{"id":"https://openalex.org/W4403662467","doi":"https://doi.org/10.48550/arxiv.2408.03790","title":"Vision-Language Guidance for LiDAR-based Unsupervised 3D Object Detection","display_name":"Vision-Language Guidance for LiDAR-based Unsupervised 3D Object Detection","publication_year":2024,"publication_date":"2024-08-07","ids":{"openalex":"https://openalex.org/W4403662467","doi":"https://doi.org/10.48550/arxiv.2408.03790"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2408.03790","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.03790","pdf_url":"https://arxiv.org/pdf/2408.03790","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.03790","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077289241","display_name":"Christian Fruhwirth-Reisinger","orcid":"https://orcid.org/0000-0001-9930-9822","observed_orcids":["https://orcid.org/0000-0001-9930-9822"]},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Fruhwirth-Reisinger, Christian","raw_affiliation_strings":["Christian Doppler Laboratory for Embedded Machine Learning","Institute of Computer Graphics and Vision Graz University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Christian Doppler Laboratory for Embedded Machine Learning","institution_ids":[]},{"raw_affiliation_string":"Institute of Computer Graphics and Vision Graz University of Technology","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620874","display_name":"Wei Shiang Lin","orcid":"https://orcid.org/0000-0001-9213-5954","observed_orcids":["https://orcid.org/0000-0001-9213-5954"]},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Lin, Wei","raw_affiliation_strings":["Institute for Machine Learning Johannes Kepler University Linz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Machine Learning Johannes Kepler University Linz","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041706615","display_name":"Du\u0161an Mali\u0107","orcid":"https://orcid.org/0009-0002-1846-4228","observed_orcids":["https://orcid.org/0009-0002-1846-4228"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mali\u0107, Du\u0161an","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011359067","display_name":"Horst Bischof","orcid":"https://orcid.org/0000-0002-9096-6671","observed_orcids":["https://orcid.org/0000-0002-9096-6671"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bischof, Horst","raw_affiliation_strings":["Christian Doppler Laboratory for Embedded Machine Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Christian Doppler Laboratory for Embedded Machine Learning","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039382695","display_name":"Horst Possegger","orcid":"https://orcid.org/0000-0002-5427-9938","observed_orcids":["https://orcid.org/0000-0002-5427-9938"]},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Possegger, Horst","raw_affiliation_strings":["Christian Doppler Laboratory for Embedded Machine Learning","Institute of Computer Graphics and Vision Graz University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Christian Doppler Laboratory for Embedded Machine Learning","institution_ids":[]},{"raw_affiliation_string":"Institute of Computer Graphics and Vision Graz University of Technology","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.7188000082969666,"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":0.7188000082969666,"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":0.2062000036239624,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.018200000748038292,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/lidar-point-cloud","display_name":"LiDAR point cloud","score":0.9980000257492065},{"id":"https://openalex.org/keywords/clip","display_name":"CLIP","score":0.8980000019073486},{"id":"https://openalex.org/keywords/pseudo-labeling","display_name":"pseudo-labeling","score":0.8999999761581421},{"id":"https://openalex.org/keywords/point-cloud-clustering","display_name":"point cloud clustering","score":0.8600000143051147},{"id":"https://openalex.org/keywords/object-tracking","display_name":"object tracking","score":0.7239999771118164},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.7300000190734863},{"id":"https://openalex.org/keywords/waymo-open-dataset","display_name":"Waymo Open Dataset","score":0.9539999961853027},{"id":"https://openalex.org/keywords/argoverse-2","display_name":"Argoverse 2","score":0.9750000238418579}],"concepts":[{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.8707672357559204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6071212291717529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5744374394416809},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5693457722663879},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5464850068092346},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4617602527141571},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3757210075855255},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2747354507446289},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.24517446756362915}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2408.03790","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.03790","pdf_url":"https://arxiv.org/pdf/2408.03790","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2408.03790","doi":"https://doi.org/10.48550/arxiv.2408.03790","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.03790","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.03790","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.03790","pdf_url":"https://arxiv.org/pdf/2408.03790","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311813","display_name":"\u00d6sterreichische Nationalstiftung f\u00fcr Forschung, Technologie und Entwicklung","ror":"https://ror.org/04hb33h70"},{"id":"https://openalex.org/F4320323591","display_name":"Christian Doppler Forschungsgesellschaft","ror":"https://ror.org/00mv8h305"},{"id":"https://openalex.org/F4320327593","display_name":"Bundesministerium f\u00fcr Digitalisierung und Wirtschaftsstandort","ror":"https://ror.org/00eh1sz49"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403662467.pdf","grobid_xml":"https://content.openalex.org/works/W4403662467.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4319317934","https://openalex.org/W2901265155","https://openalex.org/W2956374172","https://openalex.org/W2351984678","https://openalex.org/W2140032575","https://openalex.org/W2011860471","https://openalex.org/W2012196540","https://openalex.org/W3011451421","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Accurate":[0],"3D":[1,114,165],"object":[2,38,47,166,186],"detection":[3,48,115],"in":[4,193],"LiDAR":[5,121,147],"point":[6,122,130,148],"clouds":[7,149],"is":[8,30],"crucial":[9],"for":[10,53,150],"autonomous":[11],"driving":[12],"systems.":[13],"To":[14,40,105],"achieve":[15],"state-of-the-art":[16,163],"performance,":[17],"the":[18,92,142,169,194],"supervised":[19],"training":[20],"of":[21,26,132,146],"detectors":[22,167],"requires":[23],"large":[24],"amounts":[25],"human-annotated":[27],"data,":[28],"which":[29,137],"expensive":[31],"to":[32,36,61,78,86,128],"obtain":[33],"and":[34,101,134,157,174,178],"restricted":[35,85],"predefined":[37],"categories.":[39],"mitigate":[41],"manual":[42],"labeling":[43],"efforts,":[44],"recent":[45],"unsupervised":[46,113,164],"approaches":[49,69],"generate":[50],"class-agnostic":[51],"pseudo-labels":[52],"moving":[54,135],"objects,":[55,136],"subsequently":[56],"serving":[57],"as":[58,153,155],"supervision":[59],"signal":[60],"bootstrap":[62],"a":[63,98,111,190],"detector.":[64],"Despite":[65],"promising":[66],"results,":[67],"these":[68,107],"do":[70],"not":[71,182],"provide":[72],"class":[73,180],"labels":[74,181],"or":[75,95],"generalize":[76],"well":[77,154],"static":[79,133],"objects.":[80],"Furthermore,":[81],"they":[82],"are":[83],"mostly":[84],"data":[87],"containing":[88],"multiple":[89],"drives":[90],"from":[91,97],"same":[93],"scene":[94],"images":[96],"precisely":[99],"calibrated":[100],"synchronized":[102],"camera":[103],"setup.":[104],"overcome":[106],"limitations,":[108],"we":[109,138],"propose":[110],"vision-language-guided":[112],"approach":[116,161],"that":[117],"operates":[118],"exclusively":[119],"on":[120,168,185],"clouds.":[123],"We":[124],"transfer":[125],"CLIP":[126],"knowledge":[127],"classify":[129],"clusters":[131],"discover":[139],"by":[140],"exploiting":[141],"inherent":[143],"spatio-temporal":[144],"information":[145],"clustering,":[151],"tracking,":[152],"box":[156],"label":[158],"refinement.":[159],"Our":[160],"outperforms":[162],"Waymo":[170],"Open":[171],"Dataset":[172],"($+23~\\text{AP}_{3D}$)":[173],"Argoverse":[175],"2":[176],"($+7.9~\\text{AP}_{3D}$)":[177],"provides":[179],"solely":[183],"based":[184],"size":[187],"assumptions,":[188],"marking":[189],"significant":[191],"advancement":[192],"field.":[195]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2025-10-10T00:00:00"}