{"id":"https://openalex.org/W4407638343","doi":"https://doi.org/10.1109/tmm.2025.3543084","title":"Constructing Balanced Training Samples: A New Perspective on Long-Tailed Classification","display_name":"Constructing Balanced Training Samples: A New Perspective on Long-Tailed Classification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407638343","doi":"https://doi.org/10.1109/tmm.2025.3543084"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3543084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3543084","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/A5006250085","display_name":"Wenyi Zhao","orcid":"https://orcid.org/0000-0002-8339-5081"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenyi Zhao","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114910368","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-6601-9148"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332402","display_name":"Yuhan Li","orcid":"https://orcid.org/0000-0003-1324-5819"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhan Li","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079130579","display_name":"Lu Yang","orcid":"https://orcid.org/0000-0003-3857-3982"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Yang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100311730","display_name":"Zhenhao Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhao Liang","raw_affiliation_strings":["Beijing Normal University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077221055","display_name":"Enwen Hu","orcid":"https://orcid.org/0000-0001-5019-3961"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enwen Hu","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428758","display_name":"Weidong Zhang","orcid":"https://orcid.org/0000-0003-2495-4469"},"institutions":[{"id":"https://openalex.org/I4210163247","display_name":"Henan Institute of Science and Technology","ror":"https://ror.org/0578f1k82","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163247"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Zhang","raw_affiliation_strings":["School of Information Engineering, Henan Institute of Science and Technology, Xinxiang, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Henan Institute of Science and Technology, Xinxiang, China","institution_ids":["https://openalex.org/I4210163247"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068323815","display_name":"Huihua Yang","orcid":"https://orcid.org/0000-0001-6334-4044"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huihua Yang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5006250085"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":18.0155,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98888432,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"27","issue":null,"first_page":"5130","last_page":"5143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.27649998664855957,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.27649998664855957,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8138867616653442},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6103804111480713},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5561662912368774},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5106917023658752},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.434684157371521},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3225862383842468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8138867616653442},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6103804111480713},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5561662912368774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5106917023658752},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.434684157371521},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3225862383842468},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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:10.1109/tmm.2025.3543084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3543084","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4513028780","display_name":null,"funder_award_id":"62403066","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2797977484","https://openalex.org/W2962933664","https://openalex.org/W2963691377","https://openalex.org/W2992308087","https://openalex.org/W3034601242","https://openalex.org/W3035524453","https://openalex.org/W3125815192","https://openalex.org/W3145450063","https://openalex.org/W3176009670","https://openalex.org/W3194146976","https://openalex.org/W3196349267","https://openalex.org/W3215720729","https://openalex.org/W4214718285","https://openalex.org/W4226197276","https://openalex.org/W4285295127","https://openalex.org/W4285295719","https://openalex.org/W4292241799","https://openalex.org/W4292347999","https://openalex.org/W4306386459","https://openalex.org/W4312244159","https://openalex.org/W4312592425","https://openalex.org/W4312659823","https://openalex.org/W4312866014","https://openalex.org/W4312877479","https://openalex.org/W4312910036","https://openalex.org/W4312986563","https://openalex.org/W4313151233","https://openalex.org/W4361799030","https://openalex.org/W4366148216","https://openalex.org/W4377235500","https://openalex.org/W4385212332","https://openalex.org/W4385268901","https://openalex.org/W4385695913","https://openalex.org/W4385805163","https://openalex.org/W4386065716","https://openalex.org/W4386065868","https://openalex.org/W4386071546","https://openalex.org/W4386072089","https://openalex.org/W4386076287","https://openalex.org/W4386076395","https://openalex.org/W4386078160","https://openalex.org/W4386702786","https://openalex.org/W4390873427","https://openalex.org/W4390873567","https://openalex.org/W4390874449","https://openalex.org/W4390889781","https://openalex.org/W4391305686","https://openalex.org/W4391537734","https://openalex.org/W4392122189","https://openalex.org/W4399168442","https://openalex.org/W4401671282","https://openalex.org/W4402389270","https://openalex.org/W4402715941","https://openalex.org/W4402727605","https://openalex.org/W4402727938","https://openalex.org/W4402753620","https://openalex.org/W4402753758","https://openalex.org/W4403791223"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"The":[0],"most":[1],"significant":[2],"characteristic":[3],"of":[4,26,37,64,82,101,126,135,141,169],"long-tailed":[5,24,77,127],"classification":[6],"is":[7,86],"that":[8],"severe":[9],"sample":[10,53],"imbalance":[11],"causes":[12],"the":[13,19,23,35,45,62,83,99,110,124,132,139,167],"model":[14,158],"to":[15,55,60,73,88,108,113],"be":[16],"biased":[17],"towards":[18],"head":[20],"category.":[21],"While":[22],"distribution":[25,128],"multimedia":[27],"dataset":[28],"remains":[29],"a":[30,52,69],"constant,":[31],"we":[32],"can":[33],"enhance":[34,61],"acquisition":[36,63],"balanced":[38,57,103,111,136],"training":[39,58],"samples":[40,59,90,104],"and":[41,67,105,152],"corresponding":[42],"features":[43,112,137],"during":[44],"learning":[46,125],"process.":[47],"This":[48,119],"paper":[49],"innovatively":[50],"designs":[51],"provider":[54],"construct":[56],"comprehensive":[65],"features,":[66],"proposes":[68],"Siamese-based":[70],"parameter-sharing":[71],"framework":[72],"handle":[74],"data":[75],"with":[76,91,180],"distributions.":[78],"Specifically,":[79,172],"one":[80],"branch":[81,97],"Siamese":[84],"network":[85],"introduced":[87],"classify":[89],"conventional":[92],"random":[93],"cropping":[94],"sampling,":[95],"another":[96],"integrates":[98],"advantages":[100],"constructed":[102],"hybrid":[106],"optimization":[107],"capture":[109],"identify":[114],"more":[115],"precise":[116],"category":[117],"boundaries.":[118],"combination":[120],"not":[121,159],"only":[122,160],"facilitates":[123],"but":[129,164],"also":[130,165],"strengthens":[131],"model's":[133],"extraction":[134],"through":[138],"incorporation":[140],"contrastive":[142],"learning.":[143],"Most":[144],"significantly,":[145],"extensive":[146],"experiments":[147],"on":[148,178],"CIFAR10-LT,":[149],"CIFAR100-LT,":[150],"ImageNet-LT":[151,179],"iNaturalist":[153],"2018":[154],"datasets":[155],"demonstrate":[156],"our":[157,173],"achieves":[161,175],"superior":[162],"performance":[163],"retains":[166],"benefits":[168],"end-to-end":[170,182],"training.":[171],"method":[174],"60.7%":[176],"accuracy":[177],"an":[181],"ResNeXt-50":[183],"backbone.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}