{"id":"https://openalex.org/W4406890911","doi":"https://doi.org/10.1109/tmm.2025.3535395","title":"Towards Gradient Equalization and Feature Diversification for Long-Tailed Multi-Label Image Recognition","display_name":"Towards Gradient Equalization and Feature Diversification for Long-Tailed Multi-Label Image Recognition","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406890911","doi":"https://doi.org/10.1109/tmm.2025.3535395"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3535395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535395","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5065549500","display_name":"Zhao-Min Chen","orcid":"https://orcid.org/0000-0001-9492-0796"},"institutions":[{"id":"https://openalex.org/I146620803","display_name":"Wenzhou University","ror":"https://ror.org/020hxh324","country_code":"CN","type":"education","lineage":["https://openalex.org/I146620803"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao-Min Chen","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China","National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9492-0796","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China","institution_ids":["https://openalex.org/I146620803"]},{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011432617","display_name":"Quan Cui","orcid":"https://orcid.org/0000-0003-3428-4913"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Quan Cui","raw_affiliation_strings":["Graduate School of Information, Production and Systems, Waseda University, Fukuoka, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3428-4913","affiliations":[{"raw_affiliation_string":"Graduate School of Information, Production and Systems, Waseda University, Fukuoka, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699785","display_name":"Xiaoqin Zhang","orcid":"https://orcid.org/0000-0003-0958-7285"},"institutions":[{"id":"https://openalex.org/I146620803","display_name":"Wenzhou University","ror":"https://ror.org/020hxh324","country_code":"CN","type":"education","lineage":["https://openalex.org/I146620803"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqin Zhang","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0958-7285","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China","institution_ids":["https://openalex.org/I146620803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004212956","display_name":"Ruoxi Deng","orcid":"https://orcid.org/0000-0001-5912-0152"},"institutions":[{"id":"https://openalex.org/I146620803","display_name":"Wenzhou University","ror":"https://ror.org/020hxh324","country_code":"CN","type":"education","lineage":["https://openalex.org/I146620803"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruoxi Deng","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China","institution_ids":["https://openalex.org/I146620803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017674477","display_name":"Chaoqun Xia","orcid":"https://orcid.org/0000-0002-0167-0423"},"institutions":[{"id":"https://openalex.org/I146620803","display_name":"Wenzhou University","ror":"https://ror.org/020hxh324","country_code":"CN","type":"education","lineage":["https://openalex.org/I146620803"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoqun Xia","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0167-0423","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China","institution_ids":["https://openalex.org/I146620803"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023507910","display_name":"Shijian Lu","orcid":"https://orcid.org/0000-0002-6766-2506"},"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":"Shijian Lu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-6766-2506","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, 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":3.1769,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.91532307,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"27","issue":null,"first_page":"3489","last_page":"3500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9498999714851379,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9498999714851379,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9196000099182129,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9018999934196472,"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":0.7740717530250549},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6083447933197021},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.555212676525116},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5220303535461426},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4702310264110565},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46266961097717285},{"id":"https://openalex.org/keywords/diversification","display_name":"Diversification (marketing strategy)","score":0.455564022064209},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43914666771888733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7740717530250549},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6083447933197021},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.555212676525116},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5220303535461426},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4702310264110565},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46266961097717285},{"id":"https://openalex.org/C180916674","wikidata":"https://www.wikidata.org/wiki/Q3711935","display_name":"Diversification (marketing strategy)","level":2,"score":0.455564022064209},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43914666771888733},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2025.3535395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535395","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/218091","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/218091","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G131960074","display_name":null,"funder_award_id":"62201401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G133414184","display_name":null,"funder_award_id":"U2033210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1549599755","display_name":"\u57fa\u4e8e\u7ea2\u5916\u9065\u611f\u7684\u5149\u4f0f\u7ec4\u4ef6\u70ed\u6591\u667a\u80fd\u68c0\u6d4b\u4e0e\u8bc6\u522b\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"LQ23F020003","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G2119780399","display_name":null,"funder_award_id":"62202337","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6130558414","display_name":"\u590d\u6742\u8de8\u6a21\u6001\u8868\u5f81\u7684\u5173\u8054\u5206\u6790\u4e0e\u56e0\u679c\u8868\u793a\u65b9\u6cd5","funder_award_id":"LDT23F02024F02","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G7135619476","display_name":null,"funder_award_id":"U24A20242","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/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2108598243","https://openalex.org/W2116750654","https://openalex.org/W2194775991","https://openalex.org/W2339172597","https://openalex.org/W2440599146","https://openalex.org/W2736688973","https://openalex.org/W2738853914","https://openalex.org/W2792765514","https://openalex.org/W2795282075","https://openalex.org/W2798405286","https://openalex.org/W2932399282","https://openalex.org/W2962933664","https://openalex.org/W2963076818","https://openalex.org/W2963300078","https://openalex.org/W2963351448","https://openalex.org/W2963691377","https://openalex.org/W2963875806","https://openalex.org/W2982083293","https://openalex.org/W2982112268","https://openalex.org/W2998496429","https://openalex.org/W3000675402","https://openalex.org/W3009073662","https://openalex.org/W3034601242","https://openalex.org/W3036328963","https://openalex.org/W3094967083","https://openalex.org/W3095707208","https://openalex.org/W3095809828","https://openalex.org/W3099518117","https://openalex.org/W3135745701","https://openalex.org/W3163811911","https://openalex.org/W3166798381","https://openalex.org/W3167456680","https://openalex.org/W3179096061","https://openalex.org/W3184090563","https://openalex.org/W3192931333","https://openalex.org/W3202884348","https://openalex.org/W3208922547","https://openalex.org/W4220813865","https://openalex.org/W4298326794","https://openalex.org/W4312884841","https://openalex.org/W4313479813","https://openalex.org/W4383709761","https://openalex.org/W6726873649","https://openalex.org/W6760201928","https://openalex.org/W6764733053"],"related_works":["https://openalex.org/W2601157893","https://openalex.org/W2373006798","https://openalex.org/W2131735617","https://openalex.org/W2056912418","https://openalex.org/W2033213769","https://openalex.org/W4312376745","https://openalex.org/W2136016640","https://openalex.org/W2049538278","https://openalex.org/W2886173746","https://openalex.org/W4200043248"],"abstract_inverted_index":{"Multi-label":[0],"image":[1,20,55],"recognition":[2,21,56],"with":[3,177],"convolutional":[4],"neural":[5],"networks":[6],"has":[7],"achieved":[8],"remarkable":[9],"progress":[10],"in":[11],"the":[12,25,46,65,86,97,123,130,142,148,158,161,170,192,195],"past":[13],"few":[14,40],"years.":[15],"However,":[16],"most":[17,33],"existing":[18,53,66],"multi-label":[19,54],"methods":[22,67,179],"suffer":[23],"from":[24,150],"long-tailed":[26,49],"data":[27,50,111],"distribution":[28,51],"problem,i.e.,":[29],"head":[30,75],"categories":[31],"occupy":[32],"training":[34,93],"samples,":[35],"while":[36],"tailed":[37,77],"classes":[38],"have":[39],"samples.":[41,94],"This":[42],"work":[43],"firstly":[44],"studies":[45,187],"influence":[47],"of":[48,64,88,90,163,194],"on":[52,59,180],"methods.":[57],"Based":[58],"this,":[60],"two":[61],"crucial":[62],"issues":[63],"are":[68,83,188],"identified:":[69],"1)":[70],"severe":[71],"gradient":[72,116,124],"imbalance":[73],"between":[74],"and":[76,173,182],"categories,":[78,146],"even":[79],"though":[80],"re-balancing":[81],"strategies":[82],"adopted;":[84],"2)":[85],"lack":[87],"diversity":[89,137],"tail":[91,152],"category":[92],"To":[95,128],"tackle":[96,129],"first":[98],"issue,":[99,132],"this":[100,133],"paper":[101,134],"proposes":[102,135],"a":[103,114,136],"group":[104],"sampling":[105],"strategy":[106],"to":[107,121,140,190],"create":[108],"group-wise":[109],"balanced":[110],"distribution.":[112],"Meanwhile,":[113],"dynamic":[115],"balancing":[117],"loss":[118],"is":[119],"proposed":[120],"equalize":[122],"for":[125],"all":[126,145],"categories.":[127],"second":[131],"enhancement":[138],"module":[139],"fuse":[141],"information":[143],"across":[144],"preventing":[147],"network":[149],"overfitting":[151],"classes.":[153],"Furthermore,":[154],"it":[155],"also":[156],"balances":[157],"gradient,":[159],"promoting":[160],"discriminability":[162],"learned":[164],"classifiers.":[165],"Our":[166],"method":[167,172],"significantly":[168],"outperforms":[169],"baseline":[171],"achieves":[174],"competitive":[175],"performance":[176],"state-of-the-art":[178],"VOC-LT":[181],"COCO-LT":[183],"datasets.":[184],"Extensive":[185],"ablation":[186],"conducted":[189],"verify":[191],"effectiveness":[193],"essential":[196],"proposals.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}