{"id":"https://openalex.org/W4403792221","doi":"https://doi.org/10.1145/3664647.3680623","title":"Two in One Go: Single-stage Emotion Recognition with Decoupled Subject-context Transformer","display_name":"Two in One Go: Single-stage Emotion Recognition with Decoupled Subject-context Transformer","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792221","doi":"https://doi.org/10.1145/3664647.3680623"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680623","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680623","pdf_url":null,"source":null,"license":null,"license_id":null,"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":"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/A5050586034","display_name":"Xinpeng Li","orcid":"https://orcid.org/0000-0003-4703-7778"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinpeng Li","raw_affiliation_strings":["China Telecom & Northwestern Polytechnical University, Beijing, China","Shenzhen Technology University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-4703-7778","affiliations":[{"raw_affiliation_string":"China Telecom & Northwestern Polytechnical University, Beijing, China","institution_ids":["https://openalex.org/I17145004","https://openalex.org/I4210136246"]},{"raw_affiliation_string":"Shenzhen Technology University, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047351419","display_name":"Teng Wang","orcid":"https://orcid.org/0000-0003-2331-3619"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Teng Wang","raw_affiliation_strings":["The University of Hong Kong, Hongkong, China"],"raw_orcid":"https://orcid.org/0000-0003-2331-3619","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hongkong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078587654","display_name":"Jian Zhao","orcid":"https://orcid.org/0000-0002-3508-756X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhao","raw_affiliation_strings":["China Telecom & Northwestern Polytechnical University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3508-756X","affiliations":[{"raw_affiliation_string":"China Telecom & Northwestern Polytechnical University, Beijing, China","institution_ids":["https://openalex.org/I17145004","https://openalex.org/I4210136246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103004350","display_name":"Shuyi Mao","orcid":"https://orcid.org/0009-0000-4338-687X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyi Mao","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0000-4338-687X","affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101698854","display_name":"Jinbao Wang","orcid":"https://orcid.org/0000-0001-5916-8965"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinbao Wang","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5916-8965","affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063285882","display_name":"Feng Zheng","orcid":"https://orcid.org/0000-0002-1701-9141"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zheng","raw_affiliation_strings":["Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-1701-9141","affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033413473","display_name":"Xiaojiang Peng","orcid":"https://orcid.org/0000-0002-5783-321X"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojiang Peng","raw_affiliation_strings":["Shenzhen Technology University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5783-321X","affiliations":[{"raw_affiliation_string":"Shenzhen Technology University, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100740143","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0002-0019-4197"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["China Telecom & Northwestern Polytechnical University, Beijing, China","Shenzhen Technology University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0019-4197","affiliations":[{"raw_affiliation_string":"China Telecom & Northwestern Polytechnical University, Beijing, China","institution_ids":["https://openalex.org/I17145004","https://openalex.org/I4210136246"]},{"raw_affiliation_string":"Shenzhen Technology University, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21823717,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9340","last_page":"9349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9944999814033508,"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/T10057","display_name":"Face and Expression Recognition","score":0.9914000034332275,"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/computer-science","display_name":"Computer science","score":0.6135009527206421},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.5926598906517029},{"id":"https://openalex.org/keywords/single-stage","display_name":"Single stage","score":0.5868620872497559},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5622093677520752},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4632270336151123},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4609196186065674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41025620698928833},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17951706051826477},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12847930192947388},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11950129270553589},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.08042049407958984},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.0776483416557312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6135009527206421},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.5926598906517029},{"id":"https://openalex.org/C3020376581","wikidata":"https://www.wikidata.org/wiki/Q16866784","display_name":"Single stage","level":2,"score":0.5868620872497559},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5622093677520752},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4632270336151123},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4609196186065674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41025620698928833},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17951706051826477},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12847930192947388},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11950129270553589},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.08042049407958984},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0776483416557312},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680623","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W2045977420","https://openalex.org/W2082794029","https://openalex.org/W2122736472","https://openalex.org/W2134995458","https://openalex.org/W2158705122","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2345305417","https://openalex.org/W2766272105","https://openalex.org/W2784257003","https://openalex.org/W2788728386","https://openalex.org/W2907891676","https://openalex.org/W2946410230","https://openalex.org/W2962766617","https://openalex.org/W2963351448","https://openalex.org/W2964751875","https://openalex.org/W3034504038","https://openalex.org/W3034520808","https://openalex.org/W3035336958","https://openalex.org/W3093232475","https://openalex.org/W3094378471","https://openalex.org/W3096609285","https://openalex.org/W3107331169","https://openalex.org/W3118310928","https://openalex.org/W3119221111","https://openalex.org/W3124675547","https://openalex.org/W3135844897","https://openalex.org/W3137284029","https://openalex.org/W3137646246","https://openalex.org/W3171516518","https://openalex.org/W3173787706","https://openalex.org/W3174480456","https://openalex.org/W3175546442","https://openalex.org/W3176899168","https://openalex.org/W3179103990","https://openalex.org/W3182328899","https://openalex.org/W3184134865","https://openalex.org/W3185372235","https://openalex.org/W3187313248","https://openalex.org/W3199093552","https://openalex.org/W3202521030","https://openalex.org/W3203003533","https://openalex.org/W3206349670","https://openalex.org/W3211510783","https://openalex.org/W4205768578","https://openalex.org/W4300550485","https://openalex.org/W4304091998","https://openalex.org/W4304098213","https://openalex.org/W4312312588","https://openalex.org/W4312465353","https://openalex.org/W4312554764","https://openalex.org/W4312609734","https://openalex.org/W4312823769","https://openalex.org/W4312848112","https://openalex.org/W4312907849","https://openalex.org/W4319300140","https://openalex.org/W4380993795","https://openalex.org/W4385644282","https://openalex.org/W4386047789","https://openalex.org/W4386071535","https://openalex.org/W4386072325","https://openalex.org/W4386075510","https://openalex.org/W4386075843","https://openalex.org/W4386076487","https://openalex.org/W4387968338","https://openalex.org/W4387969399","https://openalex.org/W4403242122"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4388258507","https://openalex.org/W2392013855","https://openalex.org/W4318064328","https://openalex.org/W2357926602","https://openalex.org/W3200517220","https://openalex.org/W2374569605","https://openalex.org/W2386062718","https://openalex.org/W4393047559","https://openalex.org/W899618282"],"abstract_inverted_index":{"Emotion":[0],"recognition":[1,71,154],"aims":[2],"to":[3,100,109],"discern":[4],"the":[5,38,47,64],"emotional":[6],"state":[7],"of":[8,41],"subjects":[9,29],"within":[10,131],"an":[11],"image,":[12],"relying":[13],"on":[14,148,179],"subject-centric":[15,102],"and":[16,43,55,83,95,125,136,141,157,173,181,186],"contextual":[17],"visual":[18],"cues.":[19],"Current":[20],"approaches":[21],"typically":[22],"follow":[23],"a":[24,68,74,117,169,174],"two-stage":[25,162],"pipeline:":[26],"first":[27],"localize":[28],"by":[30],"off-the-shelf":[31],"detectors,":[32],"then":[33],"perform":[34],"emotion":[35,70,84,96,153],"classification":[36],"through":[37],"late":[39],"fusion":[40],"subject":[42,81],"context":[44,126],"features.":[45],"However,":[46],"complicated":[48],"paradigm":[49],"suffers":[50],"from":[51],"disjoint":[52],"training":[53,89],"stages":[54],"limited":[56],"fine-grained":[57,113],"interaction":[58],"between":[59,112],"subject-context":[60,114],"elements.":[61],"To":[62],"address":[63],"challenge,":[65],"we":[66,91,106],"present":[67],"single-stage":[69,146],"approach,":[72],"employing":[73],"Decoupled":[75],"Subject-Context":[76],"Transformer":[77],"(DSCT),":[78],"for":[79],"simultaneous":[80],"localization":[82],"classification.":[85],"Rather":[86],"than":[87],"compartmentalizing":[88],"stages,":[90],"jointly":[92],"leverage":[93],"box":[94],"signals":[97],"as":[98],"supervision":[99],"enrich":[101],"feature":[103],"learning.":[104],"Furthermore,":[105],"introduce":[107],"DSCT":[108],"facilitate":[110],"interactions":[111],"cues":[115],"in":[116],"''decouple-then-fuse''":[118],"manner.":[119],"The":[120],"decoupled":[121],"query":[122],"tokens-subject":[123],"queries":[124],"queries-gradually":[127],"intertwine":[128],"across":[129],"layers":[130],"DSCT,":[132],"during":[133],"which":[134],"spatial":[135],"semantic":[137],"relations":[138],"are":[139,188],"exploited":[140],"aggregated.":[142],"We":[143],"evaluate":[144],"our":[145],"framework":[147],"two":[149],"widely":[150],"used":[151],"context-aware":[152],"datasets,":[155,183],"CAER-S":[156,180],"EMOTIC.":[158],"Our":[159],"approach":[160],"surpasses":[161],"alternatives":[163],"with":[164],"fewer":[165],"parameter":[166],"numbers,":[167],"achieving":[168],"3.39%":[170],"accuracy":[171],"improvement":[172],"6.46%":[175],"average":[176],"precision":[177],"gain":[178],"EMOTIC":[182],"respectively.":[184],"Code":[185],"models":[187],"available":[189],"at:":[190],"https://github.com/Sampson-Lee/DSCT.":[191]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}