{"id":"https://openalex.org/W4415709306","doi":"https://doi.org/10.1109/icme59968.2025.11209185","title":"DuMo: A Dual-Model Framework for Effective Long-tailed Object Detection","display_name":"DuMo: A Dual-Model Framework for Effective Long-tailed Object Detection","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709306","doi":"https://doi.org/10.1109/icme59968.2025.11209185"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5035005750","display_name":"Chenbo Zhang","orcid":"https://orcid.org/0000-0002-4196-5701"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenbo Zhang","raw_affiliation_strings":["Fudan University,Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035989799","display_name":"Yinglu Zhang","orcid":"https://orcid.org/0000-0003-0772-4549"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinglu Zhang","raw_affiliation_strings":["Fudan University,Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086316879","display_name":"Jihong Guan","orcid":"https://orcid.org/0000-0003-2313-7635"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihong Guan","raw_affiliation_strings":["Tongji University,School of Computer Science & Technology,China"],"affiliations":[{"raw_affiliation_string":"Tongji University,School of Computer Science & Technology,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017862559","display_name":"Shuigeng Zhou","orcid":"https://orcid.org/0000-0002-1949-2768"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuigeng Zhou","raw_affiliation_strings":["Fudan University,Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035005750"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34026807,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7459999918937683,"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":0.7459999918937683,"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":0.07240000367164612,"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":0.02449999935925007,"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/overfitting","display_name":"Overfitting","score":0.8518000245094299},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.675000011920929},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5730999708175659},{"id":"https://openalex.org/keywords/long-tail","display_name":"Long tail","score":0.5554999709129333},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5527999997138977},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.534600019454956},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4991999864578247},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.49219998717308044}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8518000245094299},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.675000011920929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6510000228881836},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5730999708175659},{"id":"https://openalex.org/C15189868","wikidata":"https://www.wikidata.org/wiki/Q534685","display_name":"Long tail","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5527999997138977},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.534600019454956},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4991999864578247},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.49219998717308044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48579999804496765},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.4650999903678894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46000000834465027},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3458000123500824},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C2781289151","wikidata":"https://www.wikidata.org/wiki/Q2903989","display_name":"Class hierarchy","level":3,"score":0.2870999872684479},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2023060295","https://openalex.org/W2031489346","https://openalex.org/W2194775991","https://openalex.org/W2749908420","https://openalex.org/W2948672349","https://openalex.org/W2962898354","https://openalex.org/W2963150697","https://openalex.org/W3034933032","https://openalex.org/W3035552357","https://openalex.org/W3088982929","https://openalex.org/W3093220398","https://openalex.org/W3108105109","https://openalex.org/W3166228617","https://openalex.org/W3166898278","https://openalex.org/W3172971995","https://openalex.org/W3182635745","https://openalex.org/W4312577413","https://openalex.org/W4312923558","https://openalex.org/W4313162605","https://openalex.org/W4386078160","https://openalex.org/W4390871665","https://openalex.org/W4390873226","https://openalex.org/W4391305686","https://openalex.org/W4392903013","https://openalex.org/W4393153493"],"related_works":[],"abstract_inverted_index":{"Real-world":[0],"data":[1,42,63],"often":[2],"exhibits":[3],"a":[4,55,70,104,111,126,154,177],"long-tailed":[5,13],"distribution,":[6],"which":[7,75,159,188],"fuels":[8],"growing":[9],"research":[10],"interest":[11],"in":[12,32],"object":[14],"detection":[15,199],"(LTOD)":[16],"from":[17,173,184],"both":[18,60],"academia":[19],"and":[20,51,65,84,110,123,196,208],"industry.":[21],"However,":[22],"existing":[23],"methods":[24],"primarily":[25],"focus":[26],"on":[27,48,193,205],"the":[28,35,77,96,140,145,161,165,171,211,214],"head-tail":[29,66,150],"imbalance":[30,67,151],"issue":[31,38],"LTOD,":[33],"neglecting":[34],"more":[36],"critical":[37],"of":[39,103,213],"tail":[40,49,61,105,121,127,141,167,194],"class":[41,62,98,106,128,142],"scarcity.":[43],"This":[44,57],"leads":[45],"to":[46,91,118,138,186],"overfitting":[47],"classes":[50,195],"poor":[52],"performance":[53,94,192],"as":[54],"whole.":[56],"paper":[58],"addresses":[59],"scarcity":[64],"by":[68,80,88,125,152],"proposing":[69],"Dual-Model":[71],"framework":[72],"named":[73],"DuMo,":[74],"tackles":[76],"two":[78,81],"challenges":[79],"separate":[82],"models,":[83],"then":[85],"merges":[86],"them":[87],"knowledge":[89,178],"transfer":[90,179],"ensure":[92],"superior":[93],"across":[95,200],"entire":[97],"space.":[99],"Specifically,":[100],"DuMo":[101],"consists":[102],"expert":[107],"model":[108,113],"(EM)":[109],"base":[112],"(BM).":[114],"EM":[115,185],"is":[116],"dedicated":[117],"detecting":[119],"scarce":[120],"classes,":[122,168],"enhanced":[124],"feature":[129],"augmentation":[130],"(TCFA)":[131],"module":[132,181],"that":[133],"uses":[134],"CLIP-generated":[135],"semantic":[136],"embeddings":[137],"diversify":[139],"features.":[143],"On":[144],"other":[146],"hand,":[147],"BM":[148],"handles":[149],"employing":[153],"class-specific":[155],"margin":[156],"loss":[157],"(CSML),":[158],"moves":[160],"decision":[162],"boundary":[163],"toward":[164],"underrepresented":[166],"thus":[169],"reducing":[170],"suppression":[172],"head":[174],"classes.":[175,202],"Finally,":[176],"(KT)":[180],"transfers":[182],"expertise":[183],"BM,":[187],"further":[189],"enhances":[190],"BM\u2019s":[191],"ensures":[197],"robust":[198],"all":[201],"Extensive":[203],"experiments":[204],"LVIS":[206],"v1.0":[207],"LVIS-X":[209],"validate":[210],"effectiveness":[212],"proposed":[215],"method":[216],"DuMo.":[217]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}