{"id":"https://openalex.org/W4304091741","doi":"https://doi.org/10.1145/3503161.3547945","title":"Proxy Probing Decoder for Weakly Supervised Object Localization: A Baseline Investigation","display_name":"Proxy Probing Decoder for Weakly Supervised Object Localization: A Baseline Investigation","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304091741","doi":"https://doi.org/10.1145/3503161.3547945"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547945","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547945","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/A5028154645","display_name":"Jingyuan Xu","orcid":"https://orcid.org/0000-0002-4462-315X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingyuan Xu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078162380","display_name":"Hongtao Xie","orcid":"https://orcid.org/0000-0002-6249-5315"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtao Xie","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059194547","display_name":"Chuanbin Liu","orcid":"https://orcid.org/0000-0002-2840-6235"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanbin Liu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028154645"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.1799,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.50948239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4185","last_page":"4193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.7726047039031982},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6777011156082153},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6381725072860718},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.603828489780426},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5393140316009521},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.4956320524215698},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4845115542411804},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40036535263061523},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32887858152389526},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11120933294296265}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7726047039031982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6777011156082153},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6381725072860718},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.603828489780426},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5393140316009521},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.4956320524215698},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4845115542411804},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40036535263061523},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32887858152389526},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11120933294296265},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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:10.1145/3503161.3547945","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547945","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/G5050325314","display_name":null,"funder_award_id":"WK3480000011, WK2100000026","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5723266252","display_name":null,"funder_award_id":"2021M703081","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"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":29,"referenced_works":["https://openalex.org/W1538422756","https://openalex.org/W2133324800","https://openalex.org/W2295107390","https://openalex.org/W2747329762","https://openalex.org/W2808091730","https://openalex.org/W2883554151","https://openalex.org/W2950557962","https://openalex.org/W2963402313","https://openalex.org/W2964274719","https://openalex.org/W2990154684","https://openalex.org/W2990371274","https://openalex.org/W3032908737","https://openalex.org/W3034315787","https://openalex.org/W3035318183","https://openalex.org/W3092932168","https://openalex.org/W3109988120","https://openalex.org/W3111980808","https://openalex.org/W3116157532","https://openalex.org/W3138516171","https://openalex.org/W3152635971","https://openalex.org/W3159481202","https://openalex.org/W3203593070","https://openalex.org/W3204484221","https://openalex.org/W3204976424","https://openalex.org/W4212774754","https://openalex.org/W4225381939","https://openalex.org/W4283821214","https://openalex.org/W4312349930","https://openalex.org/W4313150877"],"related_works":["https://openalex.org/W3203142394","https://openalex.org/W2161474341","https://openalex.org/W2028495302","https://openalex.org/W4302615923","https://openalex.org/W1974101135","https://openalex.org/W4396872084","https://openalex.org/W2351061015","https://openalex.org/W2017509870","https://openalex.org/W4220731478","https://openalex.org/W2542937328"],"abstract_inverted_index":{"Weakly":[0],"supervised":[1],"object":[2,9],"localization":[3],"(WSOL)":[4],"aims":[5],"to":[6,30,48,75,110,131,158,187],"localize":[7,163],"the":[8,19,32,37,46,52,59,81,88,106,133,137,140,154,160,164,169,175,181,188,201,209],"with":[10,21,97],"only":[11,180],"image":[12],"category":[13],"labels.":[14],"Existing":[15],"methods":[16],"generally":[17],"fine-tune":[18],"models":[20,226],"manually":[22],"selected":[23],"training":[24,152],"epochs":[25],"and":[26,55,92,114,143,162,179,192,204,219,225],"subjective":[27],"loss":[28],"functions":[29],"mitigate":[31],"partial":[33,116],"activation":[34],"problem":[35],"of":[36,58,84,125,128,139],"classification-based":[38],"model.":[39,61],"However,":[40],"such":[41],"fine-tuning":[42,96],"scheme":[43],"would":[44],"cause":[45],"model":[47,95,172],"degrade,":[49],"e.g.":[50],"affect":[51],"classification":[53],"performance":[54],"generalization":[56],"capabilities":[57,178],"pre-trained":[60],"In":[62,166],"this":[63,167],"paper,":[64],"we":[65,104,119],"propose":[66],"a":[67,98,122,126,216,221],"novel":[68,99],"method":[69],"named":[70],"Proxy":[71],"Probing":[72],"Decoder":[73],"(PPD)":[74],"meet":[76],"these":[77],"challenges,":[78],"which":[79,212],"utilizes":[80],"segmentation":[82],"property":[83],"self-attention":[85],"map":[86],"in":[87],"self-supervised":[89,107],"vision":[90,108,170],"transformer":[91,109,171],"breaks":[93],"through":[94],"proxy":[100,123,155,182],"probing":[101],"decoder.":[102],"Specifically,":[103],"utilize":[105],"capture":[111],"long-range":[112],"dependencies":[113],"avoid":[115],"activation.":[117],"Then":[118],"simply":[120],"adopt":[121],"consisting":[124],"series":[127],"decoding":[129],"layers":[130],"transform":[132],"feature":[134,161,176],"representations":[135],"into":[136],"heatmap":[138],"objects'":[141],"foreground":[142],"conduct":[144],"localization.":[145],"The":[146],"backbone":[147],"parameters":[148],"are":[149],"frozen":[150],"during":[151],"while":[153],"is":[156,183],"used":[157],"decode":[159],"object.":[165],"way,":[168],"can":[173],"maintain":[174],"representation":[177],"required":[184],"for":[185],"adapting":[186],"task.":[189],"Without":[190],"bells":[191],"whistles,":[193],"our":[194],"framework":[195],"achieves":[196],"55.0%":[197],"Top-1":[198,206],"Loc":[199,207],"on":[200,208,230],"ILSVRC2012":[202],"dataset":[203],"78.8%":[205],"CUB-200-2011":[210],"dataset,":[211],"surpasses":[213],"state-of-the-art":[214],"by":[215],"large":[217],"margin":[218],"provides":[220],"simple":[222],"baseline.":[223],"Codes":[224],"will":[227],"be":[228],"available":[229],"Github.":[231]},"counts_by_year":[{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}