{"id":"https://openalex.org/W4405785224","doi":"https://doi.org/10.1109/iros58592.2024.10801350","title":"PCT: Perspective Cue Training Framework for Multi-Camera BEV Segmentation","display_name":"PCT: Perspective Cue Training Framework for Multi-Camera BEV Segmentation","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785224","doi":"https://doi.org/10.1109/iros58592.2024.10801350"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5023048142","display_name":"Haruya Ishikawa","orcid":"https://orcid.org/0000-0003-1494-3635"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haruya Ishikawa","raw_affiliation_strings":["Keio University,Department of Electrical Engineering,Yokohama,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University,Department of Electrical Engineering,Yokohama,Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034912826","display_name":"Takumi Iida","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takumi Iida","raw_affiliation_strings":["SenseTime Japan,Kyoto,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Japan,Kyoto,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111747340","display_name":"Yoshinori Konishi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoshinori Konishi","raw_affiliation_strings":["SenseTime Japan,Kyoto,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Japan,Kyoto,Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070908826","display_name":"Yoshimitsu Aoki","orcid":"https://orcid.org/0000-0001-7361-0027"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshimitsu Aoki","raw_affiliation_strings":["Keio University,Department of Electrical Engineering,Yokohama,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University,Department of Electrical Engineering,Yokohama,Japan","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9155,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79401214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"13253","last_page":"13260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.7667999863624573,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.7667999863624573,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.8056084513664246},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7165735363960266},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6075167059898376},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5746854543685913},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5261789560317993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5120849609375},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.487868070602417},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.04199719429016113}],"concepts":[{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.8056084513664246},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7165735363960266},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6075167059898376},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5746854543685913},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5261789560317993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5120849609375},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.487868070602417},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.04199719429016113},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2340897893","https://openalex.org/W2431874326","https://openalex.org/W2593768305","https://openalex.org/W2884822772","https://openalex.org/W2962687275","https://openalex.org/W2964309882","https://openalex.org/W2990231018","https://openalex.org/W2992308087","https://openalex.org/W3034627419","https://openalex.org/W3035294798","https://openalex.org/W3035564946","https://openalex.org/W3035574168","https://openalex.org/W3035680157","https://openalex.org/W3109395584","https://openalex.org/W3172507542","https://openalex.org/W3217147624","https://openalex.org/W4312641958","https://openalex.org/W4312815172","https://openalex.org/W4319300669","https://openalex.org/W4382464460","https://openalex.org/W4383066393","https://openalex.org/W4386075981","https://openalex.org/W4386076701","https://openalex.org/W4389665489","https://openalex.org/W4394593077","https://openalex.org/W4401414637","https://openalex.org/W4401416042","https://openalex.org/W4402727359","https://openalex.org/W4402976603","https://openalex.org/W6637618735","https://openalex.org/W6674330103","https://openalex.org/W6683633756","https://openalex.org/W6733814495","https://openalex.org/W6743428213","https://openalex.org/W6773005947","https://openalex.org/W6776411772","https://openalex.org/W6797399245","https://openalex.org/W6801880476","https://openalex.org/W6839067270","https://openalex.org/W6851890368"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2018871932","https://openalex.org/W2997094352","https://openalex.org/W641279757","https://openalex.org/W370975646","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Generating":[0],"annotations":[1],"for":[2,123,153,175],"bird\u2019s-eye-view":[3],"(BEV)":[4],"segmentation":[5,59,81,105],"presents":[6],"significant":[7,170],"challenges":[8,26],"due":[9],"to":[10,73,88,112],"the":[11,15,29,37,74,79,85,92,184],"scenes\u2019":[12],"complexity":[13],"and":[14,110,127,142,166,177],"high":[16],"manual":[17],"annotation":[18],"cost.":[19],"In":[20,117],"this":[21,118],"work,":[22],"we":[23,120,133],"address":[24],"these":[25],"by":[27],"leveraging":[28],"abundance":[30],"of":[31],"unlabeled":[32,52,86],"data":[33,87],"available.":[34],"We":[35],"propose":[36],"Perspective":[38],"Cue":[39],"Training":[40],"(PCT)":[41],"framework,":[42],"a":[43,68],"novel":[44],"training":[45],"framework":[46],"that":[47],"utilizes":[48],"pseudo-labels":[49],"generated":[50,93],"from":[51],"perspective":[53,69],"images":[54],"using":[55,157],"publicly":[56],"available":[57],"semantic":[58],"models":[60],"trained":[61,90],"on":[62],"large":[63],"street-view":[64],"datasets.":[65],"PCT":[66,107,122],"applies":[67],"view":[70],"task":[71],"head":[72],"image":[75,96],"encoder":[76],"shared":[77],"with":[78,91],"BEV":[80,104,115,146],"head,":[82],"effectively":[83],"utilizing":[84],"be":[89],"pseudo-labels.":[94],"Since":[95],"encoders":[97],"are":[98,151],"present":[99],"in":[100],"nearly":[101],"all":[102],"camera-based":[103],"architectures,":[106],"is":[108,164],"flexible":[109,167],"applicable":[111],"various":[113,173],"existing":[114],"architectures.":[116],"paper,":[119],"applied":[121],"semi-supervised":[124],"learning":[125],"(SSL)":[126],"unsupervised":[128],"domain":[129],"adaptation":[130],"(UDA).":[131],"Additionally,":[132],"introduce":[134],"strong":[135],"input":[136],"perturbation":[137,144],"through":[138],"Camera":[139],"Dropout":[140,148],"(CamDrop)":[141],"feature":[143],"via":[145],"Feature":[147],"(BFD),":[149],"which":[150],"crucial":[152],"enhancing":[154],"SSL":[155,176],"capabilities":[156],"our":[158],"teacher-student":[159],"framework.":[160],"Our":[161],"comprehensive":[162],"approach":[163],"simple":[165],"but":[168],"yields":[169],"improvements":[171],"over":[172],"baselines":[174],"UDA,":[178],"achieving":[179],"competitive":[180],"performances":[181],"even":[182],"against":[183],"current":[185],"state-of-the-art.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}