{"id":"https://openalex.org/W3129083170","doi":"https://doi.org/10.1109/tnnls.2021.3056383","title":"YolTrack: Multitask Learning Based Real-Time Multiobject Tracking and Segmentation for Autonomous Vehicles","display_name":"YolTrack: Multitask Learning Based Real-Time Multiobject Tracking and Segmentation for Autonomous Vehicles","publication_year":2021,"publication_date":"2021-02-13","ids":{"openalex":"https://openalex.org/W3129083170","doi":"https://doi.org/10.1109/tnnls.2021.3056383","mag":"3129083170","pmid":"https://pubmed.ncbi.nlm.nih.gov/33577460"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3056383","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3056383","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Neural Networks and Learning Systems","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/A5086748182","display_name":"Xuepeng Chang","orcid":"https://orcid.org/0000-0002-4011-4243"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuepeng Chang","raw_affiliation_strings":["Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-4011-4243","affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053317950","display_name":"Huihui Pan","orcid":"https://orcid.org/0000-0002-8931-1774"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huihui Pan","raw_affiliation_strings":["Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-8931-1774","affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100726954","display_name":"Weichao Sun","orcid":"https://orcid.org/0000-0001-6837-3821"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weichao Sun","raw_affiliation_strings":["Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0001-6837-3821","affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036684787","display_name":"Huijun Gao","orcid":"https://orcid.org/0000-0001-5554-5452"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijun Gao","raw_affiliation_strings":["Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0001-5554-5452","affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":2.8265,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.92168225,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"32","issue":"12","first_page":"5323","last_page":"5333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","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/T10331","display_name":"Video Surveillance and Tracking Methods","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/T10036","display_name":"Advanced Neural Network Applications","score":0.9980000257492065,"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":0.9840999841690063,"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":0.7852234840393066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7207465171813965},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6857125163078308},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.522024929523468},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.472332626581192},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46998870372772217},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4450909197330475},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4291943311691284},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4260496497154236},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4176260828971863},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.345248818397522},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3330887258052826},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11715057492256165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852234840393066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7207465171813965},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6857125163078308},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.522024929523468},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.472332626581192},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46998870372772217},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4450909197330475},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4291943311691284},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4260496497154236},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4176260828971863},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.345248818397522},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3330887258052826},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11715057492256165},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3056383","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3056383","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:33577460","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33577460","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 neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1801953439","display_name":null,"funder_award_id":"U1964201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4735424120","display_name":null,"funder_award_id":"61773135","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7904895343","display_name":null,"funder_award_id":"61803120","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W2121772968","https://openalex.org/W2273813901","https://openalex.org/W2315797843","https://openalex.org/W2557889580","https://openalex.org/W2562137921","https://openalex.org/W2585173317","https://openalex.org/W2598634450","https://openalex.org/W2603203130","https://openalex.org/W2612072635","https://openalex.org/W2615712430","https://openalex.org/W2624871570","https://openalex.org/W2742332513","https://openalex.org/W2754856369","https://openalex.org/W2767434619","https://openalex.org/W2790484468","https://openalex.org/W2791482549","https://openalex.org/W2792429196","https://openalex.org/W2883780447","https://openalex.org/W2884367402","https://openalex.org/W2888159112","https://openalex.org/W2894176037","https://openalex.org/W2895071559","https://openalex.org/W2923724424","https://openalex.org/W2939112079","https://openalex.org/W2940791172","https://openalex.org/W2950673314","https://openalex.org/W2953920664","https://openalex.org/W2963150697","https://openalex.org/W2963430933","https://openalex.org/W2963498646","https://openalex.org/W2963677766","https://openalex.org/W2964089273","https://openalex.org/W2966182616","https://openalex.org/W2966617434","https://openalex.org/W2977487707","https://openalex.org/W2981537222","https://openalex.org/W2982161360","https://openalex.org/W2990874363","https://openalex.org/W2992899517","https://openalex.org/W2993182889","https://openalex.org/W3003127026","https://openalex.org/W3034681942","https://openalex.org/W3035049382","https://openalex.org/W3035060563","https://openalex.org/W3035410385","https://openalex.org/W3100953775","https://openalex.org/W3106763294","https://openalex.org/W3110159886","https://openalex.org/W3117987410","https://openalex.org/W3216986862","https://openalex.org/W4293849695","https://openalex.org/W6735531217","https://openalex.org/W6739365718","https://openalex.org/W6742702747","https://openalex.org/W6744461261","https://openalex.org/W6745995898","https://openalex.org/W6753767121","https://openalex.org/W6754005058","https://openalex.org/W6754654878","https://openalex.org/W6755347651","https://openalex.org/W6768435530","https://openalex.org/W6771237170","https://openalex.org/W6774781626"],"related_works":["https://openalex.org/W2385949326","https://openalex.org/W2789220062","https://openalex.org/W1967061043","https://openalex.org/W2019566805","https://openalex.org/W1487175407","https://openalex.org/W2068395580","https://openalex.org/W2517104666","https://openalex.org/W3177406559","https://openalex.org/W2375636617","https://openalex.org/W2115674166"],"abstract_inverted_index":{"Modern":[0],"autonomous":[1,83,220],"vehicles":[2],"are":[3,24,140,151,183],"required":[4],"to":[5,60,77,102,142,153],"perform":[6,103],"various":[7],"visual":[8],"perception":[9],"tasks":[10,27,41,182],"for":[11,217],"scene":[12],"construction":[13],"and":[14,20,34,53,120,146,214],"motion":[15],"decision.":[16],"The":[17,123,177],"multiobject":[18],"tracking":[19,70,156],"instance":[21,97,144],"segmentation":[22,98,169],"(MOTS)":[23],"the":[25,32,37,62,65,79,104,155,186,192,198],"main":[26],"since":[28],"they":[29],"directly":[30],"influence":[31],"steering":[33],"braking":[35],"of":[36,64,82,111,180],"car.":[38],"Implementing":[39],"both":[40],"using":[42],"a":[43,68,88,134],"multitask":[44,90],"learning":[45],"neural":[46],"network":[47,66,91,131],"presents":[48],"significant":[49],"challenges":[50],"in":[51,174,211,219],"performance":[52,157],"complexity.":[54],"Current":[55],"work":[56],"on":[57,95,197],"MOTS":[58,105,200,209],"devotes":[59],"improve":[61,154],"precision":[63,121],"with":[67,117,128,163],"two-stage":[69],"by":[71,158,185],"detection":[72],"model,":[73],"which":[74,137],"is":[75,100,215],"difficult":[76],"satisfy":[78],"real-time":[80,89,212],"requirement":[81],"vehicles.":[84,221],"In":[85],"this":[86],"article,":[87],"named":[92],"YolTrack":[93,124,205],"based":[94],"one-stage":[96],"model":[99],"proposed":[101],"task,":[106],"achieving":[107],"an":[108,171],"inference":[109],"speed":[110],"29.5":[112],"frames":[113],"per":[114],"second":[115],"(fps)":[116],"slight":[118],"accuracy":[119],"drop.":[122],"uses":[125],"ShuffleNet":[126],"V2":[127],"feature":[129,164],"pyramid":[130],"(FPN)":[132],"as":[133],"backbone,":[135],"from":[136],"two":[138],"decoders":[139],"extended":[141],"generate":[143],"segments":[145],"embedding":[147],"vectors.":[148],"Segmentation":[149],"masks":[150],"used":[152],"performing":[159],"logic":[160],"AND":[161],"operation":[162],"maps,":[165],"proving":[166],"that":[167,204],"foreground":[168],"plays":[170],"important":[172],"role":[173],"object":[175],"tracking.":[176],"different":[178],"scales":[179],"multiple":[181],"balanced":[184],"optimized":[187],"geometric":[188],"mean":[189],"loss":[190],"during":[191],"training":[193],"phase.":[194],"Experimental":[195],"results":[196],"KITTI":[199],"data":[201],"set":[202],"show":[203],"outperforms":[206],"other":[207],"state-of-the-art":[208],"architectures":[210],"aspect":[213],"appropriate":[216],"deployment":[218]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}