{"id":"https://openalex.org/W7138152682","doi":"https://doi.org/10.1609/aaai.v40i14.38157","title":"MonoCLUE: Object-Aware Clustering Enhances Monocular 3D Object Detection","display_name":"MonoCLUE: Object-Aware Clustering Enhances Monocular 3D Object Detection","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138152682","doi":"https://doi.org/10.1609/aaai.v40i14.38157"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i14.38157","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38157","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38157/42119","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38157/42119","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129743026","display_name":"Sunghun Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sunghun Yang","raw_affiliation_strings":["Yonsei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129721166","display_name":"Minhyeok Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minhyeok Lee","raw_affiliation_strings":["Yonsei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129694254","display_name":"Jungho Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jungho Lee","raw_affiliation_strings":["Yonsei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125577862","display_name":"Sangyoun Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangyoun Lee","raw_affiliation_strings":["Yonsei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.8252,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95014245,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"40","issue":"14","first_page":"11721","last_page":"11729"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9289000034332275,"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":0.9289000034332275,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.00860000029206276,"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/T11448","display_name":"Face recognition and analysis","score":0.00839999970048666,"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/monocular","display_name":"Monocular","score":0.6827999949455261},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6625999808311462},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6019999980926514},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5604000091552734},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5182999968528748},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4657000005245209},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45899999141693115},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.3871000111103058}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8152999877929688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7041000127792358},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6833999752998352},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6827999949455261},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6625999808311462},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6019999980926514},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5604000091552734},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5182999968528748},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4657000005245209},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.33340001106262207},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.3262999951839447},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.314300000667572},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.2919999957084656},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C178278151","wikidata":"https://www.wikidata.org/wiki/Q7936607","display_name":"Visual memory","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i14.38157","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38157","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38157/42119","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i14.38157","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38157","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38157/42119","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138152682.pdf","grobid_xml":"https://content.openalex.org/works/W7138152682.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Monocular":[0],"3D":[1,73,200],"object":[2,62,175],"detection":[3,74,109,159,201],"offers":[4],"a":[5,19,133],"cost-effective":[6],"solution":[7],"for":[8,60],"autonomous":[9],"driving,":[10],"but":[11],"it":[12],"suffers":[13],"from":[14],"the":[15,28,54,108,121,152,183,214],"ill-posed":[16],"depth":[17,46],"and":[18,33,80,170,191,204],"limited":[20,205],"field":[21],"of":[22,30,56,84,110,154],"view.":[23],"These":[24],"constraints":[25],"lead":[26],"to":[27,48,95,124],"lack":[29],"geometric":[31,50],"cues":[32,58],"reduced":[34],"accuracy":[35],"in":[36,182],"occluded":[37],"or":[38],"truncated":[39],"scenes.":[40,149],"While":[41],"recent":[42],"approaches":[43],"incorporate":[44],"additional":[45],"information":[47],"address":[49],"ambiguity,":[51],"they":[52],"overlook":[53],"importance":[55],"visual":[57,85,93,100],"essential":[59],"robust":[61,198],"recognition.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,88,131,164],"propose":[68],"MonoCLUE":[69,196],"that":[70,147],"enhances":[71],"monocular":[72,199],"by":[75,137],"leveraging":[76],"both":[77,166],"local":[78,167,189],"clustering":[79,91,190],"generalized":[81,134,171,192],"scene":[82,135,172,193],"memory":[83,136,173,194],"features.":[86],"First,":[87],"perform":[89],"K-means":[90],"on":[92,213],"features":[94,116,140,169],"capture":[96,125],"distinct":[97],"object-level":[98,155],"appearance":[99,145],"parts":[101],"(e.g.,":[102],"bonnet,":[103],"car":[104],"roof),":[105],"which":[106],"improves":[107,151],"partially":[111],"visible":[112],"objects.":[113],"The":[114],"clustered":[115,139],"are":[117],"then":[118],"propagated":[119],"across":[120,141,160],"entire":[122],"region":[123],"objects":[126],"with":[127],"similar":[128],"appearances.":[129],"Second,":[130],"construct":[132],"aggregating":[138],"images,":[142],"providing":[143],"consistent":[144],"representations":[146],"generalize":[148],"This":[150],"consistency":[153],"features,":[156],"enabling":[157],"stable":[158],"varying":[161],"environments.":[162],"Lastly,":[163],"integrate":[165],"cluster":[168],"into":[174],"queries,":[176],"guiding":[177],"attention":[178],"toward":[179],"informative":[180],"regions":[181],"feature":[184],"map.":[185],"Exploiting":[186],"an":[187],"unified":[188],"strategy,":[195],"enables":[197],"under":[202],"occlusion":[203],"visibility.":[206],"Our":[207],"proposed":[208],"model":[209],"achieves":[210],"state-of-the-art":[211],"performance":[212],"KITTI":[215],"benchmark.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}