{"id":"https://openalex.org/W4391770227","doi":"https://doi.org/10.1109/itsc57777.2023.10422564","title":"BEVMOT: A Multi-Object Detection and Tracking Method in Bird's-Eye-View via Spatiotemporal Transformers","display_name":"BEVMOT: A Multi-Object Detection and Tracking Method in Bird's-Eye-View via Spatiotemporal Transformers","publication_year":2023,"publication_date":"2023-09-24","ids":{"openalex":"https://openalex.org/W4391770227","doi":"https://doi.org/10.1109/itsc57777.2023.10422564"},"language":"en","primary_location":{"id":"doi:10.1109/itsc57777.2023.10422564","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/itsc57777.2023.10422564","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/A5031418416","display_name":"Chenglin Cui","orcid":"https://orcid.org/0009-0005-0539-6053"},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenglin Cui","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,100049","Waytous Inc., Qingdao"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Waytous Inc., Qingdao","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057463199","display_name":"Ruiqi Song","orcid":"https://orcid.org/0000-0003-2261-3724"},"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/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/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiqi Song","raw_affiliation_strings":["Waytous Inc.,Qingdao,266109","College of Surveying and Geo-Informatics, Tongji University, Shanghai, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Waytous Inc.,Qingdao,266109","institution_ids":[]},{"raw_affiliation_string":"College of Surveying and Geo-Informatics, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"State Key Laboratory of 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/A5101680569","display_name":"Xinqing Li","orcid":"https://orcid.org/0009-0001-0293-4144"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"XinQing Li","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,100049","Waytous Inc., Qingdao"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Waytous Inc., Qingdao","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022489675","display_name":"Yunfeng Ai","orcid":"https://orcid.org/0000-0002-2673-1368"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfeng Ai","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,100049","Waytous Inc., Qingdao"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Waytous Inc., Qingdao","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031418416"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10020618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":null,"first_page":"5446","last_page":"5451"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.8100000023841858,"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"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.8100000023841858,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.785099983215332,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.6808000206947327,"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-vision","display_name":"Computer vision","score":0.6913266181945801},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.669022798538208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6163697242736816},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5738887786865234},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5023572444915771},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.45009949803352356},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.23908379673957825},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1534813642501831},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0845843255519867},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06581324338912964}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6913266181945801},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.669022798538208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6163697242736816},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5738887786865234},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5023572444915771},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.45009949803352356},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.23908379673957825},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1534813642501831},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0845843255519867},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06581324338912964},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc57777.2023.10422564","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/itsc57777.2023.10422564","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2603203130","https://openalex.org/W3084173793","https://openalex.org/W3096609285","https://openalex.org/W3106763294","https://openalex.org/W3165926952","https://openalex.org/W3167949052","https://openalex.org/W3207615232","https://openalex.org/W4225422725","https://openalex.org/W4226305814","https://openalex.org/W4292793982","https://openalex.org/W4308080437","https://openalex.org/W4310746146","https://openalex.org/W4312894406","https://openalex.org/W4313054887","https://openalex.org/W4320736629","https://openalex.org/W4382465779","https://openalex.org/W4383066393"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2058170566","https://openalex.org/W2036807459","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2079911747"],"abstract_inverted_index":{"Camera-based":[0],"Bird'View":[1],"(BEV)":[2],"3D":[3,27],"object":[4,22,133,141],"detection":[5,67,126],"is":[6,30],"thoroughly":[7],"challenging":[8],"and":[9,24,68,119,127,136,143,164,190],"essential":[10],"in":[11,38,71,75,94,186],"autonomous":[12,39],"driving":[13,40],"perception":[14,36,110],"system":[15],"for":[16,139],"alleviating":[17],"the":[18,33,45,86,92,95,100,105,109,132,148],"impression":[19],"caused":[20],"by":[21,49,123],"overlap":[23],"occlusion":[25],"effectively.":[26],"multi-object":[28,66,125],"tracking":[29,69,128,137,144,152,155],"one":[31,51],"of":[32,82,116,188],"most":[34],"important":[35],"tasks":[37],"system,":[41],"which":[42,64,130,181],"suffers":[43],"from":[44],"narrow":[46],"view":[47,98],"provided":[48],"only":[50],"single":[52],"camera.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"present":[58],"a":[59,72,76,124],"novel":[60],"framework":[61,74,84],"called":[62],"BEVMOT,":[63],"combines":[65],"task":[70],"unified":[73],"considerable":[77],"inference":[78],"speed.":[79],"The":[80],"encoder":[81],"our":[83,173],"generates":[85],"360":[87],"degree":[88],"panoramic":[89],"image":[90],"around":[91],"ego-car":[93],"bird's":[96],"eyes":[97],"utilizing":[99],"multiple":[101],"cameras":[102],"equipped":[103],"on":[104,178],"car":[106],"to":[107,157],"broaden":[108],"field.":[111],"An":[112],"efficient":[113],"decoder":[114],"composes":[115],"multi-head":[117],"attention":[118,121],"deformable":[120],"following":[122],"head,":[129],"learn":[131],"center":[134],"point":[135],"embedding":[138,156],"acquiring":[140],"boxes":[142],"id":[145],"directly":[146],"without":[147],"NMS":[149],"post-processing.":[150],"Meanwhile,":[151],"branch":[153],"utilize":[154],"initialize":[158],"new":[159],"trajectories,":[160],"update":[161],"existing":[162],"trajectories":[163],"achieve":[165],"data":[166],"association":[167],"frame-by-frame.":[168],"Extensive":[169],"experiments":[170],"show":[171],"that":[172],"approach":[174],"represents":[175],"wonderful":[176],"performance":[177],"NuScenes":[179],"datasets,":[180],"exceeds":[182],"many":[183],"classic":[184],"methods":[185],"term":[187],"AMOTA":[189],"AMOTP":[191],"metrics.":[192]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}