{"id":"https://openalex.org/W4404403752","doi":"https://doi.org/10.1109/tits.2026.3659175","title":"Efficient Feature Aggregation and Scale-Aware Regression for Monocular 3-D Object Detection","display_name":"Efficient Feature Aggregation and Scale-Aware Regression for Monocular 3-D Object Detection","publication_year":2026,"publication_date":"2026-02-12","ids":{"openalex":"https://openalex.org/W4404403752","doi":"https://doi.org/10.1109/tits.2026.3659175"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2026.3659175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2026.3659175","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/view/author/57667.html>","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yifan Wang","orcid":"https://orcid.org/0009-0003-0950-8142"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Wang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0003-0950-8142","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038412984","display_name":"Xiaochen Yang","orcid":"https://orcid.org/0000-0002-9299-5951"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaochen Yang","raw_affiliation_strings":["School of Mathematics and Statistics, University of Glasgow, Glasgow, U.K"],"raw_orcid":"https://orcid.org/0000-0002-9299-5951","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, University of Glasgow, Glasgow, U.K","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fanqi Pu","orcid":"https://orcid.org/0009-0001-7299-1072"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fanqi Pu","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0001-7299-1072","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111663001","display_name":"Qingmin Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingmin Liao","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-7509-3964","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wenming Yang","orcid":"https://orcid.org/0000-0002-2506-1286"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenming Yang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2506-1286","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"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":1,"citation_normalized_percentile":{"value":0.004345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"27","issue":"6","first_page":"6605","last_page":"6618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9944000244140625,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9944000244140625,"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":0.9916999936103821,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9868000149726868,"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/scale","display_name":"Scale (ratio)","score":0.6992700099945068},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6814162731170654},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6694296598434448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6514722108840942},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6382616758346558},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.533400297164917},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5284115076065063},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5203287601470947},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.497085839509964},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40668249130249023},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.21150872111320496},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1810888946056366},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.13353422284126282},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0960814356803894}],"concepts":[{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6992700099945068},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6814162731170654},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6694296598434448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6514722108840942},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6382616758346558},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.533400297164917},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5284115076065063},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5203287601470947},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.497085839509964},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40668249130249023},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21150872111320496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1810888946056366},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13353422284126282},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0960814356803894},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tits.2026.3659175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2026.3659175","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","raw_type":"journal-article"},{"id":"pmh:oai:eprints.gla.ac.uk:380111","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/57667.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Articles"},{"id":"pmh:oai:arXiv.org:2411.02747","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.02747","pdf_url":"https://arxiv.org/pdf/2411.02747","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,"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":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2411.02747","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2411.02747","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.02747","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,"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:eprints.gla.ac.uk:380111","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/57667.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Articles"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3181256067","display_name":null,"funder_award_id":"KJZD20 231023094700001","funder_id":"https://openalex.org/F4320335972","funder_display_name":"Special Foundation for the Development of Strategic Emerging Industries of Shenzhen"},{"id":"https://openalex.org/G924216758","display_name":null,"funder_award_id":"2023YFB4302200","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},{"id":"https://openalex.org/F4320335972","display_name":"Special Foundation for the Development of Strategic Emerging Industries of Shenzhen","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W200819717","https://openalex.org/W2032269556","https://openalex.org/W1991834176","https://openalex.org/W2944448661","https://openalex.org/W2064421702","https://openalex.org/W4253756925","https://openalex.org/W2805523177","https://openalex.org/W2131956013","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Monocular":[0],"3D":[1,29,110,124,201],"object":[2,24,81,157],"detection":[3,20,111],"has":[4],"received":[5],"considerable":[6],"attention":[7,132],"for":[8,65,204],"its":[9],"simplicity":[10],"and":[11,26,50,61,86,96,121,142,166,212,223],"low":[12],"cost.":[13],"Existing":[14],"methods":[15],"typically":[16],"follow":[17],"conventional":[18],"2D":[19,162],"paradigms,":[21],"first":[22],"locating":[23],"centers":[25],"then":[27,167],"predicting":[28],"attributes":[30],"via":[31],"neighboring":[32],"features.":[33],"However,":[34],"these":[35,102],"approaches":[36],"mainly":[37],"focus":[38],"on":[39,209],"local":[40],"information,":[41],"which":[42],"may":[43],"limit":[44],"the":[45,56,172,210],"model\u2019s":[46],"global":[47,57,135],"context":[48,58],"awareness":[49],"result":[51],"in":[52,69,80,191],"missed":[53],"detections,":[54],"as":[55],"provides":[59],"semantic":[60,140,173],"spatial":[62],"dependencies":[63],"essential":[64],"detecting":[66],"small":[67],"objects":[68],"cluttered":[70],"or":[71],"occluded":[72],"environments.":[73],"In":[74],"addition,":[75],"due":[76],"to":[77,93,138,147],"large":[78],"variation":[79],"scales":[82],"across":[83,152],"different":[84,153],"scenes":[85],"depths,":[87],"inaccurate":[88],"receptive":[89,136,194],"fields":[90],"often":[91],"lead":[92],"background":[94],"noise":[95],"degraded":[97],"feature":[98,181,186],"representation.":[99],"To":[100],"address":[101],"issues,":[103],"we":[104],"introduce":[105],"MonoASRH,":[106],"a":[107,134,179],"novel":[108],"monocular":[109],"framework":[112],"composed":[113],"of":[114],"Efficient":[115],"Hybrid":[116],"Feature":[117],"Aggregation":[118],"Module":[119],"(EH-FAM)":[120],"Adaptive":[122],"Scale-Aware":[123],"Regression":[125],"Head":[126],"(ASRH).":[127],"Specifically,":[128],"EH-FAM":[129,177],"employs":[130],"multi-head":[131],"with":[133,171],"field":[137,195],"extract":[139],"features":[141,151,170,174],"leverages":[143],"lightweight":[144],"convolutional":[145],"modules":[146],"efficiently":[148],"aggregate":[149],"visual":[150],"scales,":[154],"enhancing":[155],"small-scale":[156],"detection.":[158],"The":[159,184,221],"ASRH":[160,190],"encodes":[161],"bounding":[163],"box":[164],"dimensions":[165],"fuses":[168],"scale":[169,198],"aggregated":[175],"by":[176],"through":[178],"scale-semantic":[180,185],"fusion":[182,187],"module.":[183],"module":[188],"guides":[189],"learning":[192],"dynamic":[193],"offsets,":[196],"incorporating":[197],"information":[199],"into":[200],"position":[202],"prediction":[203],"better":[205],"scale-awareness.":[206],"Extensive":[207],"experiments":[208],"KITTI":[211],"Waymo":[213],"datasets":[214],"demonstrate":[215],"that":[216],"MonoASRH":[217],"achieves":[218],"state-of-the-art":[219],"performance.":[220],"code":[222],"model":[224],"are":[225],"released":[226],"athttps://github.com/WYFDUT/MonoASRH":[227]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-03T07:22:36.454288","created_date":"2024-11-16T00:00:00"}