{"id":"https://openalex.org/W4309213282","doi":"https://doi.org/10.48550/arxiv.2211.08287","title":"Towards 3D Object Detection with 2D Supervision","display_name":"Towards 3D Object Detection with 2D Supervision","publication_year":2022,"publication_date":"2022-11-15","ids":{"openalex":"https://openalex.org/W4309213282","doi":"https://doi.org/10.48550/arxiv.2211.08287"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2211.08287","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.08287","pdf_url":"https://arxiv.org/pdf/2211.08287","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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.08287","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101930120","display_name":"Jinrong Yang","orcid":"https://orcid.org/0000-0002-7678-0360"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yang, Jinrong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110647238","display_name":"Tiancai Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Tiancai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106405555","display_name":"Zheng Ge","orcid":"https://orcid.org/0000-0002-8630-8270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge, Zheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005056360","display_name":"Weixin Mao","orcid":"https://orcid.org/0000-0002-0444-1079"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao, Weixin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101510267","display_name":"Xiaoping Li","orcid":"https://orcid.org/0000-0001-9213-0416"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiaoping","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362465","display_name":"Xiangyu Zhang","orcid":"https://orcid.org/0000-0003-2138-4608"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiangyu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101930120"],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9973999857902527,"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":0.9972000122070312,"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/bottleneck","display_name":"Bottleneck","score":0.8207317590713501},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.8053334951400757},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7771692276000977},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6282875537872314},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.6060535907745361},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5991727709770203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5474675893783569},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5306649804115295},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.49193596839904785},{"id":"https://openalex.org/keywords/homography","display_name":"Homography","score":0.4665985107421875},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4611546993255615},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.45910385251045227},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38529130816459656},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.26568564772605896},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.220784991979599}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8207317590713501},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.8053334951400757},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7771692276000977},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6282875537872314},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6060535907745361},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5991727709770203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5474675893783569},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5306649804115295},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.49193596839904785},{"id":"https://openalex.org/C28751775","wikidata":"https://www.wikidata.org/wiki/Q2112539","display_name":"Homography","level":4,"score":0.4665985107421875},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4611546993255615},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.45910385251045227},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38529130816459656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26568564772605896},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.220784991979599},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C75280867","wikidata":"https://www.wikidata.org/wiki/Q877775","display_name":"Projective space","level":3,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C177846678","wikidata":"https://www.wikidata.org/wiki/Q1501864","display_name":"Projective test","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2211.08287","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.08287","pdf_url":"https://arxiv.org/pdf/2211.08287","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.2211.08287","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2211.08287","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.08287","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.08287","pdf_url":"https://arxiv.org/pdf/2211.08287","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W4287027631","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4390524233"],"abstract_inverted_index":{"The":[0,14],"great":[1],"progress":[2],"of":[3,67,125,147],"3D":[4,12,18,49,59,87,107,132,151],"object":[5,50],"detectors":[6],"relies":[7],"on":[8,116],"large-scale":[9],"data":[10],"and":[11,30,98],"annotations.":[13,60,133],"annotation":[15],"cost":[16],"for":[17,112,142,150],"bounding":[19],"boxes":[20],"is":[21],"extremely":[22],"expensive":[23],"while":[24],"the":[25,64,86,106,117],"2D":[26,54,68,76,82,91,99,110,148],"ones":[27,111],"are":[28,102],"easier":[29],"cheaper":[31],"to":[32,45,84,104],"collect.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37,70],"introduce":[38],"a":[39,47,72,80,144],"hybrid":[40],"training":[41],"framework,":[42],"enabling":[43],"us":[44],"learn":[46],"visual":[48],"detector":[51],"with":[52,89,129],"massive":[53],"(pseudo)":[55],"labels,":[56],"even":[57],"without":[58],"To":[61],"break":[62],"through":[63],"information":[65],"bottleneck":[66],"clues,":[69],"explore":[71],"new":[73,140],"perspective:":[74],"Temporal":[75],"Supervision.":[77],"We":[78,134],"propose":[79],"temporal":[81,90],"transformation":[83],"bridge":[85],"predictions":[88,108],"labels.":[92],"Two":[93],"steps,":[94],"including":[95],"homography":[96],"wraping":[97],"box":[100],"deduction,":[101],"taken":[103],"transform":[105],"into":[109],"supervision.":[113],"Experiments":[114],"conducted":[115],"nuScenes":[118],"dataset":[119],"show":[120],"strong":[121],"results":[122],"(nearly":[123],"90%":[124],"its":[126],"fully-supervised":[127],"performance)":[128],"only":[130],"25%":[131],"hope":[135],"our":[136],"findings":[137],"can":[138],"provide":[139],"insights":[141],"using":[143],"large":[145],"number":[146],"annotations":[149],"perception.":[152]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}