{"id":"https://openalex.org/W4304479854","doi":"https://doi.org/10.1109/tpami.2022.3213073","title":"Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers","display_name":"Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304479854","doi":"https://doi.org/10.1109/tpami.2022.3213073","pmid":"https://pubmed.ncbi.nlm.nih.gov/36215373"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3213073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3213073","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5074395949","display_name":"Tianyu Zhu","orcid":"https://orcid.org/0000-0002-6735-0553"},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tianyu Zhu","raw_affiliation_strings":["Department of Electrical and Computer Systems Engineering, Monash University, Clayton, VIC, Australia","Australian Centre for Robotic Vision"],"raw_orcid":"https://orcid.org/0000-0002-6735-0553","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Systems Engineering, Monash University, Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]},{"raw_affiliation_string":"Australian Centre for Robotic Vision","institution_ids":["https://openalex.org/I4210127558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078387676","display_name":"M. Hiller","orcid":"https://orcid.org/0000-0002-8133-0102"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Markus Hiller","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Parkville, VIC, Australia","Australian Centre for Robotic Vision"],"raw_orcid":"https://orcid.org/0000-0002-8133-0102","affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Parkville, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"Australian Centre for Robotic Vision","institution_ids":["https://openalex.org/I4210127558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053292496","display_name":"Mahsa Ehsanpour","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mahsa Ehsanpour","raw_affiliation_strings":["Australian Institute for Machine Learning, The University of Adelaide, Adelaide, SA, Australia","Australian Centre for Robotic Vision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning, The University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]},{"raw_affiliation_string":"Australian Centre for Robotic Vision","institution_ids":["https://openalex.org/I4210127558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044169923","display_name":"Rongkai Ma","orcid":"https://orcid.org/0000-0001-8574-6239"},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rongkai Ma","raw_affiliation_strings":["Department of Electrical and Computer Systems Engineering, Monash University, Clayton, VIC, Australia","Australian Centre for Robotic Vision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Systems Engineering, Monash University, Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]},{"raw_affiliation_string":"Australian Centre for Robotic Vision","institution_ids":["https://openalex.org/I4210127558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017469047","display_name":"Tom Drummond","orcid":"https://orcid.org/0000-0001-8204-5904"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tom Drummond","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Parkville, VIC, Australia","Australian Centre for Robotic Vision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Parkville, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"Australian Centre for Robotic Vision","institution_ids":["https://openalex.org/I4210127558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089444805","display_name":"Ian Reid","orcid":"https://orcid.org/0000-0001-7790-6423"},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ian Reid","raw_affiliation_strings":["Australian Institute for Machine Learning, The University of Adelaide, Adelaide, SA, Australia","Australian Centre for Robotic Vision"],"raw_orcid":"https://orcid.org/0000-0001-7790-6423","affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning, The University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]},{"raw_affiliation_string":"Australian Centre for Robotic Vision","institution_ids":["https://openalex.org/I4210127558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034608678","display_name":"Hamid Rezatofighi","orcid":"https://orcid.org/0000-0002-8659-8773"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hamid Rezatofighi","raw_affiliation_strings":["Department of Data Science and AI, Monash University, Clayton, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8659-8773","affiliations":[{"raw_affiliation_string":"Department of Data Science and AI, Monash University, Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8728,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.97339465,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"45","issue":"11","first_page":"12783","last_page":"12797"},"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/T11019","display_name":"Image Enhancement Techniques","score":0.9902999997138977,"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/T12120","display_name":"Air Quality Monitoring and Forecasting","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental 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":0.7681453227996826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6721457242965698},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6685595512390137},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.6319217681884766},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5783295631408691},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5215497016906738},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4971809685230255},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4341152310371399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7681453227996826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6721457242965698},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6685595512390137},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.6319217681884766},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5783295631408691},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5215497016906738},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4971809685230255},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4341152310371399},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2022.3213073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3213073","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:36215373","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36215373","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":111,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1521019969","https://openalex.org/W1568122762","https://openalex.org/W1590686026","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1965449873","https://openalex.org/W2035153336","https://openalex.org/W2082716591","https://openalex.org/W2104828970","https://openalex.org/W2105934661","https://openalex.org/W2124781496","https://openalex.org/W2134529534","https://openalex.org/W2150298366","https://openalex.org/W2150440166","https://openalex.org/W2168356304","https://openalex.org/W2194775991","https://openalex.org/W2209193152","https://openalex.org/W2222512263","https://openalex.org/W2237765446","https://openalex.org/W2252355370","https://openalex.org/W2291627510","https://openalex.org/W2474389331","https://openalex.org/W2511791013","https://openalex.org/W2547098537","https://openalex.org/W2570343428","https://openalex.org/W2579024533","https://openalex.org/W2603203130","https://openalex.org/W2609144136","https://openalex.org/W2739491435","https://openalex.org/W2765741142","https://openalex.org/W2773761519","https://openalex.org/W2798542761","https://openalex.org/W2806630220","https://openalex.org/W2809595622","https://openalex.org/W2889935068","https://openalex.org/W2891254924","https://openalex.org/W2891268664","https://openalex.org/W2895150009","https://openalex.org/W2897582990","https://openalex.org/W2900871370","https://openalex.org/W2903855329","https://openalex.org/W2920942303","https://openalex.org/W2921601546","https://openalex.org/W2962766617","https://openalex.org/W2962803115","https://openalex.org/W2962855257","https://openalex.org/W2962923976","https://openalex.org/W2963323244","https://openalex.org/W2963574614","https://openalex.org/W2964015640","https://openalex.org/W2964019074","https://openalex.org/W2967533163","https://openalex.org/W2972691802","https://openalex.org/W2981393651","https://openalex.org/W2981413347","https://openalex.org/W2983208726","https://openalex.org/W2986732333","https://openalex.org/W2989738721","https://openalex.org/W3011626133","https://openalex.org/W3012922853","https://openalex.org/W3028052296","https://openalex.org/W3034334609","https://openalex.org/W3034679090","https://openalex.org/W3035442500","https://openalex.org/W3035727180","https://openalex.org/W3084173793","https://openalex.org/W3086436251","https://openalex.org/W3094502228","https://openalex.org/W3095753995","https://openalex.org/W3096068180","https://openalex.org/W3096609285","https://openalex.org/W3104218139","https://openalex.org/W3104778224","https://openalex.org/W3106763294","https://openalex.org/W3115390238","https://openalex.org/W3119686997","https://openalex.org/W3165926952","https://openalex.org/W3167949052","https://openalex.org/W3174101598","https://openalex.org/W3174690341","https://openalex.org/W3175455177","https://openalex.org/W3175782503","https://openalex.org/W3176403636","https://openalex.org/W3184439416","https://openalex.org/W3201085568","https://openalex.org/W3204488436","https://openalex.org/W3207452968","https://openalex.org/W3208667955","https://openalex.org/W4206519819","https://openalex.org/W4206706211","https://openalex.org/W4206711703","https://openalex.org/W4213060883","https://openalex.org/W4214494320","https://openalex.org/W4214516362","https://openalex.org/W4246193833","https://openalex.org/W4293398155","https://openalex.org/W4295331127","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6696672603","https://openalex.org/W6750697433","https://openalex.org/W6751040501","https://openalex.org/W6763367864","https://openalex.org/W6763509872","https://openalex.org/W6775253321","https://openalex.org/W6779650541","https://openalex.org/W6784094891","https://openalex.org/W6788023325","https://openalex.org/W6798838024"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W2151749779","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W1690653314","https://openalex.org/W3179968364","https://openalex.org/W2401723157","https://openalex.org/W2065055572"],"abstract_inverted_index":{"Tracking":[0],"a":[1,8,14,52,91],"time-varying":[2],"indefinite":[3],"number":[4],"of":[5,93,112,148,165],"objects":[6,115,132,135],"in":[7,19,37],"video":[9],"sequence":[10],"over":[11,116,157],"time":[12],"remains":[13],"challenge":[15],"despite":[16],"recent":[17],"advances":[18],"the":[20,71,101,105,110,131,134,137,140,163,177],"field.":[21],"Most":[22],"existing":[23],"approaches":[24],"are":[25],"not":[26],"able":[27],"to":[28,63,108,125,136,154],"properly":[29],"handle":[30,64],"multi-object":[31,57,187],"tracking":[32,58,188],"challenges":[33],"such":[34],"as":[35],"occlusion,":[36],"part":[38],"because":[39],"they":[40],"ignore":[41],"long-term":[42,87],"temporal":[43,88,96,141],"information.":[44],"To":[45],"address":[46],"these":[47],"shortcomings,":[48],"we":[49],"present":[50],"MO3TR:":[51],"truly":[53],"end-to-end":[54],"Transformer-based":[55],"online":[56],"(MOT)":[59],"framework":[60,124],"that":[61],"learns":[62],"occlusions,":[65],"track":[66],"initiation":[67],"and":[68,95,98,133],"termination":[69],"without":[70],"need":[72],"for":[73,184],"an":[74],"explicit":[75],"data":[76,107],"association":[77],"module":[78],"or":[79,174],"any":[80],"heuristics.":[81],"MO3TR":[82],"encodes":[83],"object":[84],"interactions":[85],"into":[86],"embeddings":[89],"using":[90],"combination":[92],"spatial":[94,119],"Transformers,":[97],"recursively":[99],"uses":[100],"information":[102],"jointly":[103],"with":[104,173],"input":[106],"estimate":[109],"states":[111],"all":[113,130],"tracked":[114],"time.":[117],"The":[118],"attention":[120,142],"mechanism":[121,143],"enables":[122],"our":[123,152],"learn":[126],"implicit":[127],"representations":[128],"between":[129],"measurements,":[138],"while":[139],"focuses":[144],"on":[145,171,180],"specific":[146],"parts":[147],"past":[149],"information,":[150],"allowing":[151],"approach":[153],"resolve":[155],"occlusions":[156],"multiple":[158,181],"frames.":[159],"Our":[160],"experiments":[161],"demonstrate":[162],"potential":[164],"this":[166],"new":[167],"approach,":[168],"achieving":[169],"results":[170],"par":[172],"better":[175],"than":[176],"current":[178],"state-of-the-art":[179],"MOT":[182],"metrics":[183],"several":[185],"popular":[186],"benchmarks.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}