{"id":"https://openalex.org/W7138444457","doi":"https://doi.org/10.1609/aaai.v40i16.38317","title":"Facial Dynamics in Video: Instruction Tuning for Improved Facial Expression Perception and Contextual Awareness","display_name":"Facial Dynamics in Video: Instruction Tuning for Improved Facial Expression Perception and Contextual Awareness","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138444457","doi":"https://doi.org/10.1609/aaai.v40i16.38317"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i16.38317","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38317","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i16.38317","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123923698","display_name":"Jiaxing Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxing Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129741014","display_name":"Boyuan Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boyuan Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129701843","display_name":"Xiang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129689560","display_name":"Xihan Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xihan Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"16","first_page":"13163","last_page":"13171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.3549000024795532,"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/T11448","display_name":"Face recognition and analysis","score":0.3549000024795532,"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":0.32820001244544983,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.12080000340938568,"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":0.7509999871253967},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5753999948501587},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5286999940872192},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5141000151634216},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.46889999508857727},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.41850000619888306},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.40639999508857727},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.3926999866962433},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3785000145435333},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.36230000853538513}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7797999978065491},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.7509999871253967},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5753999948501587},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5286999940872192},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5141000151634216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4887000024318695},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.46889999508857727},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.41850000619888306},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40139999985694885},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3926999866962433},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3292999863624573},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C137877099","wikidata":"https://www.wikidata.org/wiki/Q1332977","display_name":"Subsequence","level":3,"score":0.3151000142097473},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.290800005197525},{"id":"https://openalex.org/C2780760462","wikidata":"https://www.wikidata.org/wiki/Q7927952","display_name":"Video modeling","level":4,"score":0.28929999470710754},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2827000021934509},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.26409998536109924},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.26170000433921814},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i16.38317","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38317","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i16.38317","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38317","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Facial":[0],"expression":[1,74],"captioning":[2],"has":[3,20],"found":[4],"widespread":[5],"application":[6],"across":[7],"various":[8],"domains.":[9],"Recently,":[10],"the":[11,42,51,94,117,132,136,157,165,184],"emergence":[12],"of":[13,44,56,96,113,135,172,186],"video":[14,25,57,81,97,188],"Multimodal":[15],"Large":[16],"Language":[17],"Models":[18],"(MLLMs)":[19],"shown":[21],"promise":[22],"in":[23,126,140,190],"general":[24],"understanding":[26],"tasks.":[27],"However,":[28],"describing":[29],"facial":[30,73,102,133],"expressions":[31,134],"within":[32],"videos":[33],"poses":[34],"two":[35],"major":[36],"challenges":[37],"for":[38,71],"these":[39,61],"models:":[40],"(1)":[41],"lack":[43],"adequate":[45],"datasets":[46],"and":[47,49,129,156,168],"benchmarks,":[48],"(2)":[50],"limited":[52,111],"visual":[53],"token":[54],"capacity":[55],"MLLMs.":[58],"To":[59],"address":[60],"issues,":[62],"this":[63,191],"paper":[64],"introduces":[65],"a":[66,110,147,179],"new":[67],"instruction-following":[68],"dataset":[69,77],"tailored":[70],"dynamic":[72],"caption.":[75],"The":[76],"comprises":[78],"5,033":[79],"high-quality":[80],"clips":[82],"annotated":[83],"manually,":[84],"containing":[85],"over":[86],"700,000":[87],"tokens.":[88],"Its":[89],"purpose":[90],"is":[91],"to":[92,99,115,163,182],"improve":[93],"capability":[95],"MLLMs":[98,189],"discern":[100],"subtle":[101],"nuances.":[103],"Furthermore,":[104],"we":[105,145,176],"propose":[106],"FaceTrack-MM,":[107],"which":[108],"leverages":[109],"number":[112],"tokens":[114],"encode":[116],"main":[118,137],"character\u2019s":[119],"face.":[120],"This":[121],"model":[122],"demonstrates":[123],"superior":[124],"performance":[125,185],"tracking":[127],"faces":[128],"focusing":[130],"on":[131],"characters,":[138],"even":[139],"intricate":[141],"multiperson":[142],"scenarios.":[143],"Additionally,":[144],"introduce":[146],"novel":[148],"evaluation":[149],"metric":[150],"combining":[151],"event":[152],"extraction,":[153],"relation":[154],"classification,":[155],"longest":[158],"common":[159],"subsequence":[160],"(LCS)":[161],"algorithm":[162],"assess":[164,183],"content":[166],"consistency":[167,171],"temporal":[169],"sequence":[170],"generated":[173],"text.":[174],"Moreover,":[175],"present":[177],"FECBench,":[178],"benchmark":[180],"designed":[181],"existing":[187],"specific":[192],"task.":[193]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}