{"id":"https://openalex.org/W4391769570","doi":"https://doi.org/10.1109/itsc57777.2023.10422272","title":"MSIT-Det: Multi-Scale Feature Aggregation with Iterative Transformer Networks for 3D Object Detection","display_name":"MSIT-Det: Multi-Scale Feature Aggregation with Iterative Transformer Networks for 3D Object Detection","publication_year":2023,"publication_date":"2023-09-24","ids":{"openalex":"https://openalex.org/W4391769570","doi":"https://doi.org/10.1109/itsc57777.2023.10422272"},"language":"en","primary_location":{"id":"doi:10.1109/itsc57777.2023.10422272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc57777.2023.10422272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)","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/A5062325535","display_name":"Xi Li","orcid":"https://orcid.org/0000-0002-3015-513X"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]},{"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xi Li","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049","Shanghai Artificial Intelligence Laboratory, Shanghai, China","State Key Laboratory for Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"State Key Laboratory for Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066796478","display_name":"Yuanyuan Chen","orcid":"https://orcid.org/0000-0002-5358-9213"},"institutions":[{"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"]},{"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Chen","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049","State Key Laboratory for Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory for Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076992681","display_name":"Yisheng Lv","orcid":"https://orcid.org/0000-0002-7565-4979"},"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yisheng Lv","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049","State Key Laboratory for Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory for Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062325535"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210100255","https://openalex.org/I4210112150","https://openalex.org/I4210165038","https://openalex.org/I4391012619"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20114524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5510","last_page":"5515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9969000220298767,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9940000176429749,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7621952891349792},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.6045699119567871},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5752165913581848},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5261375904083252},{"id":"https://openalex.org/keywords/lidar","display_name":"Lidar","score":0.512817919254303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5023448467254639},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4890066385269165},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4358879327774048},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4357709288597107},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4249919652938843},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42357584834098816},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4178909957408905},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3644726872444153},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3225443363189697},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2815242409706116},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10132494568824768},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09293043613433838}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7621952891349792},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.6045699119567871},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5752165913581848},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5261375904083252},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.512817919254303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5023448467254639},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4890066385269165},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4358879327774048},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4357709288597107},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4249919652938843},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42357584834098816},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4178909957408905},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3644726872444153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3225443363189697},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2815242409706116},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10132494568824768},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09293043613433838},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc57777.2023.10422272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc57777.2023.10422272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G794781215","display_name":null,"funder_award_id":"2022ZD0162200","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2139137304","https://openalex.org/W2555618208","https://openalex.org/W2897529137","https://openalex.org/W2962766617","https://openalex.org/W3008105217","https://openalex.org/W3034494113","https://openalex.org/W3034602892","https://openalex.org/W3111535274","https://openalex.org/W3113028524","https://openalex.org/W3118341329","https://openalex.org/W3130358931","https://openalex.org/W3130614392","https://openalex.org/W3153465022","https://openalex.org/W3154570906","https://openalex.org/W3159028934","https://openalex.org/W3159695738","https://openalex.org/W3166089996","https://openalex.org/W3171887460","https://openalex.org/W3172560577","https://openalex.org/W3176287975","https://openalex.org/W3185205840","https://openalex.org/W3200064570","https://openalex.org/W3205005447","https://openalex.org/W3205437216","https://openalex.org/W4200632008","https://openalex.org/W4214755140","https://openalex.org/W4214777292","https://openalex.org/W4224231583","https://openalex.org/W4225506583","https://openalex.org/W4226512186","https://openalex.org/W4291653324","https://openalex.org/W4293811845","https://openalex.org/W4296501493","https://openalex.org/W4308079993","https://openalex.org/W4308080010","https://openalex.org/W4308211562","https://openalex.org/W4312081617","https://openalex.org/W4312317609","https://openalex.org/W4312941264","https://openalex.org/W4313039600","https://openalex.org/W4321366760","https://openalex.org/W4322730856","https://openalex.org/W4367182782","https://openalex.org/W4376166839","https://openalex.org/W4377298394","https://openalex.org/W4385245566","https://openalex.org/W4386608660"],"related_works":["https://openalex.org/W4319317934","https://openalex.org/W2901265155","https://openalex.org/W2956374172","https://openalex.org/W4319837668","https://openalex.org/W4308071650","https://openalex.org/W3188333020","https://openalex.org/W4281783339","https://openalex.org/W1964041166","https://openalex.org/W4293094720","https://openalex.org/W2739701376"],"abstract_inverted_index":{"LiDAR-based":[0],"perception":[1],"is":[2,24],"pivotal":[3],"for":[4,18,26,41],"ensuring":[5],"the":[6,78,111,117,121],"safety":[7],"of":[8,123,135],"autonomous":[9],"driving.":[10],"Despite":[11],"numerous":[12],"detection":[13,37,136],"methods":[14,132],"being":[15],"continually":[16],"optimized":[17],"both":[19],"timeliness":[20],"and":[21,54,91,110,138],"accuracy,":[22],"there":[23],"room":[25],"improvement.":[27],"This":[28],"paper":[29],"introduces":[30],"MSIT-Det,":[31],"an":[32],"innovative":[33],"two-stage":[34],"3D":[35],"object":[36],"framework":[38],"designed":[39],"explicitly":[40],"LiDAR":[42],"point":[43],"cloud":[44],"data.":[45],"MSIT-Det":[46],"distinguishes":[47],"itself":[48],"by":[49],"emphasizing":[50],"on":[51,116],"proposal":[52],"regions":[53],"exploiting":[55],"a":[56],"multi-scale":[57],"graph":[58,65],"structured":[59],"feature":[60,74,93],"aggregation":[61],"(MSGA)":[62],"to":[63,86,89,105,130],"extract":[64],"geometric":[66],"information":[67],"across":[68],"diverse":[69],"scales.":[70],"To":[71,96],"further":[72],"enhance":[73],"expression,":[75],"we":[76,100],"propose":[77],"iterative":[79],"Transformer":[80],"networks":[81],"(ITNet),":[82],"which":[83],"integrates":[84],"attention":[85,88],"concreteness,":[87],"abstraction,":[90],"unified":[92],"representation":[94],"modules.":[95],"optimize":[97],"our":[98],"framework,":[99],"incorporate":[101],"parallel":[102],"loss":[103],"functions":[104],"simultaneously":[106],"refine":[107],"each":[108],"scale":[109],"final":[112],"output.":[113],"Experimental":[114],"results":[115],"KITTI":[118],"dataset":[119],"demonstrate":[120],"effectiveness":[122],"MSIT-":[124],"Det,":[125],"showing":[126],"promising":[127],"performance":[128],"compared":[129],"existing":[131],"in":[133],"terms":[134],"accuracy":[137],"efficiency.":[139]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}