{"id":"https://openalex.org/W4396214386","doi":"https://doi.org/10.1109/tcsvt.2024.3395132","title":"CARD: Semantic Segmentation With Efficient Class-Aware Regularized Decoder","display_name":"CARD: Semantic Segmentation With Efficient Class-Aware Regularized Decoder","publication_year":2024,"publication_date":"2024-04-29","ids":{"openalex":"https://openalex.org/W4396214386","doi":"https://doi.org/10.1109/tcsvt.2024.3395132"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3395132","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3395132","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/A5067402751","display_name":"Ye Huang","orcid":"https://orcid.org/0000-0001-5668-5529"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye Huang","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5668-5529","affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007545410","display_name":"Di Kang","orcid":"https://orcid.org/0000-0002-8996-0897"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Kang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-8996-0897","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334644","display_name":"Liang Chen","orcid":"https://orcid.org/0000-0003-0712-4738"},"institutions":[{"id":"https://openalex.org/I111753288","display_name":"Fujian Normal University","ror":"https://ror.org/020azk594","country_code":"CN","type":"education","lineage":["https://openalex.org/I111753288"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Chen","raw_affiliation_strings":["College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0712-4738","affiliations":[{"raw_affiliation_string":"College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou, China","institution_ids":["https://openalex.org/I111753288"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395314","display_name":"Wenjing Jia","orcid":"https://orcid.org/0000-0002-0940-3338"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wenjing Jia","raw_affiliation_strings":["Global Big Data Technologies Centre, University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0940-3338","affiliations":[{"raw_affiliation_string":"Global Big Data Technologies Centre, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006921134","display_name":"Xiangjian He","orcid":"https://orcid.org/0000-0001-8962-540X"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangjian He","raw_affiliation_strings":["School of Computer Science, University of Nottingham Ningbo China, Ningbo, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Nottingham Ningbo China, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080093489","display_name":"Lixin Duan","orcid":"https://orcid.org/0000-0002-0723-4016"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lixin Duan","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0723-4016","affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044236581","display_name":"Xuefei Zhe","orcid":"https://orcid.org/0000-0002-5005-7166"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefei Zhe","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5005-7166","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079937813","display_name":"Linchao Bao","orcid":"https://orcid.org/0000-0001-9543-3754"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Linchao Bao","raw_affiliation_strings":["School of Computer Science, University of Birmingham, Birmingham, U.K","Tencent AI Lab, China"],"raw_orcid":"https://orcid.org/0000-0001-9543-3754","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Birmingham, Birmingham, U.K","institution_ids":["https://openalex.org/I79619799"]},{"raw_affiliation_string":"Tencent AI Lab, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4306,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81994275,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"34","issue":"10","first_page":"9024","last_page":"9038"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","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"}},"topics":[{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7194292545318604},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6224462985992432},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6016669273376465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5565987229347229},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44875723123550415},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.43813759088516235},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.41477036476135254},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3422635793685913},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14141759276390076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7194292545318604},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6224462985992432},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6016669273376465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5565987229347229},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44875723123550415},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.43813759088516235},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.41477036476135254},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3422635793685913},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14141759276390076}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2024.3395132","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3395132","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"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/37087cb7-a8c2-4e5c-a80d-a32dc3b0f1a6","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/37087cb7-a8c2-4e5c-a80d-a32dc3b0f1a6","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Huang , Y , Kang , D , Chen , L , Jia , W , He , X , Duan , L , Zhe , X & Bao , L 2024 , ' CARD : Semantic Segmentation with Efficient Class-Aware Regularized Decoder ' , IEEE Transactions on Circuits and Systems for Video Technology . https://doi.org/10.1109/TCSVT.2024.3395132","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3815549405","display_name":null,"funder_award_id":"2023J01083","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G860262076","display_name":null,"funder_award_id":"61901117","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/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2125215748","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2412782625","https://openalex.org/W2520774990","https://openalex.org/W2531409750","https://openalex.org/W2560023338","https://openalex.org/W2561196672","https://openalex.org/W2565639579","https://openalex.org/W2630837129","https://openalex.org/W2787091153","https://openalex.org/W2884822772","https://openalex.org/W2910628332","https://openalex.org/W2924464923","https://openalex.org/W2943070176","https://openalex.org/W2946948417","https://openalex.org/W2948080074","https://openalex.org/W2955058313","https://openalex.org/W2963091558","https://openalex.org/W2963727650","https://openalex.org/W2981899103","https://openalex.org/W2990775046","https://openalex.org/W2993235622","https://openalex.org/W3014641072","https://openalex.org/W3034355852","https://openalex.org/W3034958977","https://openalex.org/W3035339581","https://openalex.org/W3040304705","https://openalex.org/W3097065222","https://openalex.org/W3122412340","https://openalex.org/W3138516171","https://openalex.org/W3139049060","https://openalex.org/W3159637683","https://openalex.org/W3165745140","https://openalex.org/W3170410460","https://openalex.org/W3170841864","https://openalex.org/W4214520160","https://openalex.org/W4214893857","https://openalex.org/W4225292349","https://openalex.org/W4225827210","https://openalex.org/W4283802055","https://openalex.org/W4297665946","https://openalex.org/W4312422436","https://openalex.org/W4312443924","https://openalex.org/W4312744505","https://openalex.org/W4312815172","https://openalex.org/W4312820606","https://openalex.org/W4312847199","https://openalex.org/W4313303572","https://openalex.org/W4323338514","https://openalex.org/W4367359631","https://openalex.org/W4383112592","https://openalex.org/W4385245566","https://openalex.org/W4386076222","https://openalex.org/W4386076493","https://openalex.org/W4386076522","https://openalex.org/W4393154878","https://openalex.org/W6637373629","https://openalex.org/W6739696289","https://openalex.org/W6760897771","https://openalex.org/W6772853553","https://openalex.org/W6775845032","https://openalex.org/W6791353385","https://openalex.org/W6796761347","https://openalex.org/W6797399245","https://openalex.org/W6802010497","https://openalex.org/W6811002592","https://openalex.org/W6842806116","https://openalex.org/W6846007759","https://openalex.org/W6846529796","https://openalex.org/W6848671364"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2501551404","https://openalex.org/W4385583601","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W2799953226","https://openalex.org/W3204400600","https://openalex.org/W3112772842","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Semantic":[0],"segmentation":[1,219],"has":[2],"recently":[3],"achieved":[4],"notable":[5],"advances":[6],"by":[7,92,101,261],"exploiting":[8],"\u201cclass-level\u201d":[9],"contextual":[10,47],"information":[11,31],"during":[12,88,221],"learning,":[13,39,90],"e.g.,":[14],"the":[15,82,93,169,173,180,184,192,207,250,255],"Object":[16],"Contextual":[17],"Representation":[18],"(OCR)":[19],"and":[20,45,85,129,179,189,225,227,240],"Context":[21],"Prior":[22],"(CPNet)":[23],"approaches.":[24],"However,":[25],"these":[26,50],"approaches":[27,51,273],"simply":[28],"concatenate":[29],"class-level":[30,70],"to":[32,35,64,80,133,216,263],"pixel":[33,37],"features":[34],"boost":[36,254],"representation":[38],"which":[40,61,105,121],"cannot":[41],"fully":[42],"utilize":[43],"intra-class":[44,83],"inter-class":[46,86,187],"information.":[48],"Moreover,":[49,111],"learn":[52],"soft":[53],"class":[54,164,177,193],"centers":[55,188],"based":[56],"on":[57,244,274],"coarse":[58,209],"mask":[59],"prediction,":[60],"is":[62,198],"prone":[63],"error":[65],"accumulation.":[66],"To":[67],"better":[68],"exploit":[69],"information,":[71],"we":[72,112],"propose":[73],"a":[74,114,124,278],"universal":[75],"Class-Aware":[76],"Regularization":[77],"(CAR)":[78],"approach":[79,197],"optimize":[81],"variance":[84],"distance":[87,174,185],"feature":[89],"motivated":[91],"fact":[94],"that":[95,249],"humans":[96],"can":[97,212,228,253],"recognize":[98],"an":[99,130],"object":[100],"itself":[102],"no":[103,234],"matter":[104],"other":[106],"objects":[107],"it":[108],"appears":[109],"with.":[110],"design":[113],"dedicated":[115],"decoder":[116],"for":[117,137],"CAR":[118,150,211,252],"(named":[119],"CARD),":[120],"consists":[122,151],"of":[123,146,152,205,257],"novel":[125,154],"spatial":[126],"token":[127],"mixer":[128],"upsampling":[131],"module,":[132],"maximize":[134],"its":[135],"gain":[136],"existing":[138,218],"baselines":[139],"while":[140],"being":[141],"highly":[142,279],"efficient":[143,280],"in":[144,195],"terms":[145],"computational":[147],"cost.":[148],"Specifically,":[149],"three":[153],"loss":[155,159],"functions.":[156],"The":[157,282],"first":[158],"function":[160],"encourages":[161],"more":[162],"compact":[163],"representations":[165],"within":[166],"each":[167],"class,":[168],"second":[170],"directly":[171,199,214],"maximizes":[172],"between":[175,186],"different":[176],"centers,":[178],"third":[181],"further":[182],"pushes":[183],"pixels.":[190],"Furthermore,":[191],"center":[194],"our":[196],"generated":[200],"from":[201,206],"ground":[202],"truth":[203],"instead":[204],"error-prone":[208],"prediction.":[210],"be":[213,285],"applied":[215],"most":[217],"models":[220,260],"training,":[222],"including":[223],"OCR":[224],"CPNet,":[226],"largely":[229],"improve":[230],"their":[231],"accuracy":[232,256],"at":[233,287],"additional":[235],"inference":[236],"overhead.":[237],"Extensive":[238],"experiments":[239],"ablation":[241],"studies":[242],"conducted":[243],"multiple":[245,275],"benchmark":[246],"datasets":[247],"demonstrate":[248],"proposed":[251],"all":[258],"baseline":[259],"up":[262],"2.23%":[264],"mIOU":[265],"with":[266,277],"superior":[267],"generalization":[268],"ability.":[269],"CARD":[270],"outperforms":[271],"state-of-the-art":[272],"benchmarks":[276],"architecture.":[281],"code":[283],"will":[284],"available":[286],"https://github.com/edwardyehuang/CAR.":[288]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}