{"id":"https://openalex.org/W4415535465","doi":"https://doi.org/10.1145/3746027.3755036","title":"Learning from Heterogeneity: Generalizing Dynamic Facial Expression Recognition via Distributionally Robust Optimization","display_name":"Learning from Heterogeneity: Generalizing Dynamic Facial Expression Recognition via Distributionally Robust Optimization","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415535465","doi":"https://doi.org/10.1145/3746027.3755036"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755036","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.15765","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114413524","display_name":"Feng-Qi Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feng-Qi Cui","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-0454-940X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043997486","display_name":"Anyang Tong","orcid":"https://orcid.org/0000-0003-0960-1497"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anyang Tong","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-0960-1497","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100928377","display_name":"Jinyang Huang","orcid":"https://orcid.org/0000-0001-5483-2812"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyang Huang","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5483-2812","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436740","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0002-4230-1077"},"institutions":[{"id":"https://openalex.org/I4210161496","display_name":"A*STAR Graduate Academy","ror":"https://ror.org/059yjzn93","country_code":"SG","type":"education","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210161496"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["IHPC and CFAR, A*STAR, singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4230-1077","affiliations":[{"raw_affiliation_string":"IHPC and CFAR, A*STAR, singapore, Singapore","institution_ids":["https://openalex.org/I4210161496"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059530979","display_name":"Dan Guo","orcid":"https://orcid.org/0000-0003-2594-254X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Guo","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2594-254X","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100603421","display_name":"Zhi Liu","orcid":"https://orcid.org/0000-0003-0537-4522"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhi Liu","raw_affiliation_strings":["The University of Electro-Communications, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-0537-4522","affiliations":[{"raw_affiliation_string":"The University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100377147","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3094-7735","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5114413524"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":5.6662,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96329709,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5587","last_page":"5596"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9987999796867371,"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/T10057","display_name":"Face and Expression Recognition","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9966999888420105,"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/robustness","display_name":"Robustness (evolution)","score":0.7128000259399414},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7046999931335449},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.49559998512268066},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4593000113964081},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45649999380111694},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4336000084877014},{"id":"https://openalex.org/keywords/facial-expression-recognition","display_name":"Facial expression recognition","score":0.4162999987602234},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3614000082015991},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.3596000075340271}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7128000259399414},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7046999931335449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.677299976348877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5350000262260437},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.49559998512268066},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4593000113964081},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4336000084877014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41749998927116394},{"id":"https://openalex.org/C2987714656","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Facial expression recognition","level":4,"score":0.4162999987602234},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.32659998536109924},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.2896000146865845},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25690001249313354},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755036","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.15765","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15765","pdf_url":"https://arxiv.org/pdf/2507.15765","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.15765","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15765","pdf_url":"https://arxiv.org/pdf/2507.15765","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2139916508","https://openalex.org/W2194775991","https://openalex.org/W2788334925","https://openalex.org/W2963524571","https://openalex.org/W2997240345","https://openalex.org/W3034572008","https://openalex.org/W3206349670","https://openalex.org/W3209798173","https://openalex.org/W4309660795","https://openalex.org/W4376132596","https://openalex.org/W4380520337","https://openalex.org/W4387969399","https://openalex.org/W4387969416","https://openalex.org/W4391216149","https://openalex.org/W4403791238","https://openalex.org/W4403792097"],"related_works":[],"abstract_inverted_index":{"Dynamic":[0],"Facial":[1],"Expression":[2],"Recognition":[3],"(DFER)":[4],"plays":[5],"a":[6,44,84],"critical":[7],"role":[8],"in":[9],"affective":[10],"computing":[11],"and":[12,34,52,61,80,93,102,120,126,138,148,158,169],"human-computer":[13],"interaction.":[14],"Although":[15],"existing":[16],"methods":[17],"achieve":[18],"comparable":[19],"performance,":[20],"they":[21],"inevitably":[22],"suffer":[23],"from":[24],"performance":[25],"degradation":[26],"under":[27],"sample":[28],"heterogeneity":[29],"caused":[30,65],"by":[31,66],"multi-source":[32],"data":[33],"individual":[35],"expression":[36],"variability.":[37],"To":[38],"address":[39],"these":[40],"challenges,":[41],"we":[42],"propose":[43],"novel":[45],"framework,":[46],"called":[47],"Heterogeneity-aware":[48],"Distributional":[49,72],"Framework":[50],"(HDF),":[51],"design":[53],"two":[54,133],"plug-and-play":[55],"modules":[56],"to":[57,90,116],"enhance":[58],"time-frequency":[59],"modeling":[60],"mitigate":[62],"optimization":[63,108],"imbalance":[64],"hard":[67],"samples.":[68],"Specifically,":[69],"the":[70],"Time-Frequency":[71],"Attention":[73],"Module":[74,112],"(DAM)":[75],"captures":[76],"both":[77,145],"temporal":[78],"consistency":[79],"frequency":[81],"robustness":[82],"through":[83],"dual-branch":[85],"attention":[86],"design,":[87],"improving":[88],"tolerance":[89],"sequence":[91],"inconsistency":[92],"visual":[94],"style":[95],"shifts.":[96],"Then,":[97],"based":[98],"on":[99,132],"gradient":[100],"sensitivity":[101],"information":[103],"bottleneck":[104],"principles,":[105],"an":[106],"adaptive":[107],"module":[109],"Distribution-aware":[110],"Scaling":[111],"(DSM)":[113],"is":[114],"introduced":[115],"dynamically":[117],"balance":[118],"classification":[119],"contrastive":[121],"losses,":[122],"enabling":[123],"more":[124],"stable":[125],"discriminative":[127],"representation":[128],"learning.":[129],"Extensive":[130],"experiments":[131],"widely":[134],"used":[135],"datasets,":[136],"DFEW":[137],"FERV39k,":[139],"demonstrate":[140],"that":[141],"HDF":[142],"significantly":[143],"improves":[144],"recognition":[146],"accuracy":[147],"robustness.":[149],"Our":[150],"method":[151],"achieves":[152],"superior":[153],"weighted":[154],"average":[155,160],"recall":[156,161],"(WAR)":[157],"unweighted":[159],"(UAR)":[162],"while":[163],"maintaining":[164],"strong":[165],"generalization":[166],"across":[167],"diverse":[168],"imbalanced":[170],"scenarios.":[171],"Codes":[172],"are":[173],"released":[174],"at":[175],"https://github.com/QIcita/HDF_DFER.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}