{"id":"https://openalex.org/W4387969676","doi":"https://doi.org/10.1145/3581783.3611959","title":"Rethinking the Localization in Weakly Supervised Object Localization","display_name":"Rethinking the Localization in Weakly Supervised Object Localization","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969676","doi":"https://doi.org/10.1145/3581783.3611959"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611959","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5114929853","display_name":"Rui Xu","orcid":"https://orcid.org/0000-0002-0737-5214"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xu","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-0737-5214","affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039158745","display_name":"Yong Luo","orcid":"https://orcid.org/0000-0002-2296-6370"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Luo","raw_affiliation_strings":["Wuhan University & Hubei Luojia Laboratory, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-2296-6370","affiliations":[{"raw_affiliation_string":"Wuhan University & Hubei Luojia Laboratory, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020194895","display_name":"Han Hu","orcid":"https://orcid.org/0000-0001-7532-0496"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Hu","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7532-0496","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060042752","display_name":"Bo Du","orcid":"https://orcid.org/0000-0002-0059-8458"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Du","raw_affiliation_strings":["Wuhan University & Hubei Luojia Laboratory, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-0059-8458","affiliations":[{"raw_affiliation_string":"Wuhan University & Hubei Luojia Laboratory, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026951130","display_name":"Jialie Shen","orcid":"https://orcid.org/0000-0002-4560-8509"},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jialie Shen","raw_affiliation_strings":["City, University of London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-4560-8509","affiliations":[{"raw_affiliation_string":"City, University of London, London, United Kingdom","institution_ids":["https://openalex.org/I180825142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041572550","display_name":"Yonggang Wen","orcid":"https://orcid.org/0000-0002-2751-5114"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yonggang Wen","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-2751-5114","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5484","last_page":"5494"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.780427098274231},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.7550095319747925},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7316203117370605},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.66521155834198},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6478859186172485},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6110273003578186},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5747719407081604},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5394763350486755},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5373119115829468},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4976532757282257},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4950107932090759},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.4850413203239441},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.46765369176864624},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4633643329143524},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46166306734085083},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.36706286668777466},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.08569854497909546}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.780427098274231},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.7550095319747925},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7316203117370605},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.66521155834198},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6478859186172485},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6110273003578186},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5747719407081604},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5394763350486755},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5373119115829468},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4976532757282257},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4950107932090759},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.4850413203239441},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.46765369176864624},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4633643329143524},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46166306734085083},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36706286668777466},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.08569854497909546},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611959","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1284973545","display_name":null,"funder_award_id":"62276195","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1836220556","display_name":null,"funder_award_id":"62225113","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4674470810","display_name":null,"funder_award_id":"62276195, 62141112, 62225113","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4798117554","display_name":null,"funder_award_id":"2021YFC3300200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4902648202","display_name":null,"funder_award_id":"62141112","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5449343560","display_name":null,"funder_award_id":"2042023kf1033","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6357995720","display_name":null,"funder_award_id":"2021YFC3300200","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1919709169","https://openalex.org/W1995875735","https://openalex.org/W2097117768","https://openalex.org/W2117539524","https://openalex.org/W2183341477","https://openalex.org/W2295107390","https://openalex.org/W2934198733","https://openalex.org/W2946948417","https://openalex.org/W2950557962","https://openalex.org/W2955425717","https://openalex.org/W2963090248","https://openalex.org/W2964028976","https://openalex.org/W2997138816","https://openalex.org/W3011722050","https://openalex.org/W3012573144","https://openalex.org/W3034315787","https://openalex.org/W3042283600","https://openalex.org/W3048686909","https://openalex.org/W3107169861","https://openalex.org/W3110272085","https://openalex.org/W3111557229","https://openalex.org/W3172752666","https://openalex.org/W3175156984","https://openalex.org/W3188868777","https://openalex.org/W3192693288","https://openalex.org/W3203003533","https://openalex.org/W3203593070","https://openalex.org/W3204484221","https://openalex.org/W4283794102","https://openalex.org/W4287775237","https://openalex.org/W4295795885","https://openalex.org/W4304091741","https://openalex.org/W4312647976","https://openalex.org/W6602452458","https://openalex.org/W6753494528","https://openalex.org/W6778485988"],"related_works":["https://openalex.org/W3192357901","https://openalex.org/W3036286480","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W4237171675","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W2962677013"],"abstract_inverted_index":{"Weakly":[0],"supervised":[1],"object":[2,39,42,75],"localization":[3,40],"(WSOL)":[4],"is":[5,19,104,130],"one":[6,74],"of":[7,101,155,171],"the":[8,22,25,29,46,61,81,89,98,128,134,147,152,162,169],"most":[9],"popular":[10,163],"and":[11,41,136,165],"challenging":[12],"tasks":[13],"in":[14,24],"computer":[15],"vision.":[16],"This":[17],"task":[18],"to":[20,80,115,150],"localize":[21,73],"objects":[23],"images":[26],"given":[27],"only":[28,72],"image-level":[30],"supervision.":[31],"Recently,":[32],"dividing":[33],"WSOL":[34],"into":[35],"two":[36],"parts":[37],"(class-agnostic":[38],"classification)":[43],"has":[44],"become":[45],"state-of-the-art":[47],"pipeline":[48,57],"for":[49,76,86,123],"this":[50,56],"task.":[51],"However,":[52],"existing":[53],"solutions":[54],"under":[55],"usually":[58],"suffer":[59],"from":[60],"following":[62],"drawbacks:":[63],"1)":[64],"they":[65,70],"are":[66],"not":[67,105],"flexible":[68],"since":[69],"can":[71],"each":[77],"image":[78],"due":[79],"adopted":[82],"single-class":[83],"regression":[84],"(SCR)":[85],"localization;":[87],"2)":[88],"generated":[90],"pseudo":[91],"bounding":[92,157],"boxes":[93],"may":[94],"be":[95],"noisy,":[96],"but":[97],"negative":[99,153],"impact":[100,154],"such":[102],"noise":[103],"well":[106],"addressed.":[107],"To":[108],"remedy":[109],"these":[110],"drawbacks,":[111],"we":[112,139],"first":[113],"propose":[114],"replace":[116],"SCR":[117],"with":[118],"a":[119,141],"binary-class":[120],"detector":[121,129],"(BCD)":[122],"localizing":[124],"multiple":[125],"objects,":[126],"where":[127],"trained":[131],"by":[132],"discriminating":[133],"foreground":[135],"background.":[137],"Then":[138],"design":[140],"weighted":[142],"entropy":[143],"(WE)":[144],"loss":[145],"using":[146],"unlabeled":[148],"data":[149],"reduce":[151],"noisy":[156],"boxes.":[158],"Extensive":[159],"experiments":[160],"on":[161],"CUB-200-2011":[164],"ImageNet-1K":[166],"datasets":[167],"demonstrate":[168],"effectiveness":[170],"our":[172],"method.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}