{"id":"https://openalex.org/W4385804784","doi":"https://doi.org/10.1109/cvprw59228.2023.00020","title":"MotionTrack: End-to-End Transformer-based Multi-Object Tracking with LiDAR-Camera Fusion","display_name":"MotionTrack: End-to-End Transformer-based Multi-Object Tracking with LiDAR-Camera Fusion","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4385804784","doi":"https://doi.org/10.1109/cvprw59228.2023.00020"},"language":"en","primary_location":{"id":"doi:10.1109/cvprw59228.2023.00020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw59228.2023.00020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","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/A5019905451","display_name":"Ce Zhang","orcid":"https://orcid.org/0000-0002-4344-5259"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ce Zhang","raw_affiliation_strings":["Motional","Virginia Tech"],"affiliations":[{"raw_affiliation_string":"Motional","institution_ids":[]},{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082240875","display_name":"Chengjie Zhang","orcid":"https://orcid.org/0000-0001-6885-1678"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengjie Zhang","raw_affiliation_strings":["Motional","Virginia Tech"],"affiliations":[{"raw_affiliation_string":"Motional","institution_ids":[]},{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037416485","display_name":"Yiluan Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiluan Guo","raw_affiliation_strings":["Motional"],"affiliations":[{"raw_affiliation_string":"Motional","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091288403","display_name":"Lingji Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingji Chen","raw_affiliation_strings":["Motional"],"affiliations":[{"raw_affiliation_string":"Motional","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003315670","display_name":"Michael Happold","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Happold","raw_affiliation_strings":["Motional"],"affiliations":[{"raw_affiliation_string":"Motional","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5019905451"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":2.8001,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92395681,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":1.0,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":1.0,"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":0.9973999857902527,"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/T12597","display_name":"Fire Detection and Safety Systems","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/computer-science","display_name":"Computer science","score":0.6940574645996094},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.633311927318573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6266303062438965},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6177875995635986},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6131336092948914},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5444096922874451},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.5118052363395691},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5097271800041199},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4420171082019806},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3239934742450714},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.23955518007278442},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.18877047300338745},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15279126167297363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6940574645996094},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.633311927318573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6266303062438965},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6177875995635986},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6131336092948914},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5444096922874451},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.5118052363395691},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5097271800041199},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4420171082019806},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3239934742450714},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.23955518007278442},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.18877047300338745},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15279126167297363},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"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/cvprw59228.2023.00020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw59228.2023.00020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","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":78,"referenced_works":["https://openalex.org/W1857884451","https://openalex.org/W2183182206","https://openalex.org/W2194775991","https://openalex.org/W2252355370","https://openalex.org/W2341459421","https://openalex.org/W2558899534","https://openalex.org/W2603203130","https://openalex.org/W2920942303","https://openalex.org/W2963727135","https://openalex.org/W2963940252","https://openalex.org/W2964060597","https://openalex.org/W2964064111","https://openalex.org/W2964333437","https://openalex.org/W2968296999","https://openalex.org/W2981393651","https://openalex.org/W2996012538","https://openalex.org/W3012922853","https://openalex.org/W3025976100","https://openalex.org/W3035574168","https://openalex.org/W3056795521","https://openalex.org/W3095753995","https://openalex.org/W3104218139","https://openalex.org/W3106763294","https://openalex.org/W3115390238","https://openalex.org/W3119686997","https://openalex.org/W3190141195","https://openalex.org/W3196204376","https://openalex.org/W3199048838","https://openalex.org/W3206199195","https://openalex.org/W3208137297","https://openalex.org/W3214282487","https://openalex.org/W3216604356","https://openalex.org/W4200051644","https://openalex.org/W4214516362","https://openalex.org/W4221155237","https://openalex.org/W4224992933","https://openalex.org/W4225422725","https://openalex.org/W4283795368","https://openalex.org/W4285812971","https://openalex.org/W4286904999","https://openalex.org/W4293255939","https://openalex.org/W4295689624","https://openalex.org/W4304479854","https://openalex.org/W4310467366","https://openalex.org/W4312473433","https://openalex.org/W4312689495","https://openalex.org/W4312707458","https://openalex.org/W4313117614","https://openalex.org/W4321232487","https://openalex.org/W4382203297","https://openalex.org/W4385245566","https://openalex.org/W4386075680","https://openalex.org/W4386918917","https://openalex.org/W4390189588","https://openalex.org/W4390190223","https://openalex.org/W6687483927","https://openalex.org/W6739901393","https://openalex.org/W6745896446","https://openalex.org/W6757384202","https://openalex.org/W6760782946","https://openalex.org/W6768435530","https://openalex.org/W6775253321","https://openalex.org/W6782246188","https://openalex.org/W6788023325","https://openalex.org/W6794207797","https://openalex.org/W6795368335","https://openalex.org/W6802459829","https://openalex.org/W6804018845","https://openalex.org/W6804183503","https://openalex.org/W6809664228","https://openalex.org/W6809883588","https://openalex.org/W6810561648","https://openalex.org/W6810820667","https://openalex.org/W6840663683","https://openalex.org/W6841703415","https://openalex.org/W6843199799","https://openalex.org/W6843334029","https://openalex.org/W6850116609"],"related_works":["https://openalex.org/W2922421953","https://openalex.org/W2548411843","https://openalex.org/W2811496562","https://openalex.org/W1497101000","https://openalex.org/W2624549608","https://openalex.org/W2309573947","https://openalex.org/W2355810106","https://openalex.org/W2146154945","https://openalex.org/W86724867","https://openalex.org/W1983333094"],"abstract_inverted_index":{"Multiple":[0,97],"Object":[1,98],"Tracking":[2],"(MOT)":[3],"is":[4,62],"crucial":[5],"to":[6,54,63,93,150,158],"autonomous":[7,73],"vehicle":[8],"perception.":[9],"End-to-end":[10],"transformer-based":[11,46,82,89],"algorithms,":[12],"which":[13],"detect":[14],"and":[15,87,96,104,130,154],"track":[16,55],"objects":[17,56],"simultaneously,":[18],"show":[19],"great":[20],"potential":[21],"for":[22,68,148],"the":[23,69,115,126,128,131,152,160],"MOT":[24,47,70,95],"task.":[25],"However,":[26],"most":[27],"existing":[28],"methods":[29],"focus":[30],"on":[31,114],"image-based":[32],"tracking":[33],"with":[34,50,57,119],"a":[35,65,81,88,141],"single":[36],"object":[37],"category.":[38],"In":[39,136],"this":[40],"paper,":[41],"we":[42,138],"propose":[43],"an":[44,72],"end-to-end":[45],"algorithm":[48,78],"(MotionTrack)":[49],"multi-modality":[51],"sensor":[52],"inputs":[53],"multiple":[58],"classes.":[59],"Our":[60],"objective":[61],"establish":[64],"transformer":[66],"baseline":[67,122],"in":[71],"driving":[74],"environment.":[75],"The":[76,102],"proposed":[77],"consists":[79],"of":[80],"data":[83],"association":[84],"(DA)":[85],"module":[86,92],"query":[90],"enhancement":[91],"achieve":[94,107],"Detection":[99],"(MOD)":[100],"simultaneously.":[101],"MotionTrack":[103],"its":[105],"variations":[106],"better":[108],"results":[109],"(AMOTA":[110],"score":[111],"at":[112],"0.55)":[113],"nuScenes":[116],"dataset":[117],"compared":[118],"other":[120],"classical":[121],"models,":[123],"such":[124],"as":[125],"AB3DMOT,":[127],"CenterTrack,":[129],"probabilistic":[132],"3D":[133],"Kalman":[134],"filter.":[135],"addition,":[137],"prove":[139],"that":[140],"modified":[142],"attention":[143],"mechanism":[144],"can":[145],"be":[146],"utilized":[147],"DA":[149],"accomplish":[151],"MOT,":[153],"aggregate":[155],"history":[156],"features":[157],"enhance":[159],"MOD":[161],"performance.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}