{"id":"https://openalex.org/W4304080876","doi":"https://doi.org/10.1145/3503161.3548343","title":"Two-Stream Transformer for Multi-Label Image Classification","display_name":"Two-Stream Transformer for Multi-Label Image Classification","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304080876","doi":"https://doi.org/10.1145/3503161.3548343"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548343","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548343","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th 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/A5076214561","display_name":"Xuelin Zhu","orcid":"https://orcid.org/0000-0001-7676-2843"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuelin Zhu","raw_affiliation_strings":["Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012384188","display_name":"Jiuxin Cao","orcid":"https://orcid.org/0000-0002-2448-6717"},"institutions":[{"id":"https://openalex.org/I4210155350","display_name":"Purple Mountain Laboratories","ror":"https://ror.org/04zcbk583","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210155350"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiuxin Cao","raw_affiliation_strings":["Southeast University & Purple Mountain Laboratories, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Southeast University & Purple Mountain Laboratories, Nanjing, China","institution_ids":["https://openalex.org/I4210155350","https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018527272","display_name":"Jiawei Ge","orcid":"https://orcid.org/0000-0001-7268-7815"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Ge","raw_affiliation_strings":["Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747522","display_name":"Weijia Liu","orcid":"https://orcid.org/0000-0003-2634-7283"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijia Liu","raw_affiliation_strings":["Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100461655","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-4250-6339"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]},{"id":"https://openalex.org/I4210155350","display_name":"Purple Mountain Laboratories","ror":"https://ror.org/04zcbk583","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210155350"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Southeast University & Purple Mountain Laboratories, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Southeast University & Purple Mountain Laboratories, Nanjing, China","institution_ids":["https://openalex.org/I4210155350","https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5076214561"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":2.9399,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.92707229,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3598","last_page":"3607"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9983999729156494,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9979000091552734,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9977999925613403,"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":0.8251668214797974},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.6030064225196838},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5730653405189514},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.5699160099029541},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5147026181221008},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4392760992050171},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.422793447971344},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41888633370399475},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.41792556643486023},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4113944172859192},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4063546061515808},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32136350870132446},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.27449363470077515},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.13550320267677307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251668214797974},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.6030064225196838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5730653405189514},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.5699160099029541},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5147026181221008},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4392760992050171},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.422793447971344},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41888633370399475},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.41792556643486023},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4113944172859192},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4063546061515808},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32136350870132446},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27449363470077515},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.13550320267677307},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548343","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548343","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4209845559","display_name":null,"funder_award_id":"No.62172089, No.61972087, No.62172090, No.62106045","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7257675290","display_name":null,"funder_award_id":"No.BK20191258","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1567302070","https://openalex.org/W1861492603","https://openalex.org/W1962468782","https://openalex.org/W2007972815","https://openalex.org/W2103117377","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2405989770","https://openalex.org/W2410641892","https://openalex.org/W2518918709","https://openalex.org/W2521365688","https://openalex.org/W2560096627","https://openalex.org/W2736688973","https://openalex.org/W2788361849","https://openalex.org/W2890153145","https://openalex.org/W2932399282","https://openalex.org/W2943563866","https://openalex.org/W2963300078","https://openalex.org/W2963676620","https://openalex.org/W2963745697","https://openalex.org/W2963875806","https://openalex.org/W2966628364","https://openalex.org/W2982112268","https://openalex.org/W2997136715","https://openalex.org/W2998420437","https://openalex.org/W3035665101","https://openalex.org/W3035682985","https://openalex.org/W3090449556","https://openalex.org/W3096609285","https://openalex.org/W3099518117","https://openalex.org/W3102424508","https://openalex.org/W3120129399","https://openalex.org/W3138516171","https://openalex.org/W3167456680","https://openalex.org/W3192931333","https://openalex.org/W3205618423","https://openalex.org/W4214673031","https://openalex.org/W4214893857"],"related_works":["https://openalex.org/W2750434199","https://openalex.org/W4205999209","https://openalex.org/W2347374138","https://openalex.org/W2735080633","https://openalex.org/W2129428289","https://openalex.org/W2050635624","https://openalex.org/W2101447046","https://openalex.org/W2091753323","https://openalex.org/W2168037874","https://openalex.org/W2078285696"],"abstract_inverted_index":{"Multi-label":[0],"image":[1,204],"classification":[2,205],"is":[3,124],"a":[4,19,74,91,110,120,141],"fundamental":[5],"yet":[6],"challenging":[7],"task":[8,26],"in":[9,53,80,115],"computer":[10],"vision":[11,60],"that":[12,194],"aims":[13,98],"to":[14,64,99,126,166],"identify":[15],"multiple":[16],"objects":[17],"from":[18,130],"given":[20],"image.":[21],"Recent":[22],"studies":[23],"on":[24,29,86,180,201],"this":[25,70,145],"mainly":[27],"focus":[28],"learning":[30,78],"cross-modal":[31,121],"interactions":[32],"between":[33,59,150],"label":[34,102,138,173,176],"semantics":[35,103,139],"and":[36,56,61,136,190],"high-level":[37],"visual":[38,128,169,182],"representations":[39,170],"via":[40,109,140],"an":[41],"attention":[42,47,112,122],"operation.":[43],"However,":[44],"these":[45],"one-shot":[46],"based":[48],"approaches":[49],"generally":[50],"perform":[51],"poorly":[52],"establishing":[54],"accurate":[55,175],"robust":[57],"alignments":[58],"text":[62],"due":[63],"the":[65,82,95,147,156,163,202],"acknowledged":[66],"semantic":[67,96,134,148,164],"gap.":[68],"In":[69,144],"paper,":[71],"we":[72],"propose":[73],"two-stream":[75],"transformer":[76],"(TSFormer)":[77],"framework,":[79],"which":[81],"spatial":[83,131],"stream":[84,97,132,135,165],"focuses":[85],"extracting":[87],"patch":[88],"features":[89,129],"with":[90],"global":[92],"perception,":[93],"while":[94],"learn":[100],"vision-aware":[101],"as":[104,106,155],"well":[105],"their":[107],"correlations":[108],"multi-shot":[111],"mechanism.":[113],"Specifically,":[114],"each":[116,172],"layer":[117,159],"of":[118],"TSFormer,":[119],"module":[123],"developed":[125],"aggregate":[127],"into":[133],"update":[137],"residual":[142],"connection.":[143],"way,":[146],"gap":[149],"two":[151],"streams":[152],"gradually":[153],"narrows":[154],"procedure":[157],"progresses":[158],"by":[160],"layer,":[161],"allowing":[162],"produce":[167],"sophisticated":[168],"for":[171],"towards":[174],"recognition.":[177],"Extensive":[178],"experiments":[179],"three":[181],"benchmarks,":[183],"including":[184],"Pascal":[185],"VOC":[186],"2007,":[187],"Microsoft":[188],"COCO":[189],"NUS-WIDE,":[191],"consistently":[192],"demonstrate":[193],"our":[195],"proposed":[196],"TSFormer":[197],"achieves":[198],"state-of-the-art":[199],"performance":[200],"multi-label":[203],"task.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":10}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}