{"id":"https://openalex.org/W4372268585","doi":"https://doi.org/10.1109/icassp49357.2023.10095289","title":"Class-Guided Triple Head Prediction Network for Long-Tail Object Detection","display_name":"Class-Guided Triple Head Prediction Network for Long-Tail Object Detection","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372268585","doi":"https://doi.org/10.1109/icassp49357.2023.10095289"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100624008","display_name":"Xuyang Liu","orcid":"https://orcid.org/0000-0002-0103-0098"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuyang Liu","raw_affiliation_strings":["Inner Mongolia University (Huhhot),College of Computer Science,PR China","College of Computer Science, Inner Mongolia University (Huhhot), PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University (Huhhot),College of Computer Science,PR China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University (Huhhot), PR China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072503154","display_name":"Yuan Zheng","orcid":"https://orcid.org/0000-0001-8422-2599"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zheng","raw_affiliation_strings":["Inner Mongolia University (Huhhot),College of Computer Science,PR China","College of Computer Science, Inner Mongolia University (Huhhot), PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University (Huhhot),College of Computer Science,PR China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University (Huhhot), PR China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11438","display_name":"Retinal Imaging and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11438","display_name":"Retinal Imaging and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9979000091552734,"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":0.9898999929428101,"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/discriminative-model","display_name":"Discriminative model","score":0.8555266857147217},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7361618876457214},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.7084943056106567},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6465901136398315},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5981093049049377},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5827322006225586},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5156977772712708},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4551917612552643},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35634845495224}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8555266857147217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7361618876457214},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.7084943056106567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6465901136398315},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5981093049049377},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5827322006225586},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5156977772712708},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4551917612552643},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35634845495224},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2031489346","https://openalex.org/W2132791018","https://openalex.org/W2339172597","https://openalex.org/W2602856279","https://openalex.org/W2884561390","https://openalex.org/W2948672349","https://openalex.org/W2952122856","https://openalex.org/W2963351448","https://openalex.org/W2963691377","https://openalex.org/W2964241181","https://openalex.org/W3034601242","https://openalex.org/W3035552357","https://openalex.org/W3108105109","https://openalex.org/W3166228617","https://openalex.org/W3176346992","https://openalex.org/W6620707391","https://openalex.org/W6763430915","https://openalex.org/W6764733053","https://openalex.org/W6790859549"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"In":[0],"real-world":[1],"scenarios,":[2],"data":[3],"generally":[4],"follows":[5],"a":[6,10,38,59,79,83,89],"long-tail":[7,16,48],"distribution.":[8],"Although":[9],"large":[11],"number":[12],"of":[13,124,149],"works":[14],"on":[15,102,142],"object":[17],"detection":[18],"have":[19],"emerged,":[20],"they":[21],"still":[22],"suffer":[23],"from":[24],"an":[25],"insufficient":[26],"discriminative":[27,71],"learning":[28,104],"for":[29,73,154],"tail":[30],"categories.":[31],"To":[32,76],"alleviate":[33],"this":[34],"problem,":[35],"we":[36,57,81],"devise":[37],"novel":[39,90],"Class-guided":[40],"Triple":[41,60],"Head":[42],"Prediction":[43],"Network":[44],"(CTHNet).":[45],"Considering":[46],"the":[47,122,147],"LVIS":[49,143],"dataset":[50],"contains":[51],"frequent,":[52],"common":[53],"and":[54,87,126,134,139,151],"rare":[55,99,155],"classes,":[56,69],"propose":[58],"Box":[61],"Heads":[62],"(TBH)":[63],"to":[64,95,115],"deal":[65],"with":[66,146],"these":[67],"three":[68],"enhancing":[70],"representations":[72],"all":[74],"classes.":[75],"train":[77],"such":[78],"TBH,":[80],"adopt":[82],"decoupled":[84],"training":[85],"strategy":[86],"introduce":[88],"Generic":[91],"Class-Specific":[92],"Loss":[93],"(GCSL)":[94],"further":[96],"adaptively":[97],"protect":[98],"class":[100],"based":[101],"their":[103],"status.":[105],"Experiments":[106],"indicate":[107],"that":[108],"our":[109,130],"CTHNet":[110,131],"not":[111],"only":[112],"is":[113],"superior":[114],"existing":[116],"methods,":[117],"but":[118],"also":[119],"significantly":[120],"improves":[121,132],"performance":[123],"one-stage":[125],"two-stage":[127],"detectors.":[128],"Specifically,":[129],"RetinaNet":[133],"Faster":[135],"R-CNN":[136],"by":[137],"5.7%":[138],"4%":[140],"mAPs":[141],"0.5,":[144],"especially":[145],"improvements":[148],"12%":[150],"8%":[152],"APs":[153],"class,":[156],"respectively.":[157]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}