{"id":"https://openalex.org/W7131125697","doi":"https://doi.org/10.1145/3790253","title":"R <sup>2</sup> MOAG: Robust Roadside Monocular 3D Object Detection with Adaptive Token and Ground Embedding","display_name":"R <sup>2</sup> MOAG: Robust Roadside Monocular 3D Object Detection with Adaptive Token and Ground Embedding","publication_year":2026,"publication_date":"2026-02-23","ids":{"openalex":"https://openalex.org/W7131125697","doi":"https://doi.org/10.1145/3790253"},"language":"en","primary_location":{"id":"doi:10.1145/3790253","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3790253","pdf_url":null,"source":{"id":"https://openalex.org/S2506189754","display_name":"ACM Transactions on Cyber-Physical Systems","issn_l":"2378-962X","issn":["2378-962X","2378-9638"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Cyber-Physical Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3790253","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126602277","display_name":"Jie Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jie Tang","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8602-7754","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoran Pan","orcid":"https://orcid.org/0009-0000-3515-6548"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Pan","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-3515-6548","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126592739","display_name":"Bo Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104064","display_name":"Shenzhen Academy of Robotics","ror":"https://ror.org/01h027j09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210104064"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Yu","raw_affiliation_strings":["Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0139-3622","affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China","institution_ids":["https://openalex.org/I4210104064"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126600489","display_name":"Shaoshan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104064","display_name":"Shenzhen Academy of Robotics","ror":"https://ror.org/01h027j09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210104064"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoshan Liu","raw_affiliation_strings":["Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5132-8351","affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China","institution_ids":["https://openalex.org/I4210104064"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5126602277"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26623407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"3","first_page":"1","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9147999882698059,"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":0.9147999882698059,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.05609999969601631,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.0032999999821186066,"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/monocular","display_name":"Monocular","score":0.621999979019165},{"id":"https://openalex.org/keywords/ground-plane","display_name":"Ground plane","score":0.6049000024795532},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5942999720573425},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4973999857902527},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.45100000500679016},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.44519999623298645},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4433000087738037}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7167999744415283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7027000188827515},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6825000047683716},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.621999979019165},{"id":"https://openalex.org/C88764893","wikidata":"https://www.wikidata.org/wiki/Q1547722","display_name":"Ground plane","level":3,"score":0.6049000024795532},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5942999720573425},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4973999857902527},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.45100000500679016},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.44519999623298645},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4433000087738037},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4124000072479248},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.34869998693466187},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.310699999332428},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2799000144004822},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3790253","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3790253","pdf_url":null,"source":{"id":"https://openalex.org/S2506189754","display_name":"ACM Transactions on Cyber-Physical Systems","issn_l":"2378-962X","issn":["2378-962X","2378-9638"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Cyber-Physical Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3790253","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3790253","pdf_url":null,"source":{"id":"https://openalex.org/S2506189754","display_name":"ACM Transactions on Cyber-Physical Systems","issn_l":"2378-962X","issn":["2378-962X","2378-9638"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Cyber-Physical Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.6533162593841553,"id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G4103579769","display_name":null,"funder_award_id":"62372188","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5286376425","display_name":null,"funder_award_id":"2024A1515010100","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W3096609285","https://openalex.org/W3128100939","https://openalex.org/W4225793049","https://openalex.org/W4285252188","https://openalex.org/W4313431522","https://openalex.org/W4386066137","https://openalex.org/W4387518906","https://openalex.org/W4387706956","https://openalex.org/W4390873008","https://openalex.org/W4391376795","https://openalex.org/W4394672999","https://openalex.org/W4399881121","https://openalex.org/W4402809322"],"related_works":[],"abstract_inverted_index":{"Roadside":[0],"cameras":[1],"effectively":[2],"enhance":[3],"the":[4,18,36,141,162,179,189,193,202],"perception":[5,48,105],"capabilities":[6],"of":[7,20,38,176],"embodied":[8],"artificial":[9],"intelligence":[10],"systems":[11,45],"such":[12],"as":[13,58,60],"vehicles":[14],"by":[15],"compensating":[16],"for":[17,74,99,150,192],"limitations":[19],"vehicle-mounted":[21],"cameras,":[22],"which":[23],"are":[24],"prone":[25],"to":[26,76,127],"occlusion":[27],"and":[28,67,107,122,147,168,185,212],"have":[29],"a":[30,91,183],"limited":[31],"sensing":[32],"range,":[33],"thereby":[34],"improving":[35],"safety":[37],"autonomous":[39],"vehicles.":[40],"However,":[41],"existing":[42],"object":[43,96,151],"detection":[44,97],"often":[46],"encounter":[47],"errors":[49],"when":[50],"handling":[51],"comprehensive":[52],"viewpoint":[53],"noise":[54],"in":[55,62,79,174,188],"roadside":[56,100,165],"scenes,":[57],"well":[59],"variations":[61],"traffic":[63],"flow,":[64],"lighting":[65],"conditions,":[66],"camera":[68,213],"poses.":[69],"This":[70],"makes":[71],"it":[72],"challenging":[73],"them":[75],"perform":[77],"robustly":[78],"complex":[80],"road":[81,116,210],"environments.":[82],"To":[83],"address":[84],"these":[85,197],"issues,":[86],"we":[87],"propose":[88],"\\(\\mathrm{R^{2}MOAG}\\)":[89],",":[90],"highly":[92],"robust":[93],"monocular":[94],"3D":[95],"method":[98,113],"systems,":[101],"based":[102],"on":[103,129,161,196],"ground":[104,119,135],"embedding":[106],"heterogeneous":[108,124],"visual":[109,125,139],"tokens.":[110],"The":[111,170],"proposed":[112,180],"extracts":[114],"detailed":[115],"information":[117,136],"through":[118],"plane":[120],"equations":[121],"utilizes":[123],"tokens":[126],"focus":[128],"foreground":[130],"features.":[131],"By":[132],"integrating":[133],"low-dimensional":[134],"with":[137,145],"high-dimensional":[138],"features,":[140],"model":[142,181,203],"is":[143],"provided":[144],"clear":[146],"rich":[148],"cues":[149],"detection,":[152],"significantly":[153],"enhancing":[154],"its":[155],"stability.":[156],"We":[157],"conducted":[158],"extensive":[159],"experiments":[160],"widely":[163],"recognized":[164],"datasets":[166],"DAIR-V2X-I":[167],"Rope3D.":[169],"results":[171],"show":[172],"that,":[173],"terms":[175],"overall":[177],"performance,":[178],"achieved":[182],"4.65%":[184],"4.26%":[186],"improvement":[187],"\\(AP_{3D}|_{R40}\\)":[190],"metric":[191],"vehicle":[194],"category":[195],"two":[198],"datasets,":[199],"respectively.":[200],"Moreover,":[201],"maintained":[204],"stable":[205],"recognition":[206],"performance":[207],"across":[208],"various":[209],"scenarios":[211],"poses,":[214],"demonstrating":[215],"exceptional":[216],"robustness.":[217]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-24T00:00:00"}