{"id":"https://openalex.org/W7155885727","doi":"https://doi.org/10.1145/3774904.3792417","title":"BHGap: A Deep Iterative Prompting and Multi-stage Alignment Framework for Dynamic Facial Expression Recognition","display_name":"BHGap: A Deep Iterative Prompting and Multi-stage Alignment Framework for Dynamic Facial Expression Recognition","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7155885727","doi":"https://doi.org/10.1145/3774904.3792417"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792417","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792417","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 ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792417","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134665924","display_name":"Yichi Zhang","orcid":"https://orcid.org/0009-0000-7647-4454"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichi Zhang","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-7647-4454","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134694040","display_name":"Yunqi Han","orcid":"https://orcid.org/0009-0009-6776-5108"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunqi Han","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-6776-5108","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134666828","display_name":"Jiayue Ding","orcid":"https://orcid.org/0009-0001-1375-8131"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayue Ding","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-1375-8131","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5094124757","display_name":"Liangyu Chen","orcid":"https://orcid.org/0009-0005-0243-3613"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangyu Chen","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-0243-3613","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":null,"issue":null,"first_page":"7247","last_page":"7258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9728000164031982,"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":0.9728000164031982,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.004900000058114529,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0031999999191612005,"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/feature","display_name":"Feature (linguistics)","score":0.5831000208854675},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.439300000667572},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4374000132083893},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.43309998512268066},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43290001153945923},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.426800012588501},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.41999998688697815},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4156999886035919},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4147999882698059},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.41260001063346863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8052999973297119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.586899995803833},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5831000208854675},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.439300000667572},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4374000132083893},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43290001153945923},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.41999998688697815},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.41260001063346863},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.35519999265670776},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.32690000534057617},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C2777742833","wikidata":"https://www.wikidata.org/wiki/Q1964083","display_name":"Reciprocal","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25589999556541443},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2540999948978424},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792417","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792417","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 ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792417","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792417","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 ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2053101950","https://openalex.org/W2519656895","https://openalex.org/W2619383789","https://openalex.org/W2754021867","https://openalex.org/W2910165986","https://openalex.org/W2964051877","https://openalex.org/W3015906487","https://openalex.org/W3040639721","https://openalex.org/W3093370878","https://openalex.org/W3206349670","https://openalex.org/W4304099179","https://openalex.org/W4312651322","https://openalex.org/W4380520337","https://openalex.org/W4382240798","https://openalex.org/W4385815506","https://openalex.org/W4386065595","https://openalex.org/W4386075538","https://openalex.org/W4386699383","https://openalex.org/W4388189896","https://openalex.org/W4393181080","https://openalex.org/W4400527853","https://openalex.org/W4402170672","https://openalex.org/W4402916290","https://openalex.org/W4402979749","https://openalex.org/W4403791893","https://openalex.org/W4403792097","https://openalex.org/W4413146043","https://openalex.org/W4413146904","https://openalex.org/W4413147095"],"related_works":[],"abstract_inverted_index":{"Dynamic":[0],"Facial":[1],"Expression":[2],"Recognition":[3],"(DFER),":[4],"as":[5,19],"a":[6,92,117,122,138,171,236],"crucial":[7],"part":[8],"of":[9,61,131,239],"affective":[10],"computing,":[11],"has":[12],"broad":[13],"applications":[14],"in":[15],"many":[16],"areas":[17],"such":[18],"human-computer":[20],"interaction":[21],"and":[22,50,69,106,162,191,216,225,243],"social":[23],"media":[24],"content":[25],"analysis.":[26],"Effectively":[27],"integrating":[28],"multimodal":[29,247],"information,":[30],"particularly":[31],"audio-visual":[32,62,114],"signals,":[33],"remains":[34],"the":[35,58,78,152,177,199,222],"core":[36],"challenge.":[37],"However,":[38],"existing":[39],"approaches":[40],"are":[41,74],"generally":[42],"constrained":[43],"by":[44,82],"two":[45],"major":[46],"challenges:":[47],"(1)":[48],"shallow":[49],"static":[51],"fusion":[52,119,242],"mechanisms,":[53],"which":[54,73,96],"fail":[55],"to":[56,76,112,185],"capture":[57],"dynamic":[59],"co-evolution":[60],"features":[63],"during":[64],"deep":[65,98,161,240],"interaction;":[66],"(2)":[67],"implicit":[68,209],"coarse":[70],"alignment":[71,105,174,182,245],"strategies,":[72],"insufficient":[75],"bridge":[77],"modality":[79,154],"gap":[80],"caused":[81],"heterogeneous":[83],"feature":[84,104,164],"distributions.":[85],"To":[86],"address":[87],"these":[88],"issues,":[89],"we":[90,136,168],"propose":[91],"novel":[93],"framework,":[94],"BHGap,":[95],"integrates":[97],"iterative":[99,241],"prompt":[100,144],"generation":[101,125],"with":[102,208],"multi-stage":[103,173],"fusion.":[107],"The":[108],"key":[109],"idea":[110],"is":[111,183,251],"reformulate":[113],"collaboration":[115],"from":[116],"one-shot":[118],"event":[120],"into":[121],"continuous,":[123],"reciprocal":[124],"process":[126],"that":[127,146,229],"spans":[128],"every":[129],"layer":[130],"frozen":[132],"backbone":[133],"encoders.":[134],"Specifically,":[135],"design":[137],"State":[139],"Space":[140],"Model":[141],"(SSM)-based":[142],"cross-modal":[143],"generator":[145],"dynamically":[147],"produces":[148],"''guidance":[149],"prompts''":[150],"for":[151,246],"counterpart":[153],"at":[155,176,198,253],"each":[156],"encoding":[157],"layer,":[158],"thereby":[159],"enabling":[160],"fine-grained":[163,213],"co-evolution.":[165],"Beyond":[166],"encoding,":[167],"further":[169],"introduce":[170],"coarse-to-fine":[172],"module:":[175],"macro":[178],"level,":[179,201],"low-rank":[180],"adversarial":[181],"employed":[184],"establish":[186],"spatio-temporal":[187],"congruity":[188],"between":[189],"audio":[190],"video":[192],"while":[193],"reducing":[194],"global":[195],"distributional":[196],"discrepancies;":[197],"micro":[200],"Maximum":[202],"Mean":[203],"Discrepancy":[204],"(MMD)":[205],"constraints":[206],"combined":[207],"differentiation":[210],"optimization":[211],"ensure":[212],"statistical":[214],"consistency":[215],"semantic":[217],"alignment.":[218],"Extensive":[219],"experiments":[220],"on":[221],"public":[223],"DFEW":[224],"MAFW":[226],"datasets":[227],"demonstrate":[228],"our":[230],"method":[231],"achieves":[232],"state-of-the-art":[233],"performance,":[234],"offering":[235],"new":[237],"paradigm":[238],"explicit":[244],"emotion":[248],"recognition.":[249],"Code":[250],"available":[252],"https://github.com/NDYZD666/-public-BHGap.":[254]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-28T00:00:00"}