{"id":"https://openalex.org/W4404988261","doi":"https://doi.org/10.1109/3dv69130.2026.00171","title":"Open Vocabulary Monocular 3D Object Detection","display_name":"Open Vocabulary Monocular 3D Object Detection","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W4404988261","doi":"https://doi.org/10.1109/3dv69130.2026.00171"},"language":"en","primary_location":{"id":"doi:10.1109/3dv69130.2026.00171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.16833","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086328337","display_name":"Yao Jin","orcid":"https://orcid.org/0000-0002-5395-8592"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jin Yao","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100735091","display_name":"Hao Gu","orcid":"https://orcid.org/0000-0002-0204-2875"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Gu","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008316477","display_name":"Xuweiyi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuweiyi Chen","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101755038","display_name":"Jiayun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayun Wang","raw_affiliation_strings":["California Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067219074","display_name":"Zezhou Cheng","orcid":"https://orcid.org/0000-0001-7754-0871"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zezhou Cheng","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00285105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1801","last_page":"1811"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.8790000081062317,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.8790000081062317,"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":0.8769000172615051,"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":0.876800000667572,"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":0.6206817626953125},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6015912890434265},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5912492275238037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.553663432598114},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.522231936454773},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.49990105628967285},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4998788833618164},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.21857962012290955},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1476081907749176}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6206817626953125},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6015912890434265},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5912492275238037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.553663432598114},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.522231936454773},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.49990105628967285},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4998788833618164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.21857962012290955},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1476081907749176},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/3dv69130.2026.00171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.16833","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.16833","pdf_url":"https://arxiv.org/pdf/2411.16833","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.16833","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.16833","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.16833","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.16833","pdf_url":"https://arxiv.org/pdf/2411.16833","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W200819717","https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W2032269556","https://openalex.org/W4292238148","https://openalex.org/W1991834176","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"We":[0,56,152],"propose":[1,87],"and":[2,95,103,160],"study":[3],"open-vocabulary":[4],"monocular":[5],"3D":[6,21,29,69,84,96,139],"detection,":[7],"a":[8,24,88,121,157,165],"novel":[9,122,142],"task":[10],"that":[11,90,124],"aims":[12],"to":[13,46,76],"detect":[14],"objects":[15],"of":[16,68,141],"any":[17],"categories":[18,143],"in":[19,61,110,137],"metric":[20,123],"space":[22],"from":[23],"single":[25],"RGB":[26],"image.":[27],"Existing":[28],"object":[30],"detectors":[31],"either":[32],"rely":[33],"on":[34,83,149],"costly":[35],"sensors":[36],"such":[37],"as":[38,144,146],"LiDAR":[39],"or":[40,43],"multi-view":[41],"setups,":[42],"remain":[44],"confined":[45],"closed":[47],"vocabularies":[48],"settings":[49],"with":[50],"limited":[51],"categories,":[52],"restricting":[53],"their":[54],"applicability.":[55],"identify":[57],"two":[58],"key":[59],"challenges":[60],"this":[62],"new":[63],"setting.":[64],"First,":[65],"the":[66,74],"scarcity":[67],"bounding":[70],"box":[71],"annotations":[72],"limits":[73],"ability":[75],"train":[77],"generalizable":[78],"models.":[79,99],"To":[80,116],"reduce":[81],"dependence":[82],"supervision,":[85],"we":[86,119],"framework":[89],"effectively":[91],"integrates":[92],"pretrained":[93],"2D":[94],"vision":[97],"foundation":[98],"Second,":[100],"missing":[101],"labels":[102],"semantic":[104],"ambiguities":[105],"(e.g.,":[106],"table":[107],"vs.":[108],"desk)":[109],"existing":[111],"datasets":[112],"hinder":[113],"reliable":[114,166],"evaluation.":[115],"address":[117],"this,":[118],"design":[120],"captures":[125],"model":[126],"performance":[127],"while":[128],"mitigating":[129],"annotation":[130],"issues.":[131],"Our":[132],"approach":[133],"achieves":[134],"state-of-the-art":[135],"results":[136],"zero-shot":[138],"detection":[140,148],"well":[145],"in-domain":[147],"seen":[150],"classes.":[151],"hope":[153],"our":[154,161],"method":[155],"provides":[156],"strong":[158],"baseline":[159],"evaluation":[162],"protocol":[163],"establishes":[164],"benchmark":[167],"for":[168],"future":[169],"research.":[170]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}