{"id":"https://openalex.org/W4408442637","doi":"https://doi.org/10.1109/tpami.2025.3548704","title":"CLIP-Driven Transformer for Weakly Supervised Object Localization","display_name":"CLIP-Driven Transformer for Weakly Supervised Object Localization","publication_year":2025,"publication_date":"2025-03-14","ids":{"openalex":"https://openalex.org/W4408442637","doi":"https://doi.org/10.1109/tpami.2025.3548704","pmid":"https://pubmed.ncbi.nlm.nih.gov/40184291"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3548704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3548704","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100442711","display_name":"Zhiwei Chen","orcid":"https://orcid.org/0000-0002-5474-3630"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Chen","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-5474-3630","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039883116","display_name":"Yunhang Shen","orcid":"https://orcid.org/0000-0002-3970-7519"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhang Shen","raw_affiliation_strings":["Youtu Laboratory, Tencent, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3970-7519","affiliations":[{"raw_affiliation_string":"Youtu Laboratory, Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014628588","display_name":"Liujuan Cao","orcid":"https://orcid.org/0000-0002-7645-9606"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liujuan Cao","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-7645-9606","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012257365","display_name":"Shengchuan Zhang","orcid":"https://orcid.org/0000-0002-0824-4945"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengchuan Zhang","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0001-9163-2932","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.9223,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98570594,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"47","issue":"6","first_page":"4878","last_page":"4896"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9771999716758728,"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":0.9771999716758728,"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/T10320","display_name":"Neural Networks and Applications","score":0.9613999724388123,"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":0.9334999918937683,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7294286489486694},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6082355380058289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5944335460662842},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5050881505012512},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4995541572570801},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4215081036090851},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3911363184452057},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13205170631408691},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0755133330821991}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7294286489486694},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6082355380058289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5944335460662842},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5050881505012512},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4995541572570801},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4215081036090851},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3911363184452057},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13205170631408691},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0755133330821991},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3548704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3548704","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40184291","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40184291","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1271955826","display_name":"\u57fa\u4e8e\u5f31\u76d1\u7763\u5b66\u4e60\u7684\u673a\u8f7d\u5730/\u6d77\u5c0f\u76ee\u6807\u68c0\u6d4b\u7814\u7a76","funder_award_id":"62072387","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1787173488","display_name":"\u9762\u5411\u6df1\u5ea6\u5b66\u4e60\u7684\u5bf9\u6297\u653b\u9632\u6280\u672f\u7814\u7a76","funder_award_id":"62072389","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2785666877","display_name":null,"funder_award_id":"62002305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3568142893","display_name":null,"funder_award_id":"62272401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G363226264","display_name":null,"funder_award_id":"U23A20383","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5284885812","display_name":null,"funder_award_id":"62176222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6075090814","display_name":null,"funder_award_id":"62025603","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"},{"id":"https://openalex.org/G6727647225","display_name":null,"funder_award_id":"62176226","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G717600273","display_name":null,"funder_award_id":"U22B2051","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7272499820","display_name":null,"funder_award_id":"U21B2037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7779606772","display_name":null,"funder_award_id":"62176223","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8406165135","display_name":"\u9762\u5411\u56fe\u654f\u611f\u6df1\u5ea6\u5b66\u4e60\u7684\u7ed3\u6784\u5316\u8d85\u56fe\u7814\u7a76","funder_award_id":"62072386","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/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":100,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W1991367009","https://openalex.org/W2088049833","https://openalex.org/W2092072518","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2295107390","https://openalex.org/W2604260814","https://openalex.org/W2797826601","https://openalex.org/W2798269247","https://openalex.org/W2813911573","https://openalex.org/W2950557962","https://openalex.org/W2963045696","https://openalex.org/W2963603913","https://openalex.org/W2963795442","https://openalex.org/W2963949812","https://openalex.org/W2963952323","https://openalex.org/W2964211037","https://openalex.org/W2964274719","https://openalex.org/W2990371274","https://openalex.org/W2991533779","https://openalex.org/W2991662170","https://openalex.org/W2992308087","https://openalex.org/W2994041372","https://openalex.org/W3000250515","https://openalex.org/W3032908737","https://openalex.org/W3034315787","https://openalex.org/W3035271324","https://openalex.org/W3035318183","https://openalex.org/W3035680157","https://openalex.org/W3035712793","https://openalex.org/W3035725370","https://openalex.org/W3095191037","https://openalex.org/W3107169861","https://openalex.org/W3109073404","https://openalex.org/W3110272085","https://openalex.org/W3128632573","https://openalex.org/W3142837074","https://openalex.org/W3151130473","https://openalex.org/W3152635971","https://openalex.org/W3160694286","https://openalex.org/W3163842339","https://openalex.org/W3172949220","https://openalex.org/W3176171254","https://openalex.org/W3176774696","https://openalex.org/W3188615767","https://openalex.org/W3198377975","https://openalex.org/W3203593070","https://openalex.org/W3204484221","https://openalex.org/W3204507850","https://openalex.org/W3207782762","https://openalex.org/W3212216520","https://openalex.org/W4200631217","https://openalex.org/W4206706211","https://openalex.org/W4210335518","https://openalex.org/W4214736485","https://openalex.org/W4221167635","https://openalex.org/W4226138051","https://openalex.org/W4226255121","https://openalex.org/W4292828879","https://openalex.org/W4304098207","https://openalex.org/W4312310776","https://openalex.org/W4312391970","https://openalex.org/W4312441698","https://openalex.org/W4312509967","https://openalex.org/W4312570500","https://openalex.org/W4313019229","https://openalex.org/W4313052647","https://openalex.org/W4382465452","https://openalex.org/W4385245566","https://openalex.org/W4385815532","https://openalex.org/W4386057743","https://openalex.org/W4386065896","https://openalex.org/W4386066092","https://openalex.org/W4386071798","https://openalex.org/W4386071966","https://openalex.org/W4386075561","https://openalex.org/W4386245233","https://openalex.org/W4387319214","https://openalex.org/W4390871714","https://openalex.org/W4390872717","https://openalex.org/W4390873248","https://openalex.org/W4391215993","https://openalex.org/W4392172801","https://openalex.org/W4398774772","https://openalex.org/W6638319203","https://openalex.org/W6678975374","https://openalex.org/W6681588610","https://openalex.org/W6717772578","https://openalex.org/W6752178629","https://openalex.org/W6753280777","https://openalex.org/W6757817989","https://openalex.org/W6763315676","https://openalex.org/W6773005947","https://openalex.org/W6785700261","https://openalex.org/W6788135285","https://openalex.org/W6791353385","https://openalex.org/W6794978867","https://openalex.org/W6803476161","https://openalex.org/W6803728867"],"related_works":["https://openalex.org/W2737719445","https://openalex.org/W2898210368","https://openalex.org/W2114275278","https://openalex.org/W1489511283","https://openalex.org/W2974914859","https://openalex.org/W2026565050","https://openalex.org/W2110244802","https://openalex.org/W2163728705","https://openalex.org/W949345935","https://openalex.org/W2109550041"],"abstract_inverted_index":{"Weakly":[0],"supervised":[1],"object":[2,37,53,89,146],"localization":[3],"(WSOL)":[4],"aims":[5],"to":[6,35,87,144],"localize":[7],"objects":[8],"using":[9],"only":[10],"image-level":[11],"labels":[12],"as":[13,165],"supervision.":[14,78],"Despite":[15],"recent":[16],"advancements":[17],"incorporating":[18],"transformers":[19],"into":[20,69,155],"WSOL":[21],"have":[22],"resulted":[23],"in":[24,91],"improvements,":[25],"these":[26],"methods":[27],"often":[28],"rely":[29],"on":[30,161],"category-agnostic":[31],"attention":[32],"maps,":[33,71],"leading":[34],"suboptimal":[36],"localization.":[38,54],"This":[39],"paper":[40],"presents":[41],"a":[42,59,92,108,118,125,139],"novel":[43],"CLIP-Driven":[44],"TRansformer":[45],"(CDTR)":[46],"that":[47,64],"learns":[48],"category-aware":[49],"representations":[50,147,154],"for":[51,128],"accurate":[52],"Specifically,":[55],"we":[56,115,132],"initially":[57],"propose":[58],"Category-aware":[60],"Stimulation":[61],"Module":[62,83],"(CSM)":[63],"embeds":[65],"learnable":[66],"category":[67],"biases":[68],"self-attention":[70,101,129,156],"enhancing":[72],"the":[73,96,100,134,170],"learning":[74],"process":[75],"with":[76],"auxiliary":[77],"Additionally,":[79],"an":[80],"Object":[81],"Constraint":[82],"(OCM)":[84],"is":[85],"designed":[86],"refine":[88],"regions":[90],"self-supervised":[93],"manner,":[94],"leveraging":[95],"discriminative":[97],"potential":[98],"of":[99,173],"maps":[102],"provided":[103],"by":[104,148],"CSM.":[105],"To":[106],"create":[107],"synergistic":[109],"connection":[110],"between":[111],"CSM":[112],"and":[113,137,152,167],"OCM,":[114],"further":[116],"develop":[117],"Semantic":[119,140],"Kernel":[120],"Integrator":[121],"(SKI),":[122],"which":[123],"generates":[124],"semantic":[126],"kernel":[127],"maps.":[130,157],"Meanwhile,":[131],"explore":[133],"CLIP":[135],"model":[136],"design":[138],"Boost":[141],"Adapter":[142],"(SBA)":[143],"enrich":[145],"integrating":[149],"semantic-specific":[150],"image":[151],"text":[153],"Extensive":[158],"experimental":[159],"evaluations":[160],"benchmark":[162],"datasets,":[163],"such":[164],"CUB-200-2011":[166],"ILSVRC":[168],"highlight":[169],"superior":[171],"performance":[172],"our":[174],"CDTR":[175],"framework.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}