{"id":"https://openalex.org/W7147540727","doi":"https://doi.org/10.1109/tip.2026.3671587","title":"Learning 3D Representation From Auto-Labeled 2D Object Boxes","display_name":"Learning 3D Representation From Auto-Labeled 2D Object Boxes","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7147540727","doi":"https://doi.org/10.1109/tip.2026.3671587","pmid":"https://pubmed.ncbi.nlm.nih.gov/41915515"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3671587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3671587","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Qian Deng","orcid":"https://orcid.org/0000-0003-0998-6788"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Deng","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-0998-6788","affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030769176","display_name":"Le Hui","orcid":"https://orcid.org/0000-0003-0851-6805"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Hui","raw_affiliation_strings":["School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-0851-6805","affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100726984","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0003-4800-832X"},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology and the School of Intelligence Science and Technology, Nanjing University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4800-832X","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology and the School of Intelligence Science and Technology, Nanjing University, Suzhou, China","institution_ids":["https://openalex.org/I308837"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jin Xie","orcid":"https://orcid.org/0000-0002-9157-838X"},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Xie","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology and the School of Intelligence Science and Technology, Nanjing University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9157-838X","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology and the School of Intelligence Science and Technology, Nanjing University, Suzhou, China","institution_ids":["https://openalex.org/I308837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.40254069,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"3566","last_page":"3580"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.7638000249862671,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.7638000249862671,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.07689999788999557,"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":0.050200000405311584,"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/leverage","display_name":"Leverage (statistics)","score":0.6783000230789185},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5864999890327454},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5554999709129333},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5414000153541565},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5033000111579895},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5026999711990356},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4862000048160553},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43779999017715454},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.41670000553131104}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7321000099182129},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6783000230789185},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6363999843597412},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5864999890327454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5414000153541565},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5033000111579895},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5026999711990356},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4900999963283539},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.41670000553131104},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C77660490","wikidata":"https://www.wikidata.org/wiki/Q244916","display_name":"Intermediate language","level":3,"score":0.334199994802475},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.3228999972343445},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2994999885559082},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.288100004196167},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3671587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3671587","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:41915515","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41915515","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4576941430568695,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5858415739","display_name":null,"funder_award_id":"2024YFC3015801","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"LiDAR":[3],"representation":[4,21,25],"learning":[5],"with":[6,93,112],"limited":[7,162],"annotations":[8],"show":[9,181],"strong":[10],"promise.":[11],"Existing":[12],"well-performed":[13],"methods":[14],"mainly":[15],"focus":[16],"on":[17,118,188],"distilling":[18],"the":[19,23,33,46,51,77,82,102,119,134,158,167,190],"2D":[20,90,96,104,173],"into":[22,107],"3D":[24,42,78,127,139,159,169],"via":[26,175],"superpixels.":[27],"Superpixels":[28],"are":[29],"used":[30],"to":[31,38,45,58,63,81,152,165],"construct":[32],"cross-modal":[34],"contrastive":[35],"learning,":[36],"leading":[37],"semantic":[39,135],"ambiguity":[40],"of":[41,137],"features":[43,79,170],"belonging":[44,80],"same":[47,83],"object":[48,84,91,98,105],"and":[49,75,100,141,192],"impairing":[50],"performance.":[52],"To":[53],"this":[54],"end,":[55],"we":[56,87,122,146],"aim":[57],"leverage":[59],"unlabeled":[60],"LiDAR-camera":[61],"pairs":[62],"design":[64],"a":[65,94,113,124,148],"novel":[66],"pre-training":[67,126],"pipeline,":[68],"which":[69],"learns":[70],"from":[71,133],"category":[72,176],"space":[73],"directly":[74],"pulls":[76],"close.":[85],"Specifically,":[86],"obtain":[88],"autolabeled":[89],"boxes":[92,106],"fixed":[95],"open-vocabulary":[97],"detector":[99],"transform":[101],"labeled":[103],"high-quality":[108],"pixel-wise":[109],"label":[110],"maps":[111],"box-to-label-maps":[114],"generation":[115],"algorithm.":[116],"Based":[117],"pseudo":[120],"labels,":[121],"present":[123],"dual-space":[125],"network":[128,160],"that":[129,171,182],"recognizes":[130],"accurate":[131],"categories":[132],"priors":[136],"paired":[138],"points":[140],"segments":[142],"complete":[143],"objects.":[144],"Furthermore,":[145],"propose":[147],"module":[149],"named":[150],"AdaptPro":[151],"improve":[153],"performance":[154],"further":[155],"when":[156],"fine-tuning":[157],"under":[161],"annotations,":[163],"aiming":[164],"explore":[166],"unpaired":[168],"lack":[172],"correspondences":[174],"prototypes.":[177],"The":[178],"experimental":[179],"results":[180],"our":[183],"method":[184],"achieves":[185],"state-of-the-art":[186],"performances":[187],"both":[189],"nuScenes":[191],"SemanticKITTI":[193],"benchmark":[194],"datasets.":[195],"Code":[196],"is":[197],"avialable":[198],"at":[199],"https://github.com/dengq7/Box4Scene.":[200]},"counts_by_year":[],"updated_date":"2026-04-08T06:01:36.053099","created_date":"2026-04-02T00:00:00"}