":[82],"OV-FER.":[83],"To":[84],"address":[85],"limitation,":[87],"propose":[89],"novel":[91,182],"Human":[92],"Expression-Sensitive":[93],"Prompting":[94],"(HESP)":[95],"mechanism":[96],"significantly":[98,200],"enhance":[99,124],"CLIP's":[100,125,202],"ability":[101,157],"model":[103],"video-based":[104],"expression":[106],"details":[107],"effectively.":[108],"Our":[109],"proposed":[110],"HESP":[111,198],"comprises":[112],"three":[113],"components:":[114],"1)":[115],"textual":[117,126,174],"prompting":[118,137],"module":[119,138],"learnable":[121],"prompts":[122],"representation":[127],"emotions,":[133],"2)":[134],"visual":[136,155,176],"encodes":[140],"temporal":[141],"emotional":[142],"information":[143],"from":[144],"video":[145,186,220],"frames":[146],"using":[147],"expression-sensitive":[148],"attention,":[149],"equipping":[150],"new":[154],"modeling":[156],"extract":[159],"emotion-rich":[160],"information,":[161],"3)":[163],"an":[164],"open-set":[165,219],"multi-task":[166],"learning":[167],"scheme":[168],"promotes":[170],"interaction":[171],"between":[172],"modules,":[177],"improving":[178],"understanding":[180,221],"emotions":[184],"sequences.":[187],"Extensive":[188],"experiments":[189],"conducted":[190],"four":[192],"OV-FER":[193],"task":[194],"settings":[195],"demonstrate":[196],"can":[199],"boost":[201],"performance":[203],"(a":[204],"relative":[205],"improvement":[206],"17.93%":[208],"AUROC":[210],"106.18%":[212],"OSCR)":[214],"outperform":[216],"other":[217],"state-of-the-art":[218],"by":[223],"large":[225],"margin.":[226],"Code":[227],"is":[228],"available":[229],"at":[230],"https://github.com/cosinehuang/HESP.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}