{"id":"https://openalex.org/W4399310901","doi":"https://doi.org/10.1109/tcsvt.2024.3408256","title":"Semantic-Guided Representation Enhancement for Multi-Label Image Classification","display_name":"Semantic-Guided Representation Enhancement for Multi-Label Image Classification","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4399310901","doi":"https://doi.org/10.1109/tcsvt.2024.3408256"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3408256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3408256","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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":"https://openalex.org/A5076214561","display_name":"Xuelin Zhu","orcid":"https://orcid.org/0000-0001-7676-2843"},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["BD","CN"],"is_corresponding":false,"raw_author_name":"Xuelin Zhu","raw_affiliation_strings":["Jiangsu Provincial Key Laboratory of Computer Network Technology and the School of Cyber Science and Engineering, Southeast University, Nanjing, China","Jiangsu Provincial Key Laboratory of Computer Network Technology, and the School of Cyber Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7676-2843","affiliations":[{"raw_affiliation_string":"Jiangsu Provincial Key Laboratory of Computer Network Technology and the School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I4210090971","https://openalex.org/I76569877"]},{"raw_affiliation_string":"Jiangsu Provincial Key Laboratory of Computer Network Technology, and the School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101478393","display_name":"Jianshu Li","orcid":"https://orcid.org/0000-0001-8554-6886"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianshu Li","raw_affiliation_strings":["Ant Group Company Ltd., Hangzhou, China","Ant Group Co. Ltd, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8554-6886","affiliations":[{"raw_affiliation_string":"Ant Group Company Ltd., Hangzhou, China","institution_ids":[]},{"raw_affiliation_string":"Ant Group Co. Ltd, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012384188","display_name":"Jiuxin Cao","orcid":"https://orcid.org/0000-0002-2448-6717"},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["BD","CN"],"is_corresponding":false,"raw_author_name":"Jiuxin Cao","raw_affiliation_strings":["Jiangsu Provincial Key Laboratory of Computer Network Technology and the School of Cyber Science and Engineering, Southeast University, Nanjing, China","Jiangsu Provincial Key Laboratory of Computer Network Technology, and the School of Cyber Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2448-6717","affiliations":[{"raw_affiliation_string":"Jiangsu Provincial Key Laboratory of Computer Network Technology and the School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I4210090971","https://openalex.org/I76569877"]},{"raw_affiliation_string":"Jiangsu Provincial Key Laboratory of Computer Network Technology, and the School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070291038","display_name":"Dongqi Tang","orcid":"https://orcid.org/0000-0001-6311-2550"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongqi Tang","raw_affiliation_strings":["Ant Group Company Ltd., Hangzhou, China","Ant Group Co. Ltd, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6311-2550","affiliations":[{"raw_affiliation_string":"Ant Group Company Ltd., Hangzhou, China","institution_ids":[]},{"raw_affiliation_string":"Ant Group Co. Ltd, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jian Liu","orcid":"https://orcid.org/0000-0002-5323-5343"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Liu","raw_affiliation_strings":["Ant Group Company Ltd., Hangzhou, China","Ant Group Co. Ltd, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5323-5343","affiliations":[{"raw_affiliation_string":"Ant Group Company Ltd., Hangzhou, China","institution_ids":[]},{"raw_affiliation_string":"Ant Group Co. Ltd, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100461575","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0001-5209-9063"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5209-9063","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8424,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.96558103,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"34","issue":"10","first_page":"10036","last_page":"10049"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9684000015258789,"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":0.9684000015258789,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9332000017166138,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.6790531873703003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6009801030158997},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5420833826065063},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.458027184009552},{"id":"https://openalex.org/keywords/image-enhancement","display_name":"Image enhancement","score":0.4561026692390442},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45607689023017883},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.42175647616386414},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4215601980686188},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41501760482788086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6790531873703003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6009801030158997},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5420833826065063},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.458027184009552},{"id":"https://openalex.org/C3017601658","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image enhancement","level":3,"score":0.4561026692390442},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45607689023017883},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.42175647616386414},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4215601980686188},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41501760482788086},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3408256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3408256","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1019060874","display_name":null,"funder_award_id":"BK20191258","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G2696649687","display_name":null,"funder_award_id":"19@ZH014","funder_id":"https://openalex.org/F4320335869","funder_display_name":"National Social Science Fund of China"},{"id":"https://openalex.org/G3070022028","display_name":null,"funder_award_id":"62172090","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4985914335","display_name":null,"funder_award_id":"2021QY2102","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5988281228","display_name":null,"funder_award_id":"62172089","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7533705064","display_name":null,"funder_award_id":"61972087","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G99284421","display_name":null,"funder_award_id":"62106045","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/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","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/F4320335869","display_name":"National Social Science Fund of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1567302070","https://openalex.org/W1861492603","https://openalex.org/W1962468782","https://openalex.org/W2007972815","https://openalex.org/W2031489346","https://openalex.org/W2064675550","https://openalex.org/W2103117377","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2410641892","https://openalex.org/W2521365688","https://openalex.org/W2560096627","https://openalex.org/W2736688973","https://openalex.org/W2808862089","https://openalex.org/W2890153145","https://openalex.org/W2932399282","https://openalex.org/W2943563866","https://openalex.org/W2963300078","https://openalex.org/W2963351448","https://openalex.org/W2963676620","https://openalex.org/W2963745697","https://openalex.org/W2963875806","https://openalex.org/W2964015378","https://openalex.org/W2966628364","https://openalex.org/W2982112268","https://openalex.org/W2997136715","https://openalex.org/W2998420437","https://openalex.org/W3034472074","https://openalex.org/W3035665101","https://openalex.org/W3035682985","https://openalex.org/W3096609285","https://openalex.org/W3099518117","https://openalex.org/W3120129399","https://openalex.org/W3138516171","https://openalex.org/W3165181705","https://openalex.org/W3167456680","https://openalex.org/W3189532445","https://openalex.org/W3192931333","https://openalex.org/W3202884348","https://openalex.org/W3205618423","https://openalex.org/W3211407538","https://openalex.org/W4214673031","https://openalex.org/W4214893857","https://openalex.org/W4220813865","https://openalex.org/W4304080876","https://openalex.org/W4366493098","https://openalex.org/W4380032284","https://openalex.org/W4381735275","https://openalex.org/W4385245566","https://openalex.org/W4390874143","https://openalex.org/W4393197066","https://openalex.org/W6620707391","https://openalex.org/W6630792627","https://openalex.org/W6713507025","https://openalex.org/W6728881024","https://openalex.org/W6743428213","https://openalex.org/W6749845547","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6780449859","https://openalex.org/W6796992224","https://openalex.org/W6798610236","https://openalex.org/W6798617289","https://openalex.org/W6850625674"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2795079307","https://openalex.org/W2793058541","https://openalex.org/W1983629434","https://openalex.org/W2055929693","https://openalex.org/W2949816130","https://openalex.org/W2138806349","https://openalex.org/W4362679294","https://openalex.org/W4375869153","https://openalex.org/W2372267477"],"abstract_inverted_index":{"Multi-label":[0],"image":[1],"classification":[2],"is":[3,60],"an":[4,117,136],"essential":[5],"yet":[6],"challenging":[7,62],"task":[8],"that":[9,121,140,189],"requires":[10],"to":[11,24,144],"recognize":[12],"multiple":[13],"objects":[14,162],"of":[15,80,112,161,183],"images.":[16],"To":[17],"this":[18,87,153],"end,":[19],"recent":[20],"studies":[21],"have":[22,44],"sought":[23],"acquire":[25],"visual":[26],"representations":[27,71,99,102,131,143,147,173],"for":[28,39,63,83,103,123,132],"each":[29,133],"label":[30,84,105,184],"by":[31,175,196],"attention":[32,65,119,138],"models,":[33],"and":[34,128,158,200,211,217],"then":[35],"train":[36],"binary":[37],"classifiers":[38],"prediction.":[40],"However,":[41],"these":[42],"methods":[43,195],"two":[45,57,113],"major":[46],"drawbacks:":[47],"1)":[48,116],"They":[49,68],"rely":[50],"heavily":[51],"on":[52,149,171,204,221],"the":[53,108,176,181,193],"precise":[54],"alignments":[55],"between":[56],"modalities,":[58],"which":[59,77,96],"still":[61],"current":[64],"models;":[66],"2)":[67,135],"ignore":[69],"patch-level":[70,98],"rich":[72],"in":[73,202],"local":[74,156],"object":[75,126,142],"features,":[76],"are":[78,163,219],"also":[79],"great":[81],"importance":[82],"recognition.":[85,106,185],"In":[86,152],"paper,":[88],"we":[89],"propose":[90],"a":[91],"semantic-guided":[92],"representation":[93],"enhancement":[94],"framework,":[95],"augments":[97],"with":[100],"object-level":[101,130,172],"robust":[104],"Concretely,":[107],"proposed":[109],"framework":[110,191],"consists":[111],"significant":[114],"components:":[115],"inter-modal":[118,177],"module":[120,139],"accounts":[122],"coarsely":[124],"locating":[125],"regions":[127],"producing":[129],"label;":[134],"intra-modal":[137],"aggregates":[141],"enhance":[145],"patch":[146],"based":[148],"their":[150],"correlations.":[151],"way,":[154],"both":[155],"clues":[157],"global":[159],"glances":[160],"fully":[164],"exploited":[165],"simultaneously,":[166],"rather":[167],"than":[168],"relying":[169],"solely":[170],"obtained":[174],"attention,":[178],"thus":[179],"improving":[180],"performance":[182],"Experimental":[186],"results":[187],"show":[188],"our":[190],"outperforms":[192],"state-of-the-art":[194],"0.5%,":[197],"0.6%,":[198],"0.7%":[199],"0.8%":[201],"mAP":[203],"Pascal":[205],"VOC":[206],"2007,":[207],"Microsoft":[208],"COCO,":[209],"NUS-WIDE":[210],"Visual":[212],"Genome":[213],"datasets,":[214],"respectively.":[215],"Codes":[216],"models":[218],"available":[220],"https://github.com/jasonseu/SGRE.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}