{"id":"https://openalex.org/W4405778939","doi":"https://doi.org/10.1109/tmm.2024.3521828","title":"Token Masking Transformer for Weakly Supervised Object Localization","display_name":"Token Masking Transformer for Weakly Supervised Object Localization","publication_year":2024,"publication_date":"2024-12-25","ids":{"openalex":"https://openalex.org/W4405778939","doi":"https://doi.org/10.1109/tmm.2024.3521828"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521828","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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":null,"display_name":"Wenhao Xu","orcid":"https://orcid.org/0009-0000-5772-5334"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Xu","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-5772-5334","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020628396","display_name":"Changwei Wang","orcid":"https://orcid.org/0000-0001-8259-7717"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changwei Wang","raw_affiliation_strings":["Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, National Supercomputer Center in Jinan, Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Shandong Academy of Sciences, Qilu University of Technology, Jinan, China","Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-8259-7717","affiliations":[{"raw_affiliation_string":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, National Supercomputer Center in Jinan, Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Shandong Academy of Sciences, Qilu University of Technology, Jinan, China","institution_ids":["https://openalex.org/I152269853"]},{"raw_affiliation_string":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038918940","display_name":"Rongtao Xu","orcid":"https://orcid.org/0000-0003-4619-9679"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongtao Xu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4619-9679","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011919230","display_name":"Shibiao Xu","orcid":"https://orcid.org/0000-0003-4037-9900"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shibiao Xu","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4037-9900","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112127114","display_name":"Weiliang Meng","orcid":"https://orcid.org/0000-0002-3221-4981"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiliang Meng","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3221-4981","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353089","display_name":"Man Zhang","orcid":"https://orcid.org/0000-0003-3043-2122"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Man Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3043-2122","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100667567","display_name":"Xiaopeng Zhang","orcid":"https://orcid.org/0000-0002-0092-6474"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Zhang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0092-6474","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":2.5958,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91929323,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"27","issue":null,"first_page":"2059","last_page":"2069"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9746999740600586,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8061223030090332},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.610821008682251},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5600146055221558},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5186890363693237},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5072143077850342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48467472195625305},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3805055618286133},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35376498103141785},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1502440869808197},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.14783677458763123},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0921514630317688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8061223030090332},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.610821008682251},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5600146055221558},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5186890363693237},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5072143077850342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48467472195625305},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3805055618286133},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35376498103141785},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1502440869808197},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.14783677458763123},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0921514630317688},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521828","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2573920917","display_name":null,"funder_award_id":"62162044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4365032757","display_name":null,"funder_award_id":"JQ23014","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G6579916853","display_name":null,"funder_award_id":"62302052","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6871481020","display_name":null,"funder_award_id":"U21A20515","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7090326123","display_name":"\u7f3a\u635f\u6570\u636e\u7684\u9c81\u68d2\u975e\u5b8c\u6574\u591a\u89c6\u56fe\u5b66\u4e60\u65b9\u6cd5\u53ca\u5176\u89c6\u89c9\u5e94\u7528\u7814\u7a76","funder_award_id":"62071157","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8311886428","display_name":null,"funder_award_id":"62171321","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8316038559","display_name":null,"funder_award_id":"62271074","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2295107390","https://openalex.org/W2527917904","https://openalex.org/W2765793020","https://openalex.org/W2883554151","https://openalex.org/W2950557962","https://openalex.org/W2962858109","https://openalex.org/W2963045696","https://openalex.org/W2964274719","https://openalex.org/W2964316443","https://openalex.org/W2971765953","https://openalex.org/W2990371274","https://openalex.org/W2992308087","https://openalex.org/W3023138874","https://openalex.org/W3033595049","https://openalex.org/W3034315787","https://openalex.org/W3035260401","https://openalex.org/W3035318183","https://openalex.org/W3035712793","https://openalex.org/W3042085267","https://openalex.org/W3087782943","https://openalex.org/W3110272085","https://openalex.org/W3142837074","https://openalex.org/W3159712850","https://openalex.org/W3165739880","https://openalex.org/W3176171254","https://openalex.org/W3176774696","https://openalex.org/W3177958285","https://openalex.org/W3188615767","https://openalex.org/W3203593070","https://openalex.org/W3204484221","https://openalex.org/W4200631217","https://openalex.org/W4221167635","https://openalex.org/W4224239295","https://openalex.org/W4224930893","https://openalex.org/W4226138051","https://openalex.org/W4285276772","https://openalex.org/W4299583570","https://openalex.org/W4306404970","https://openalex.org/W4311904006","https://openalex.org/W4312391970","https://openalex.org/W4312441698","https://openalex.org/W4312570500","https://openalex.org/W4313019229","https://openalex.org/W4313069833","https://openalex.org/W4313156423","https://openalex.org/W4318149001","https://openalex.org/W4360995498","https://openalex.org/W4366308987","https://openalex.org/W4366351734","https://openalex.org/W4379382408","https://openalex.org/W4382467532","https://openalex.org/W4386245233","https://openalex.org/W4387587560","https://openalex.org/W4388081044","https://openalex.org/W4390872875","https://openalex.org/W4390874210","https://openalex.org/W4391215993","https://openalex.org/W4393148303","https://openalex.org/W4402127888","https://openalex.org/W4408951634","https://openalex.org/W6638319203","https://openalex.org/W6746052068","https://openalex.org/W6779248606","https://openalex.org/W6788135285","https://openalex.org/W6803856452","https://openalex.org/W6852913297"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4285141722","https://openalex.org/W4304700937"],"abstract_inverted_index":{"Weakly":[0],"supervised":[1],"object":[2,16],"localization":[3,17,87,118],"(WSOL)":[4],"is":[5,132],"both":[6],"a":[7,75,101,115,126,149],"promising":[8],"and":[9,84,158,209],"challenging":[10],"task":[11,68],"that":[12,192],"aims":[13],"to":[14,31,62,69,108,113,135,140,154,162,176],"achieve":[15],"exclusively":[18],"through":[19,36],"image":[20],"category":[21],"labels":[22],"for":[23],"supervision.":[24],"Visual":[25],"transformers":[26],"have":[27],"recently":[28],"been":[29],"applied":[30],"WSOL,":[32],"demonstrating":[33],"significant":[34],"success":[35],"the":[37,47,52,58,63,66,86,92,138,160,179,198,206],"exploitation":[38],"of":[39,65,181,200],"long-range":[40],"feature":[41],"dependencies":[42],"in":[43,143],"self-attention":[44,71],"mechanisms.":[45],"However,":[46],"transformer-based":[48,110,202],"approach":[49,60],"suffers":[50],"from":[51],"same":[53],"partial":[54],"activation":[55,174],"problem":[56],"as":[57],"CNN-based":[59],"due":[61],"use":[64],"classification":[67],"train":[70],"map,":[72],"i.e.,":[73],"only":[74],"few":[76],"discriminative":[77,122,128],"regions":[78],"are":[79],"assigned":[80],"high":[81],"attention":[82],"response":[83],"thus":[85],"map":[88,119],"does":[89],"not":[90],"cover":[91],"whole":[93],"object.":[94],"To":[95],"alleviate":[96],"this":[97],"problem,":[98],"we":[99,147,168],"propose":[100],"plug-and-play":[102],"Token":[103],"Masking":[104],"Transformer":[105],"(TMT)":[106],"method":[107],"help":[109],"WSOL":[111],"methods":[112,203],"obtain":[114],"more":[116,164],"complete":[117],"by":[120,183],"dynamic":[121],"token":[123,129,150,156,173],"masking.":[124],"Specifically,":[125],"batch-wise":[127],"selection":[130],"strategy":[131],"first":[133],"introduced":[134],"flexibly":[136],"determine":[137],"tokens":[139],"be":[141],"masked":[142],"each":[144],"image.":[145],"Then,":[146],"design":[148,170],"masking":[151,157],"transformer":[152],"block":[153],"perform":[155],"inspire":[159],"network":[161],"mine":[163],"object-related":[165],"tokens.":[166,188],"Besides,":[167],"also":[169],"an":[171],"intermediate":[172,187],"loss":[175],"further":[177],"improve":[178,197],"performance":[180,199,212],"TMT":[182,194],"imposing":[184],"constraints":[185],"on":[186,213],"Extensive":[189],"experiments":[190],"demonstrate":[191],"our":[193],"can":[195],"substantially":[196],"existing":[201],"without":[204],"increasing":[205],"computational":[207],"cost,":[208],"achieves":[210],"state-of-the-art":[211],"two":[214],"mainstream":[215],"benchmarks.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}