{"id":"https://openalex.org/W4401307507","doi":"https://doi.org/10.1145/3664647.3681443","title":"Towards End-to-End Explainable Facial Action Unit Recognition via Vision-Language Joint Learning","display_name":"Towards End-to-End Explainable Facial Action Unit Recognition via Vision-Language Joint Learning","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4401307507","doi":"https://doi.org/10.1145/3664647.3681443"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681443","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681443","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3681443","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026473068","display_name":"Xuri Ge","orcid":"https://orcid.org/0000-0002-3925-4951"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xuri Ge","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-3925-4951","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012498345","display_name":"Junchen Fu","orcid":"https://orcid.org/0000-0003-4759-2042"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junchen Fu","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-4759-2042","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008400844","display_name":"Fuhai Chen","orcid":"https://orcid.org/0000-0001-5441-5998"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuhai Chen","raw_affiliation_strings":["Fuzhou University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5441-5998","affiliations":[{"raw_affiliation_string":"Fuzhou University, Fuzhou, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021902921","display_name":"Shan An","orcid":"https://orcid.org/0000-0001-7796-6952"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan An","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-7796-6952","affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027171279","display_name":"Nicu Sebe","orcid":"https://orcid.org/0000-0002-6597-7248"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicu Sebe","raw_affiliation_strings":["University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6597-7248","affiliations":[{"raw_affiliation_string":"University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069702331","display_name":"Joemon M. Jose","orcid":"https://orcid.org/0000-0001-9228-1759"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joemon M. Jose","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-9228-1759","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8189","last_page":"8198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9995999932289124,"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":0.9995999932289124,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8626972436904907},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.747825026512146},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.6039972901344299},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.552102267742157},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.48038655519485474},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47993379831314087},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43501368165016174},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42657631635665894},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4153783917427063},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3786129951477051},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3424508571624756},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.10473331809043884},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07971978187561035}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8626972436904907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.747825026512146},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.6039972901344299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.552102267742157},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.48038655519485474},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47993379831314087},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43501368165016174},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42657631635665894},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4153783917427063},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3786129951477051},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3424508571624756},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.10473331809043884},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07971978187561035},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3664647.3681443","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681443","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2408.00644","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.00644","pdf_url":"https://arxiv.org/pdf/2408.00644","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:eprints.gla.ac.uk:330436","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/60445.html>","pdf_url":"https://eprints.gla.ac.uk/330436/1/330436.pdf","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"},{"id":"pmh:oai:iris.unitn.it:11572/439451","is_oa":true,"landing_page_url":"https://dl.acm.org/doi/10.1145/3664647.3681443","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3664647.3681443","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681443","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321893","display_name":"Department of Education, Fujian Province","ror":"https://ror.org/01d6wrk87"},{"id":"https://openalex.org/F4320325408","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1595126664","https://openalex.org/W1987231241","https://openalex.org/W2036250785","https://openalex.org/W2045472600","https://openalex.org/W2051297709","https://openalex.org/W2064675550","https://openalex.org/W2079735306","https://openalex.org/W2095499283","https://openalex.org/W2104883350","https://openalex.org/W2187089797","https://openalex.org/W2396445702","https://openalex.org/W2612215259","https://openalex.org/W2789992948","https://openalex.org/W2903991757","https://openalex.org/W2963908984","https://openalex.org/W2964120214","https://openalex.org/W2969059826","https://openalex.org/W2982033433","https://openalex.org/W2988302524","https://openalex.org/W3011227460","https://openalex.org/W3035232877","https://openalex.org/W3101614002","https://openalex.org/W3102025332","https://openalex.org/W3105536522","https://openalex.org/W3115865297","https://openalex.org/W3138516171","https://openalex.org/W3168709512","https://openalex.org/W3173225380","https://openalex.org/W3174724419","https://openalex.org/W3175851380","https://openalex.org/W3176327573","https://openalex.org/W3189718596","https://openalex.org/W3206477365","https://openalex.org/W4210792305","https://openalex.org/W4283805587","https://openalex.org/W4285601347","https://openalex.org/W4293066072","https://openalex.org/W4312239024","https://openalex.org/W4318618444","https://openalex.org/W4377098248","https://openalex.org/W4378465281","https://openalex.org/W4380881572","https://openalex.org/W4385820037","https://openalex.org/W4386038389","https://openalex.org/W4391681622","https://openalex.org/W4393942911"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W2894289927"],"abstract_inverted_index":{"Facial":[0,8],"action":[1],"units":[2],"(AUs),":[3],"as":[4],"defined":[5],"in":[6,25],"the":[7,42,82,111,162,169,175,195],"Action":[9],"Coding":[10],"System":[11],"(FACS),":[12],"have":[13,34],"received":[14],"significant":[15],"research":[16],"interest":[17],"owing":[18],"to":[19,73,94,138],"their":[20],"diverse":[21],"range":[22],"of":[23,44,50,84,174],"applications":[24],"facial":[26,113,149],"state":[27],"analysis.":[28],"Current":[29],"mainstream":[30,181],"FAU":[31,67,107,182],"recognition":[32,46,68,183],"models":[33,93],"a":[35],"notable":[36],"limitation,":[37],"i.e.,":[38],"focusing":[39],"only":[40],"on":[41,146,154,172],"accuracy":[43],"AU":[45,52,75,118,133,140,158],"and":[47,78,100,115,127,156,189],"overlooking":[48],"explanations":[49],"corresponding":[51],"states.":[53],"In":[54,130,177],"this":[55],"paper,":[56],"we":[57],"propose":[58],"an":[59],"end-to-end":[60],"Vision-Language":[61],"joint":[62,85],"learning":[63,135],"network":[64],"for":[65],"explainable":[66],"(termed":[69],"VL-FAU),":[70],"which":[71],"aims":[72],"reinforce":[74],"representation":[76,114,134,143],"capability":[77],"language":[79,92,192],"interpretability":[80,191],"through":[81],"integration":[83],"multimodal":[86],"tasks.":[87],"Specifically,":[88],"VL-FAU":[89,185],"brings":[90],"together":[91],"generate":[95],"fine-grained":[96],"local":[97,117],"muscle":[98],"descriptions":[99,193],"distinguishable":[101],"global":[102,112],"face":[103],"description":[104],"when":[105],"optimising":[106],"recognition.":[108],"Through":[109],"this,":[110],"its":[116],"representations":[119],"will":[120],"achieve":[121],"higher":[122],"distinguishability":[123],"among":[124],"different":[125,128],"AUs":[126],"subjects.":[129],"addition,":[131,178],"multi-level":[132],"is":[136],"utilised":[137],"improve":[139],"individual":[141],"attention-aware":[142],"capabilities":[144],"based":[145],"multi-scale":[147],"combined":[148],"stem":[150],"feature.":[151],"Extensive":[152],"experiments":[153],"DISFA":[155],"BP4D":[157],"datasets":[159],"show":[160],"that":[161],"proposed":[163],"approach":[164],"achieves":[165],"superior":[166],"performance":[167],"over":[168],"state-of-the-art":[170],"methods":[171],"most":[173],"metrics.":[176],"compared":[179],"with":[180,194],"methods,":[184],"can":[186],"provide":[187],"local-":[188],"global-level":[190],"AUs'":[196],"predictions.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}