{"id":"https://openalex.org/W3171625335","doi":"https://doi.org/10.1109/icme52920.2022.9860016","title":"MLTR: Multi-Label Classification with Transformer","display_name":"MLTR: Multi-Label Classification with Transformer","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W3171625335","doi":"https://doi.org/10.1109/icme52920.2022.9860016","mag":"3171625335"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9860016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9860016","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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/A5101583704","display_name":"Cheng Xing","orcid":"https://orcid.org/0000-0002-8738-833X"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xing Cheng","raw_affiliation_strings":["MMU KuaiShou Inc.,Beijing,China","MMU KuaiShou Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"MMU KuaiShou Inc.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]},{"raw_affiliation_string":"MMU KuaiShou Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071301036","display_name":"Hezheng Lin","orcid":"https://orcid.org/0009-0007-8996-8438"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hezheng Lin","raw_affiliation_strings":["MMU KuaiShou Inc.,Beijing,China","MMU KuaiShou Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"MMU KuaiShou Inc.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]},{"raw_affiliation_string":"MMU KuaiShou Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021998562","display_name":"Xiangyu Wu","orcid":"https://orcid.org/0000-0003-2055-5890"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Wu","raw_affiliation_strings":["MMU KuaiShou Inc.,Beijing,China","MMU KuaiShou Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"MMU KuaiShou Inc.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]},{"raw_affiliation_string":"MMU KuaiShou Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034770996","display_name":"Dong Shen","orcid":"https://orcid.org/0000-0003-1063-1351"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Shen","raw_affiliation_strings":["MMU KuaiShou Inc.,Beijing,China","MMU KuaiShou Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"MMU KuaiShou Inc.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]},{"raw_affiliation_string":"MMU KuaiShou Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045464812","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0003-2164-8175"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["MMU KuaiShou Inc.,Beijing,China","MMU KuaiShou Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"MMU KuaiShou Inc.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]},{"raw_affiliation_string":"MMU KuaiShou Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051380367","display_name":"Honglin Liu","orcid":"https://orcid.org/0000-0002-1254-3163"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honglin Liu","raw_affiliation_strings":["MMU KuaiShou Inc.,Beijing,China","MMU KuaiShou Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"MMU KuaiShou Inc.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]},{"raw_affiliation_string":"MMU KuaiShou Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027729414","display_name":"Nian Shi","orcid":"https://orcid.org/0000-0002-5737-9846"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nian Shi","raw_affiliation_strings":["MMU KuaiShou Inc.,Beijing,China","MMU KuaiShou Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"MMU KuaiShou Inc.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]},{"raw_affiliation_string":"MMU KuaiShou Inc., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101583704"],"corresponding_institution_ids":["https://openalex.org/I4210155967"],"apc_list":null,"apc_paid":null,"fwci":4.2616,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.95458953,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9987999796867371,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9987999796867371,"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":0.9973999857902527,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7769137620925903},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6718571186065674},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.666710615158081},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6213077902793884},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.6159862875938416},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5651389360427856},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5485629439353943},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5439832210540771},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5368988513946533},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.48557135462760925},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40911799669265747},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.23673462867736816},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07603970170021057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7769137620925903},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6718571186065674},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.666710615158081},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6213077902793884},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.6159862875938416},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5651389360427856},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5485629439353943},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5439832210540771},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5368988513946533},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.48557135462760925},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40911799669265747},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23673462867736816},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07603970170021057},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9860016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9860016","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2007972815","https://openalex.org/W2031489346","https://openalex.org/W2108598243","https://openalex.org/W2132083787","https://openalex.org/W2162931300","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2520762063","https://openalex.org/W2547875792","https://openalex.org/W2560096627","https://openalex.org/W2746314669","https://openalex.org/W2795247881","https://openalex.org/W2805516822","https://openalex.org/W2884420041","https://openalex.org/W2908510526","https://openalex.org/W2932399282","https://openalex.org/W2948210185","https://openalex.org/W2963306618","https://openalex.org/W2963341956","https://openalex.org/W2963351448","https://openalex.org/W2963403868","https://openalex.org/W2963466847","https://openalex.org/W2963656735","https://openalex.org/W2963676620","https://openalex.org/W2963875806","https://openalex.org/W2969792713","https://openalex.org/W2969985801","https://openalex.org/W2982112268","https://openalex.org/W2997136715","https://openalex.org/W3030520226","https://openalex.org/W3087020912","https://openalex.org/W3089555680","https://openalex.org/W3090578762","https://openalex.org/W3092462694","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3099518117","https://openalex.org/W3120129399","https://openalex.org/W3121523901","https://openalex.org/W3126721948","https://openalex.org/W3133696297","https://openalex.org/W3138516171","https://openalex.org/W3139587317","https://openalex.org/W3139773203","https://openalex.org/W3167456680","https://openalex.org/W3170874841","https://openalex.org/W4214493665","https://openalex.org/W4214636423","https://openalex.org/W4214673031","https://openalex.org/W4385245566","https://openalex.org/W6639102338","https://openalex.org/W6683965311","https://openalex.org/W6687483927","https://openalex.org/W6739901393","https://openalex.org/W6778485988","https://openalex.org/W6785160296","https://openalex.org/W6788135285"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W4256502920","https://openalex.org/W103652678","https://openalex.org/W2999756192","https://openalex.org/W4226090359","https://openalex.org/W4205999209","https://openalex.org/W2735080633","https://openalex.org/W4387801808"],"abstract_inverted_index":{"The":[0,128],"task":[1],"of":[2,34,60,94,123],"multi-label":[3,124,137],"image":[4,125],"classification":[5,126],"is":[6],"to":[7,56,99],"recognize":[8],"all":[9],"the":[10,31,53,58,82,92,121],"object":[11],"labels":[12],"presented":[13],"in":[14],"an":[15],"image.":[16],"Though":[17],"advancing":[18],"for":[19,71],"years,":[20],"small":[21],"objects,":[22],"and":[23,90],"objects":[24],"with":[25,111,144],"high":[26],"conditional":[27],"probability":[28],"are":[29],"still":[30],"main":[32],"bottlenecks":[33],"previous":[35],"convolutional":[36,44],"neural":[37],"network":[38],"(CNN)":[39],"based":[40],"models,":[41],"limited":[42],"by":[43],"kernels'":[45],"representational":[46],"capacity.":[47],"Recent":[48],"vision":[49],"transformer":[50,97],"networks":[51],"utilize":[52],"self-attention":[54],"mechanism":[55],"extract":[57],"feature":[59],"pixel":[61,115],"granularity.":[62],"It":[63],"expresses":[64],"richer":[65],"local":[66],"semantic":[67],"information,":[68],"while":[69],"insufficient":[70],"mining":[72],"global":[73],"spatial":[74],"dependence.":[75],"In":[76],"this":[77],"paper,":[78],"we":[79],"point":[80],"out":[81],"three":[83],"crucial":[84],"problems":[85],"that":[86],"CNN-based":[87],"methods":[88],"encounter":[89],"explore":[91],"possibility":[93],"conducting":[95],"specific":[96],"modules":[98],"settle":[100],"them.":[101],"We":[102],"put":[103],"forward":[104],"a":[105],"Multi-label":[106],"Transformer":[107],"architecture":[108],"(MlTr)":[109],"constructed":[110],"windows":[112],"partitioning,":[113],"in-window":[114],"attention,":[116,118],"cross-window":[117],"particularly":[119],"improving":[120],"performance":[122],"tasks.":[127],"proposed":[129],"MlTr":[130],"shows":[131],"state-of-the-art":[132],"results":[133],"on":[134],"various":[135],"prevalent":[136],"datasets":[138],"such":[139],"as":[140],"MS-COCO,":[141],"Pascal-VOC,":[142],"NUS-WIDE":[143],"88.8%,":[145],"95.8%,":[146],"65.5%":[147],"respectively.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}