{"id":"https://openalex.org/W4401414543","doi":"https://doi.org/10.1109/icra57147.2024.10611572","title":"S2R-ViT for Multi-Agent Cooperative Perception: Bridging the Gap from Simulation to Reality","display_name":"S2R-ViT for Multi-Agent Cooperative Perception: Bridging the Gap from Simulation to Reality","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401414543","doi":"https://doi.org/10.1109/icra57147.2024.10611572"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611572","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5100454985","display_name":"Jinlong Li","orcid":"https://orcid.org/0000-0002-8746-4566"},"institutions":[{"id":"https://openalex.org/I102607778","display_name":"Cleveland State University","ror":"https://ror.org/002tx1f22","country_code":"US","type":"education","lineage":["https://openalex.org/I102607778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinlong Li","raw_affiliation_strings":["Cleveland State University, Cleveland Vision & AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cleveland State University, Cleveland Vision & AI Lab","institution_ids":["https://openalex.org/I102607778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700826","display_name":"Runsheng Xu","orcid":"https://orcid.org/0000-0001-7375-9833"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Runsheng Xu","raw_affiliation_strings":["University of California, UCLA Mobility Lab,Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, UCLA Mobility Lab,Los Angeles","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446463","display_name":"Xinyu Liu","orcid":"https://orcid.org/0009-0006-8407-3806"},"institutions":[{"id":"https://openalex.org/I102607778","display_name":"Cleveland State University","ror":"https://ror.org/002tx1f22","country_code":"US","type":"education","lineage":["https://openalex.org/I102607778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyu Liu","raw_affiliation_strings":["Cleveland State University, Cleveland Vision & AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cleveland State University, Cleveland Vision & AI Lab","institution_ids":["https://openalex.org/I102607778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008481358","display_name":"Baolu Li","orcid":"https://orcid.org/0009-0002-4741-8626"},"institutions":[{"id":"https://openalex.org/I102607778","display_name":"Cleveland State University","ror":"https://ror.org/002tx1f22","country_code":"US","type":"education","lineage":["https://openalex.org/I102607778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baolu Li","raw_affiliation_strings":["Cleveland State University, Cleveland Vision & AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cleveland State University, Cleveland Vision & AI Lab","institution_ids":["https://openalex.org/I102607778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070093927","display_name":"Qin Zou","orcid":"https://orcid.org/0000-0001-7955-0782"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Zou","raw_affiliation_strings":["Wuhan University, MVR Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University, MVR Lab","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068374815","display_name":"Jiaqi Ma","orcid":"https://orcid.org/0000-0002-8184-5157"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaqi Ma","raw_affiliation_strings":["University of California, UCLA Mobility Lab,Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, UCLA Mobility Lab,Los Angeles","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025512337","display_name":"Hongkai Yu","orcid":"https://orcid.org/0000-0001-5383-8913"},"institutions":[{"id":"https://openalex.org/I102607778","display_name":"Cleveland State University","ror":"https://ror.org/002tx1f22","country_code":"US","type":"education","lineage":["https://openalex.org/I102607778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongkai Yu","raw_affiliation_strings":["Cleveland State University, Cleveland Vision & AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cleveland State University, Cleveland Vision & AI Lab","institution_ids":["https://openalex.org/I102607778"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1295,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95212337,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"16374","last_page":"16380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9961000084877014,"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":0.9961000084877014,"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":0.9940000176429749,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/bridging","display_name":"Bridging (networking)","score":0.9347014427185059},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.7167094945907593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6425711512565613},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.4295564889907837},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40018656849861145},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.229303240776062},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13359716534614563},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.11194440722465515}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.9347014427185059},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.7167094945907593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6425711512565613},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.4295564889907837},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40018656849861145},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.229303240776062},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13359716534614563},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.11194440722465515}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611572","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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":33,"referenced_works":["https://openalex.org/W2963200935","https://openalex.org/W2963351448","https://openalex.org/W2963684088","https://openalex.org/W2968296999","https://openalex.org/W2985739927","https://openalex.org/W2996770795","https://openalex.org/W3109991383","https://openalex.org/W3122939190","https://openalex.org/W3138516171","https://openalex.org/W3177015573","https://openalex.org/W3201193904","https://openalex.org/W3202229469","https://openalex.org/W3210076120","https://openalex.org/W4214619833","https://openalex.org/W4284701604","https://openalex.org/W4297411803","https://openalex.org/W4312571135","https://openalex.org/W4312604822","https://openalex.org/W4312638656","https://openalex.org/W4312894203","https://openalex.org/W4319300947","https://openalex.org/W4327852039","https://openalex.org/W4352977781","https://openalex.org/W4383108477","https://openalex.org/W4386047746","https://openalex.org/W4386066469","https://openalex.org/W6639480849","https://openalex.org/W6685352114","https://openalex.org/W6757817989","https://openalex.org/W6784333009","https://openalex.org/W6785667878","https://openalex.org/W6839180059","https://openalex.org/W6842774165"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2059650074","https://openalex.org/W4285504728"],"abstract_inverted_index":{"Due":[0],"to":[1,40,45,111,128,158],"the":[2,20,29,41,46,51,61,82,95,114,130,137,148,154],"lack":[3],"of":[4,11,97,101],"enough":[5],"real":[6,42,54,91],"multi-agent":[7,14,68,139],"data":[8,23],"and":[9,26,53,85,90,104,117,125,144,160],"time-consuming":[10],"labeling,":[12],"existing":[13],"cooperative":[15,69,140],"perception":[16,30,70,141],"algorithms":[17],"usually":[18],"select":[19],"simulated":[21,52,89],"sensor":[22],"for":[24,67,165],"training":[25],"validating.":[27],"However,":[28],"performance":[31],"is":[32],"degraded":[33],"when":[34],"these":[35,98],"simulation-trained":[36],"models":[37],"are":[38],"deployed":[39],"world,":[43],"due":[44],"significant":[47],"domain":[48,102],"gap":[49,155],"between":[50,88],"data.":[55,92],"In":[56],"this":[57],"paper,":[58],"we":[59],"propose":[60,105],"first":[62],"Simulation-to-Reality":[63],"transfer":[64],"learning":[65],"framework":[66],"using":[71],"a":[72,106],"novel":[73,107],"Vision":[74],"Transformer,":[75],"named":[76],"as":[77],"S2R-ViT,":[78],"which":[79],"considers":[80],"both":[81],"Deployment":[83,115],"Gap":[84,87,116],"Feature":[86,131],"We":[93],"investigate":[94],"effects":[96],"two":[99],"types":[100],"gaps":[103],"uncertainty-aware":[108],"vision":[109],"transformer":[110],"effectively":[112,152],"relief":[113],"an":[118],"agent-based":[119],"feature":[120],"adaptation":[121],"module":[122],"with":[123],"inter-agent":[124],"ego-agent":[126],"discriminators":[127],"reduce":[129],"Gap.":[132],"Our":[133],"intensive":[134],"experiments":[135],"on":[136],"public":[138],"datasets":[142],"OPV2V":[143],"V2V4Real":[145],"demonstrate":[146],"that":[147],"proposed":[149],"S2R-ViT":[150],"can":[151],"bridge":[153],"from":[156],"simulation":[157],"reality":[159],"outperform":[161],"other":[162],"methods":[163],"significantly":[164],"point":[166],"cloud-based":[167],"3D":[168],"object":[169],"detection.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-05T07:55:05.734416","created_date":"2025-10-10T00:00:00"}