{"id":"https://openalex.org/W4399418517","doi":"https://doi.org/10.1145/3652583.3658026","title":"Self-Supervised Multi-Label Classification with Global Context and Local Attention","display_name":"Self-Supervised Multi-Label Classification with Global Context and Local Attention","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399418517","doi":"https://doi.org/10.1145/3652583.3658026"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658026","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658026","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658026","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658026","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103206878","display_name":"C.-M. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chun-Yen Chen","raw_affiliation_strings":["National Taiwan Normal University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0001-8469-9247","affiliations":[{"raw_affiliation_string":"National Taiwan Normal University, Taipei, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018553457","display_name":"Mei-Chen Yeh","orcid":"https://orcid.org/0000-0001-8665-7860"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Mei-Chen Yeh","raw_affiliation_strings":["National Taiwan Normal University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-8665-7860","affiliations":[{"raw_affiliation_string":"National Taiwan Normal University, Taipei, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103206878"],"corresponding_institution_ids":["https://openalex.org/I134161618"],"apc_list":null,"apc_paid":null,"fwci":0.3311,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62711584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"934","last_page":"942"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9965999722480774,"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":0.9965999722480774,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9912999868392944,"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":0.9660999774932861,"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":0.7997737526893616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6848723292350769},{"id":"https://openalex.org/keywords/swap","display_name":"Swap (finance)","score":0.5348559617996216},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5229799747467041},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.49545538425445557},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47821804881095886},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.43008774518966675},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3843550682067871},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.06664401292800903}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997737526893616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6848723292350769},{"id":"https://openalex.org/C99821215","wikidata":"https://www.wikidata.org/wiki/Q1136583","display_name":"Swap (finance)","level":2,"score":0.5348559617996216},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5229799747467041},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.49545538425445557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47821804881095886},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.43008774518966675},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3843550682067871},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.06664401292800903},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3658026","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658026","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658026","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658026","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658026","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658026","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7139107657","display_name":null,"funder_award_id":"110-2634-F-002-050","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"},{"id":"https://openalex.org/G7558381320","display_name":null,"funder_award_id":"111-2221-E-003-016-MY2,110-2634-F-002-050","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418517.pdf","grobid_xml":"https://content.openalex.org/works/W4399418517.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1567302070","https://openalex.org/W1861492603","https://openalex.org/W1999954155","https://openalex.org/W2031489346","https://openalex.org/W2052684427","https://openalex.org/W2117539524","https://openalex.org/W2602247401","https://openalex.org/W2946485437","https://openalex.org/W3109067582","https://openalex.org/W3174396085","https://openalex.org/W4247924304","https://openalex.org/W4312505596","https://openalex.org/W6600076646"],"related_works":["https://openalex.org/W614339039","https://openalex.org/W4230893873","https://openalex.org/W3125166754","https://openalex.org/W2807755437","https://openalex.org/W2509929388","https://openalex.org/W4285328440","https://openalex.org/W4390062853","https://openalex.org/W4389256085","https://openalex.org/W4399290976","https://openalex.org/W4313644201"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"has":[2],"proven":[3],"highly":[4],"effective":[5],"across":[6],"various":[7,119],"tasks,":[8,135],"showcasing":[9],"its":[10,137],"versatility":[11],"in":[12,21,64,93,131,139,148],"different":[13],"applications.":[14],"Despite":[15],"these":[16],"achievements,":[17],"the":[18,115],"challenges":[19],"inherent":[20],"multi-label":[22,35,133],"classification":[23,36,134],"have":[24],"seen":[25],"limited":[26],"attention.":[27],"This":[28],"paper":[29],"introduces":[30],"GAELLE,":[31],"a":[32,48,83,107],"novel":[33],"self-supervised":[34,132],"framework":[37],"that":[38],"simultaneously":[39],"captures":[40,96],"image":[41,71],"context":[42,52],"and":[43,53,90,109,121,146],"object":[44],"information.":[45],"GAELLE":[46,94],"employs":[47],"combination":[49],"of":[50,61,88],"global":[51,67,89,108],"local":[54,74,91,110],"attention":[55,75],"mechanisms":[56],"to":[57],"discern":[58],"diverse":[59],"levels":[60],"semantic":[62],"information":[63],"images.":[65,124,149],"The":[66,86],"component":[68],"comprehensively":[69],"learns":[70],"content":[72],"while":[73],"eliminates":[76],"object-irrelevant":[77],"nuances":[78],"by":[79],"aligning":[80],"embeddings":[81],"with":[82],"projection":[84],"head.":[85],"integration":[87],"features":[92],"effectively":[95],"intricate":[97],"object-scene":[98],"relationships.":[99],"To":[100],"further":[101],"enhance":[102],"this":[103],"capability,":[104],"we":[105],"introduce":[106],"swap":[111],"prediction":[112],"technique,":[113],"facilitating":[114],"nuanced":[116],"interplay":[117],"between":[118,143],"objects":[120,145],"scenes":[122,147],"within":[123],"Experimental":[125],"results":[126],"showcase":[127],"GAELLE's":[128],"state-of-the-art":[129],"performance":[130],"highlighting":[136],"effectiveness":[138],"uncovering":[140],"complex":[141],"relationships":[142],"multiple":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}