{"id":"https://openalex.org/W3129282545","doi":"https://doi.org/10.1109/lra.2021.3061343","title":"Monocular 3D Detection With Geometric Constraint Embedding and Semi-Supervised Training","display_name":"Monocular 3D Detection With Geometric Constraint Embedding and Semi-Supervised Training","publication_year":2021,"publication_date":"2021-02-23","ids":{"openalex":"https://openalex.org/W3129282545","doi":"https://doi.org/10.1109/lra.2021.3061343","mag":"3129282545"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3061343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3061343","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101442384","display_name":"Peixuan Li","orcid":"https://orcid.org/0000-0003-0931-1932"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peixuan Li","raw_affiliation_strings":["Shenyang Institute of Automation, Chinese Academy of Sciences, Institutes for Robotics, and Intelligent Manufacturing, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences and Key Lab of Image Understanding, and Computer Vision, Liaoning Province, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Shenyang Institute of Automation, Chinese Academy of Sciences, Institutes for Robotics, and Intelligent Manufacturing, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences and Key Lab of Image Understanding, and Computer Vision, Liaoning Province, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063377357","display_name":"Huaici Zhao","orcid":"https://orcid.org/0000-0002-7772-8652"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaici Zhao","raw_affiliation_strings":["Shenyang Institute of Automation, Chinese Academy of Sciences, Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences and Key Lab of Image Understanding and Computer Vision, Liaoning Province, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Shenyang Institute of Automation, Chinese Academy of Sciences, Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences and Key Lab of Image Understanding and Computer Vision, Liaoning Province, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101442384"],"corresponding_institution_ids":["https://openalex.org/I142078773","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":5.7641,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.97147059,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"6","issue":"3","first_page":"5565","last_page":"5572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9976999759674072,"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"}},{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7520449161529541},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7084397673606873},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5163611173629761},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5067244172096252},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47980526089668274},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.47667908668518066},{"id":"https://openalex.org/keywords/geometric-transformation","display_name":"Geometric transformation","score":0.4744226336479187},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.45845526456832886},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4547008275985718},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.448227196931839},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.44581368565559387},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.442928284406662},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43749749660491943},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.4206858277320862},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2822420001029968},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2085573971271515}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7520449161529541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7084397673606873},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5163611173629761},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5067244172096252},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47980526089668274},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.47667908668518066},{"id":"https://openalex.org/C56435381","wikidata":"https://www.wikidata.org/wiki/Q1196371","display_name":"Geometric transformation","level":3,"score":0.4744226336479187},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.45845526456832886},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4547008275985718},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.448227196931839},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.44581368565559387},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.442928284406662},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43749749660491943},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.4206858277320862},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2822420001029968},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2085573971271515},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2021.3061343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3061343","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W830076066","https://openalex.org/W2071042563","https://openalex.org/W2095705004","https://openalex.org/W2112796928","https://openalex.org/W2204257188","https://openalex.org/W2468368736","https://openalex.org/W2530816535","https://openalex.org/W2560544142","https://openalex.org/W2592691248","https://openalex.org/W2605189827","https://openalex.org/W2798462325","https://openalex.org/W2798965597","https://openalex.org/W2938672559","https://openalex.org/W2949708697","https://openalex.org/W2951970475","https://openalex.org/W2952229419","https://openalex.org/W2953070460","https://openalex.org/W2954174912","https://openalex.org/W2962807143","https://openalex.org/W2963420686","https://openalex.org/W2963667201","https://openalex.org/W2963794551","https://openalex.org/W2964062501","https://openalex.org/W2964166085","https://openalex.org/W2969050719","https://openalex.org/W2971011093","https://openalex.org/W2972211064","https://openalex.org/W2978426779","https://openalex.org/W2981857055","https://openalex.org/W2998633559","https://openalex.org/W2999947750","https://openalex.org/W3012573144","https://openalex.org/W3034479628","https://openalex.org/W3035574168","https://openalex.org/W3098467253","https://openalex.org/W3108857005","https://openalex.org/W3109240920","https://openalex.org/W3114509423","https://openalex.org/W4285719527","https://openalex.org/W6623329352","https://openalex.org/W6733814495","https://openalex.org/W6760424586","https://openalex.org/W6762913911","https://openalex.org/W6764051988","https://openalex.org/W7009541382"],"related_works":["https://openalex.org/W200819717","https://openalex.org/W1991834176","https://openalex.org/W2032269556","https://openalex.org/W2087054060","https://openalex.org/W2390287618","https://openalex.org/W2126232568","https://openalex.org/W4286728588","https://openalex.org/W2765965840","https://openalex.org/W3015622546","https://openalex.org/W1581085676"],"abstract_inverted_index":{"In":[0,144,169],"this":[1,105,126,145,244],"work,":[2],"we":[3,46,69,94,129,147,171],"propose":[4,130,188],"a":[5,26,39,52,71,100,149,189,228],"novel":[6],"one-stage":[7],"and":[8,56,65,80,82,103,166,187,234],"keypoint-based":[9],"framework":[10],"for":[11,136,156,180,192],"monocular":[12,253],"3D":[13,44,217,254],"object":[14,77,255],"detection":[15,23,218],"using":[16],"only":[17,24,197,267],"RGB":[18,199],"images,":[19,200],"called":[20],"KM3D-Net.":[21],"2D":[22,32],"requires":[25,198],"deep":[27,53],"neural":[28,54],"network":[29,55,108,167,193],"to":[30,61,75,89,109,238],"predict":[31,76],"properties":[33],"of":[34,51,117,152,185,241,249,260],"objects,":[35,186],"as":[36,99,176],"it":[37],"is":[38,245],"semanticity-aware":[40],"task.":[41],"For":[42],"image-based":[43],"detection,":[45],"argue":[47],"that":[48,221],"the":[49,96,107,115,157,173,177,181,214,222,239,246,261],"combination":[50],"geometric":[57,97],"constraints":[58,88,98],"are":[59,142],"needed":[60],"synergistically":[62],"estimate":[63],"appearance-related":[64],"spatial-related":[66],"information.":[67],"Here,":[68],"design":[70],"fully":[72,263],"convolutional":[73],"model":[74,118,196],"keypoints,":[78],"dimension,":[79],"orientation,":[81],"combine":[83],"these":[84],"with":[85,266],"perspective":[86],"geometry":[87],"compute":[90],"position":[91,184],"attributes.":[92],"Further,":[93],"reformulate":[95],"differentiable":[101],"version":[102],"embed":[104],"in":[106,120,231,252],"reduce":[110],"running":[111],"time":[112],"while":[113],"maintaining":[114],"consistency":[116],"outputs":[119],"an":[121,131],"end-to-end":[122],"fashion.":[123],"Benefiting":[124],"from":[125],"simple":[127],"structure,":[128],"effective":[132],"semi-supervised":[133,250],"training":[134,140],"strategy":[135],"settings":[137],"where":[138],"labeled":[139,269],"data":[141,270],"scarce.":[143],"strategy,":[146],"enforce":[148],"consensus":[150],"prediction":[151],"two":[153],"shared-weights":[154],"KM3D-Net":[155,223],"same":[158],"unlabeled":[159],"image":[160],"under":[161],"different":[162],"input":[163],"augmentation":[164],"conditions":[165],"regularization.":[168,194],"particular,":[170],"unify":[172],"coordinate-dependent":[174],"augmentations":[175],"affine":[178],"transformation":[179],"differential":[182],"recovering":[183],"keypoint-dropout":[190],"module":[191],"Our":[195],"without":[201],"synthetic":[202],"data,":[203],"instance":[204],"segmentation,":[205],"CAD":[206],"model,":[207],"or":[208],"depth":[209],"generator.":[210],"Extensive":[211],"experiments":[212],"on":[213,271],"popular":[215],"KITTI":[216],"dataset":[219],"indicate":[220],"surpasses":[224],"state-of-the-art":[225],"methods":[226,265],"by":[227],"large":[229],"margin":[230],"both":[232],"efficiency":[233],"accuracy.":[235],"And":[236],"also,":[237],"best":[240],"our":[242],"knowledge,":[243],"first":[247],"application":[248],"learning":[251],"detection.":[256],"We":[257],"surpass":[258],"most":[259],"previous":[262],"supervised":[264],"13%":[268],"KITTI.":[272]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}