{"id":"https://openalex.org/W3200258663","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533588","title":"Multi-Scale Spatial Transformer Network for LiDAR-Camera 3D Object Detection","display_name":"Multi-Scale Spatial Transformer Network for LiDAR-Camera 3D Object Detection","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3200258663","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533588","mag":"3200258663"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5054428215","display_name":"Zhifan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhifan Wang","raw_affiliation_strings":["School of Computer Science and Engineering Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101831461","display_name":"Xiaohong Zhang","orcid":"https://orcid.org/0000-0001-6781-5034"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohong Zhang","raw_affiliation_strings":["School of Computer Science and Engineering Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749560","display_name":"Shidong Wang","orcid":"https://orcid.org/0000-0003-1023-1286"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shidong Wang","raw_affiliation_strings":["School of Engineering Newcastle University, Newcastle, UK"],"affiliations":[{"raw_affiliation_string":"School of Engineering Newcastle University, Newcastle, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114417858","display_name":"Tong Xin","orcid":"https://orcid.org/0000-0001-5479-262X"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tong Xin","raw_affiliation_strings":["School of Computing Newcastle University, Newcastle, UK"],"affiliations":[{"raw_affiliation_string":"School of Computing Newcastle University, Newcastle, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064008061","display_name":"Haofeng Zhang","orcid":"https://orcid.org/0000-0002-4039-7618"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haofeng Zhang","raw_affiliation_strings":["School of Computer Science and Engineering Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037595310","display_name":"Jianfeng Lu","orcid":"https://orcid.org/0000-0002-9190-507X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Lu","raw_affiliation_strings":["School of Computer Science and Engineering Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5054428215"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.2907,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.5624919,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9980999827384949,"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/lidar","display_name":"Lidar","score":0.7701213359832764},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7121148705482483},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6972943544387817},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.690507709980011},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.5172668099403381},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5135505199432373},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.47019919753074646},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.45863401889801025},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4420432150363922},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44142892956733704},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2641753554344177},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.24457740783691406},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.17357775568962097},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1252882480621338},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08992299437522888}],"concepts":[{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.7701213359832764},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7121148705482483},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6972943544387817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.690507709980011},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.5172668099403381},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5135505199432373},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.47019919753074646},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.45863401889801025},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4420432150363922},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44142892956733704},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2641753554344177},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.24457740783691406},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.17357775568962097},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1252882480621338},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08992299437522888},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5699999928474426,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W639708223","https://openalex.org/W2115579991","https://openalex.org/W2342242867","https://openalex.org/W2412782625","https://openalex.org/W2468368736","https://openalex.org/W2555618208","https://openalex.org/W2558294288","https://openalex.org/W2560609797","https://openalex.org/W2613718673","https://openalex.org/W2798462325","https://openalex.org/W2798965597","https://openalex.org/W2892830084","https://openalex.org/W2894705404","https://openalex.org/W2897529137","https://openalex.org/W2899302124","https://openalex.org/W2908510526","https://openalex.org/W2911486422","https://openalex.org/W2919534447","https://openalex.org/W2944270177","https://openalex.org/W2949708697","https://openalex.org/W2962807143","https://openalex.org/W2963083779","https://openalex.org/W2963400571","https://openalex.org/W2963438049","https://openalex.org/W2963721253","https://openalex.org/W2963727135","https://openalex.org/W2963809933","https://openalex.org/W2964062501","https://openalex.org/W2968296999","https://openalex.org/W2970095196","https://openalex.org/W2981949127","https://openalex.org/W2991636182","https://openalex.org/W3004237909","https://openalex.org/W3008105217","https://openalex.org/W3023904705","https://openalex.org/W3034602892","https://openalex.org/W3034681945","https://openalex.org/W3035461736","https://openalex.org/W3035651586","https://openalex.org/W3036022788","https://openalex.org/W3096393735","https://openalex.org/W3096399234","https://openalex.org/W3106250896","https://openalex.org/W3117179147","https://openalex.org/W3117804044","https://openalex.org/W3120781197","https://openalex.org/W6618372016","https://openalex.org/W6620707391","https://openalex.org/W6754918364","https://openalex.org/W6755020103","https://openalex.org/W6755742144","https://openalex.org/W6757817989","https://openalex.org/W6763422710","https://openalex.org/W6784697942","https://openalex.org/W6785652829","https://openalex.org/W6787718739"],"related_works":["https://openalex.org/W4321784794","https://openalex.org/W3148227991","https://openalex.org/W1486593826","https://openalex.org/W2771174107","https://openalex.org/W1536965844","https://openalex.org/W2344941099","https://openalex.org/W4322212724","https://openalex.org/W2106788855","https://openalex.org/W3081561710","https://openalex.org/W2477413883"],"abstract_inverted_index":{"Accurate":[0],"3D":[1,59,102],"object":[2,60],"detection":[3,61],"has":[4,156],"recently":[5],"aroused":[6],"interest":[7],"in":[8,51,118,159],"the":[9,30,44,64,81,88,91,98,105,125,133,138,142,145,150],"context":[10],"of":[11,90,100,144,152],"emerging":[12],"autonomous":[13],"driving":[14],"technologies.":[15],"Existing":[16],"approaches":[17],"predominantly":[18],"use":[19],"LiDAR-Camera":[20,58],"fusion":[21,116],"method":[22,72],"to":[23,86,113,120,124],"fulfill":[24],"this":[25,52],"challenging":[26],"task,":[27],"while":[28],"neglecting":[29],"fact":[31],"that":[32],"LiDAR":[33],"and":[34,40,137],"camera":[35],"data":[36],"are":[37,130],"spatially":[38,114],"correlated,":[39],"cannot":[41],"well":[42],"retain":[43],"edge":[45,122],"information.":[46],"To":[47],"solve":[48],"these":[49,153],"problems,":[50],"paper,":[53],"we":[54],"propose":[55],"a":[56],"novel":[57],"method,":[62],"namely":[63],"Multi-scale":[65],"Spatial":[66,107],"Transformer":[67],"Network":[68],"(MST-Net).":[69],"The":[70],"proposed":[71,146],"exploits":[73],"an":[74],"innovative":[75],"spatial":[76],"alignment":[77],"scheme":[78],"based":[79],"on":[80,132],"projection":[82],"transformer":[83],"network":[84],"(PTN)":[85],"mitigate":[87],"effects":[89],"perspective":[92],"view":[93],"caused":[94],"by":[95],"sensors.":[96],"In":[97,148],"process":[99],"generating":[101],"bounding":[103],"boxes,":[104],"Atrous":[106],"Pyramid":[108],"Pool":[109],"(ASPP)":[110],"is":[111],"applied":[112],"aligned":[115],"features":[117],"order":[119],"preserve":[121],"information":[123],"greatest":[126],"extent.":[127],"Extensive":[128],"experiments":[129],"conducted":[131],"popular":[134],"dataset":[135],"KITTI,":[136],"results":[139],"can":[140],"demonstrate":[141],"superiority":[143],"method.":[147],"addition,":[149],"effectiveness":[151],"two":[154],"strategies":[155],"been":[157],"illustrated":[158],"ablation":[160],"studies.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}