{"id":"https://openalex.org/W4405784954","doi":"https://doi.org/10.1109/iros58592.2024.10801357","title":"Progressive Query Refinement Framework for Bird's-Eye-View Semantic Segmentation from Surrounding Images","display_name":"Progressive Query Refinement Framework for Bird's-Eye-View Semantic Segmentation from Surrounding Images","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405784954","doi":"https://doi.org/10.1109/iros58592.2024.10801357"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801357","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":"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/A5103019452","display_name":"Dooseop Choi","orcid":"https://orcid.org/0000-0003-0150-7017"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dooseop Choi","raw_affiliation_strings":["ETRI,Superintelligence Creative Research Laboratory,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETRI,Superintelligence Creative Research Laboratory,South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061842144","display_name":"Jun-Gyu Kang","orcid":"https://orcid.org/0000-0003-3411-1932"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jungyu Kang","raw_affiliation_strings":["ETRI,Superintelligence Creative Research Laboratory,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETRI,Superintelligence Creative Research Laboratory,South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013416745","display_name":"Taeg\u2010Hyun An","orcid":"https://orcid.org/0000-0002-7573-9059"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taeghyun An","raw_affiliation_strings":["ETRI,Superintelligence Creative Research Laboratory,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETRI,Superintelligence Creative Research Laboratory,South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041035629","display_name":"Kyounghwan Ahn","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyounghwan Ahn","raw_affiliation_strings":["ETRI,Superintelligence Creative Research Laboratory,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETRI,Superintelligence Creative Research Laboratory,South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041877826","display_name":"Kyoung-Wook Min","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"KyoungWook Min","raw_affiliation_strings":["ETRI,Superintelligence Creative Research Laboratory,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETRI,Superintelligence Creative Research Laboratory,South Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142401562"],"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":"10807","last_page":"10812"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9832000136375427,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9832000136375427,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9642999768257141,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9466000199317932,"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":0.804391622543335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6321661472320557},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5745108723640442},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.489866703748703},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4572370648384094},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40853413939476013},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3236618638038635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804391622543335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6321661472320557},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5745108723640442},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.489866703748703},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4572370648384094},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40853413939476013},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3236618638038635}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801357","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2948515602","https://openalex.org/W2963351448","https://openalex.org/W3034669477","https://openalex.org/W3035574168","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3109395584","https://openalex.org/W3134992866","https://openalex.org/W3138516171","https://openalex.org/W4214530037","https://openalex.org/W4225793049","https://openalex.org/W4286982960","https://openalex.org/W4312270296","https://openalex.org/W4312396550","https://openalex.org/W4312641958","https://openalex.org/W4312894406","https://openalex.org/W4312960790","https://openalex.org/W4319300075","https://openalex.org/W4383066393","https://openalex.org/W4385644318","https://openalex.org/W4386066258","https://openalex.org/W4386066572","https://openalex.org/W4386071503","https://openalex.org/W4386072002","https://openalex.org/W4386083035","https://openalex.org/W4390873598","https://openalex.org/W6638667902","https://openalex.org/W6756392615","https://openalex.org/W6757817989","https://openalex.org/W6784094891"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2501551404","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W4385583601","https://openalex.org/W4395685956","https://openalex.org/W3159516372","https://openalex.org/W4398146871","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Expressing":[0],"images":[1,175],"with":[2,84,144],"Multi-Resolution":[3],"(MR)":[4],"features":[5,173],"has":[6],"been":[7],"widely":[8],"adopted":[9],"in":[10,94,207],"many":[11],"computer":[12],"vision":[13],"tasks.":[14],"In":[15],"this":[16],"paper,":[17],"we":[18,133],"introduce":[19],"the":[20,61,104,107,112,115,122,127,136,145,156,184,204],"MR":[21,57],"concept":[22],"into":[23],"Bird's-Eye-View":[24],"(BEV)":[25],"semantic":[26,148],"segmentation":[27],"for":[28],"autonomous":[29],"driving.":[30],"This":[31,75,99],"introduction":[32],"enhances":[33],"our":[34,48,152,189,201],"model's":[35],"ability":[36],"to":[37,90,121,125,142,150,183],"capture":[38,155],"both":[39,135],"global":[40,157],"and":[41,82,138,158,176],"local":[42,159],"characteristics":[43],"of":[44,56,106,209],"driving":[45],"scenes":[46],"through":[47],"proposed":[49],"residual":[50],"learning.":[51],"Specifically,":[52],"given":[53],"a":[54,70,85,95,164,192],"set":[55],"BEV":[58,147],"query":[59,64,77,88,109,129,140],"maps,":[60],"lowest":[62,116,137],"resolution":[63,87,105,117,124],"map":[65,78,89,110,118,149],"is":[66,79,101,119],"initially":[67],"updated":[68,76,108],"using":[69],"View":[71],"Transformation":[72],"(VT)":[73],"encoder.":[74,98],"then":[80],"upscaled":[81],"merged":[83],"higher":[86],"undergo":[91],"further":[92],"updates":[93],"subsequent":[96],"VT":[97],"process":[100],"repeated":[102],"until":[103],"reaches":[111],"target.":[113],"Finally,":[114],"added":[120],"target":[123],"generate":[126],"final":[128,139],"map.":[130],"During":[131],"training,":[132],"enforce":[134],"maps":[141],"align":[143],"ground-truth":[146],"help":[151],"model":[153,190,202],"effectively":[154],"characteristics.":[160],"We":[161,187],"also":[162],"propose":[163],"visual":[165],"feature":[166,178],"interaction":[167],"network":[168],"that":[169,200],"promotes":[170],"interactions":[171],"between":[172],"across":[174,177],"levels,":[179],"thus":[180],"highly":[181],"contributing":[182],"performance":[185],"improvement.":[186],"evaluate":[188],"on":[191],"large-scale":[193],"real-world":[194],"dataset.":[195],"The":[196],"experimental":[197],"results":[198],"show":[199],"outperforms":[203],"SOTA":[205],"models":[206],"terms":[208],"IoU":[210],"metric.":[211],"Codes":[212],"are":[213],"available":[214],"at":[215],"https://github.com/d1024choi/ProgressiveQueryReneNet":[216]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}