{"id":"https://openalex.org/W4416252281","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228100","title":"Behavior-prompted Learning with Tree Attention for Advanced Facial Action Unit Detection","display_name":"Behavior-prompted Learning with Tree Attention for Advanced Facial Action Unit Detection","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252281","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228100"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5100613732","display_name":"Hao Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Zou","raw_affiliation_strings":["Zhejiang University,The State Key Laboratory of Blockchain and Data Security,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,The State Key Laboratory of Blockchain and Data Security,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101631994","display_name":"Zheng Gao","orcid":"https://orcid.org/0000-0001-5541-8840"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Gao","raw_affiliation_strings":["Zhejiang University,The State Key Laboratory of Blockchain and Data Security,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,The State Key Laboratory of Blockchain and Data Security,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020068117","display_name":"Yante Li","orcid":"https://orcid.org/0000-0003-4824-2044"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yante Li","raw_affiliation_strings":["University of Oulu,Center of Machine Vision and Signal Analysis,Oulu,Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu,Center of Machine Vision and Signal Analysis,Oulu,Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032660998","display_name":"Ce Li","orcid":"https://orcid.org/0000-0002-2202-632X"},"institutions":[{"id":"https://openalex.org/I4210132158","display_name":"Annoroad Gene Technology (China)","ror":"https://ror.org/03gyd9q58","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132158"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ce Li","raw_affiliation_strings":["Moore Threads Technology Co. Ltd.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Moore Threads Technology Co. Ltd.,Beijing,China","institution_ids":["https://openalex.org/I4210132158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101691489","display_name":"Xiao\u2010Bai Li","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobai Li","raw_affiliation_strings":["Zhejiang University,The State Key Laboratory of Blockchain and Data Security,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,The State Key Laboratory of Blockchain and Data Security,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100613732"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38225337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9768000245094299,"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":0.9768000245094299,"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/T11448","display_name":"Face recognition and analysis","score":0.007699999958276749,"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/T11094","display_name":"Face Recognition and Perception","score":0.004999999888241291,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6022999882698059},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5073999762535095},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.4941999912261963},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.48170000314712524},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.45190000534057617},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45080000162124634},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4375999867916107},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4066999852657318},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.39890000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7425000071525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6590999960899353},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6022999882698059},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5073999762535095},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.4941999912261963},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.48170000314712524},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47440001368522644},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45080000162124634},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4375999867916107},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4066999852657318},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.39890000224113464},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37070000171661377},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.33180001378059387},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C40346341","wikidata":"https://www.wikidata.org/wiki/Q1391629","display_name":"Facial Action Coding System","level":3,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/W2045472600","https://openalex.org/W2049640633","https://openalex.org/W2051297709","https://openalex.org/W2280620570","https://openalex.org/W2341528187","https://openalex.org/W2421475762","https://openalex.org/W2589142773","https://openalex.org/W2903991757","https://openalex.org/W2946287218","https://openalex.org/W2962858109","https://openalex.org/W2963875208","https://openalex.org/W2969059826","https://openalex.org/W3003850414","https://openalex.org/W3011227460","https://openalex.org/W3092956019","https://openalex.org/W3173225380","https://openalex.org/W3175851380","https://openalex.org/W3176327573","https://openalex.org/W3198377975","https://openalex.org/W3206854705","https://openalex.org/W4285601347","https://openalex.org/W4289752563","https://openalex.org/W4312239024","https://openalex.org/W4377098248","https://openalex.org/W4386076084","https://openalex.org/W4390873581","https://openalex.org/W4390873629","https://openalex.org/W4402979749","https://openalex.org/W4403509085","https://openalex.org/W4403791856"],"related_works":[],"abstract_inverted_index":{"Action":[0],"Unit":[1],"(AU)":[2],"is":[3,95,119,153],"a":[4,12,44,51,59,90,114],"systematic":[5],"coding":[6],"of":[7,35,79,102],"facial":[8,16],"behaviors":[9],"that":[10,63,121,136],"plays":[11],"crucial":[13],"role":[14],"in":[15],"expression":[17],"recognition.":[18],"AU":[19,47,80],"detection":[20,48],"faces":[21],"significant":[22],"challenges":[23],"due":[24],"to":[25,74,97],"the":[26,36,99],"fine-grained":[27,100],"categorical":[28],"differences":[29],"and":[30,87,105,129,149],"coexistence":[31],"at":[32,155],"varying":[33],"intensities":[34,86],"AU.":[37],"To":[38,109],"address":[39],"these":[40],"challenges,":[41],"we":[42,57],"propose":[43],"refined":[45],"behavior-prompt":[46,61],"model":[49],"featuring":[50],"coarse-to-fine":[52,91],"tree":[53,92],"attention":[54,93],"mechanism.":[55],"Specifically,":[56],"introduce":[58],"learnable":[60],"approach":[62],"utilizes":[64],"large":[65],"vision-language":[66],"models,":[67],"harnessing":[68],"their":[69,106],"powerful":[70],"semantic":[71],"representation":[72],"capabilities":[73],"encompass":[75],"comprehensive":[76],"prior":[77],"knowledge":[78],"behaviors.":[81],"Besides,":[82],"considering":[83],"AUs\u2019":[84],"diverse":[85],"interactive":[88],"nature,":[89],"module":[94],"customized":[96],"capture":[98],"details":[101],"individual":[103],"AUs":[104],"long-range":[107],"dependencies.":[108],"further":[110],"mitigate":[111],"vision-text":[112],"bias,":[113],"feature":[115],"interaction":[116],"learning":[117],"strategy":[118],"employed":[120],"progressively":[122],"incorporates":[123],"context-related":[124],"visual":[125],"information":[126],"into":[127],"prompts":[128],"decouples":[130],"AU-specific":[131],"representations.":[132],"Extensive":[133],"experiments":[134],"demonstrate":[135],"our":[137],"proposed":[138],"method":[139],"achieves":[140],"state-of-the-art":[141],"results":[142],"on":[143],"two":[144],"widely":[145],"used":[146],"benchmarks,":[147],"BP4D":[148],"DISFA.":[150],"Our":[151],"code":[152],"avaliable":[154],"https://github.com/ColinHaoZou/FAUD-CLIP.":[156]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}