{"id":"https://openalex.org/W4410613906","doi":"https://doi.org/10.1109/tcsvt.2025.3572810","title":"Multi-Granularity Language-Guided Training for Multi-Object Tracking","display_name":"Multi-Granularity Language-Guided Training for Multi-Object Tracking","publication_year":2025,"publication_date":"2025-05-22","ids":{"openalex":"https://openalex.org/W4410613906","doi":"https://doi.org/10.1109/tcsvt.2025.3572810"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3572810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3572810","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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":null,"display_name":"Yuhao Li","orcid":"https://orcid.org/0009-0002-7902-1949"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Li","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0002-7902-1949","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037129512","display_name":"Jiale Cao","orcid":"https://orcid.org/0000-0002-5160-6841"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Cao","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-5160-6841","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083105774","display_name":"Muzammal Naseer","orcid":"https://orcid.org/0000-0001-7663-7161"},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Muzammal Naseer","raw_affiliation_strings":["Department of Computer Science, Khalifa University, Abu Dhabi, United Arab Emirates","Department of Computer Science, Khalifa University, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0001-7663-7161","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Khalifa University, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I176601375"]},{"raw_affiliation_string":"Department of Computer Science, Khalifa University, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I176601375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100673745","display_name":"Yu Zhu","orcid":"https://orcid.org/0000-0002-2480-0569"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhu","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-2480-0569","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778199","display_name":"Jinqiu Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinqiu Sun","raw_affiliation_strings":["School of Astronautics, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-0551-6351","affiliations":[{"raw_affiliation_string":"School of Astronautics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028235866","display_name":"Yanning Zhang","orcid":"https://orcid.org/0000-0002-2977-8057"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanning Zhang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-2977-8057","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100760570","display_name":"Fahad Shahbaz Khan","orcid":"https://orcid.org/0000-0002-4263-3143"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Fahad Shahbaz Khan","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0002-4263-3143","affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5311,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.82426494,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"35","issue":"11","first_page":"11001","last_page":"11012"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.5705999732017517,"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":0.5705999732017517,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.5042999982833862,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/granularity","display_name":"Granularity","score":0.7972767353057861},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7447219491004944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.584516704082489},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5641095042228699},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5239707827568054},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.49084049463272095},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4418369233608246},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.41725432872772217},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19538035988807678}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.7972767353057861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7447219491004944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.584516704082489},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5641095042228699},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5239707827568054},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.49084049463272095},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4418369233608246},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.41725432872772217},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19538035988807678},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/tcsvt.2025.3572810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3572810","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4568926294","display_name":null,"funder_award_id":"U19B2037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4589748232","display_name":null,"funder_award_id":"61901384","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":56,"referenced_works":["https://openalex.org/W2141822239","https://openalex.org/W2252355370","https://openalex.org/W2511791013","https://openalex.org/W2920942303","https://openalex.org/W2950703532","https://openalex.org/W2963449390","https://openalex.org/W3035442500","https://openalex.org/W3035564946","https://openalex.org/W3084173793","https://openalex.org/W3086436251","https://openalex.org/W3094000868","https://openalex.org/W3095753995","https://openalex.org/W3097885906","https://openalex.org/W3104732503","https://openalex.org/W3106763294","https://openalex.org/W3149623420","https://openalex.org/W3167949052","https://openalex.org/W3179985441","https://openalex.org/W3214993537","https://openalex.org/W4285130999","https://openalex.org/W4286904999","https://openalex.org/W4312473433","https://openalex.org/W4312689495","https://openalex.org/W4312747482","https://openalex.org/W4312961069","https://openalex.org/W4313072323","https://openalex.org/W4317794944","https://openalex.org/W4319866011","https://openalex.org/W4322576511","https://openalex.org/W4324291273","https://openalex.org/W4362501010","https://openalex.org/W4382240009","https://openalex.org/W4385575022","https://openalex.org/W4386071841","https://openalex.org/W4386071948","https://openalex.org/W4386075559","https://openalex.org/W4386075937","https://openalex.org/W4386076116","https://openalex.org/W4386076180","https://openalex.org/W4386076204","https://openalex.org/W4386076331","https://openalex.org/W4386083103","https://openalex.org/W4386590375","https://openalex.org/W4387969510","https://openalex.org/W4389352686","https://openalex.org/W4390874117","https://openalex.org/W4390874237","https://openalex.org/W4393149283","https://openalex.org/W4394596409","https://openalex.org/W4401043461","https://openalex.org/W4402727808","https://openalex.org/W4402754265","https://openalex.org/W4403791540","https://openalex.org/W4403843361","https://openalex.org/W4405974723","https://openalex.org/W4409366257"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W4285271403","https://openalex.org/W2542007731","https://openalex.org/W2968379562","https://openalex.org/W2091015105","https://openalex.org/W4388689193","https://openalex.org/W2110899030","https://openalex.org/W29633852","https://openalex.org/W2985362983","https://openalex.org/W4327670844"],"abstract_inverted_index":{"Most":[0],"existing":[1,121],"multi-object":[2,88],"tracking":[3,8,89],"methods":[4],"typically":[5],"learn":[6],"visual":[7,38,69,110,146,157,212],"features":[9,34,63,111,147,158],"via":[10],"maximizing":[11],"dis-similarities":[12],"of":[13,19,45,101,177,196,200],"different":[14,99],"instances":[15],"and":[16,52,105,172,223],"minimizing":[17],"similarities":[18],"the":[20,75,145,155,175,178,186,208],"same":[21],"instance.":[22],"While":[23],"such":[24,48,78],"a":[25,86],"feature":[26],"learning":[27,32],"scheme":[28],"achieves":[29,192],"promising":[30],"performance,":[31],"discriminative":[33,114],"solely":[35],"based":[36],"on":[37,161,167],"information":[39,66,97,136],"is":[40],"challenging":[41],"especially":[42],"in":[43,73,198],"case":[44],"environmental":[46,79],"interference":[47],"as":[49],"occlusion,":[50],"blur":[51],"domain":[53],"variance.":[54],"In":[55],"this":[56,82],"work,":[57],"we":[58,84,119],"argue":[59],"that":[60,93],"multi-modal":[61],"language-driven":[62],"provide":[64],"complementary":[65],"to":[67,77,112,143,182,207],"classical":[68],"features,":[70],"thereby":[71],"aiding":[72],"improving":[74],"robustness":[76],"interference.":[80],"To":[81,116],"end,":[83],"propose":[85],"new":[87],"framework,":[90],"named":[91],"LG-MOT,":[92,118],"explicitly":[94],"leverages":[95],"language":[96,127,135,163],"at":[98,228],"levels":[100],"granularity":[102],"(scene-and":[103],"instance-level)":[104],"combines":[106],"it":[107],"with":[108,124],"standard":[109,156],"obtain":[113],"representations.":[115],"develop":[117],"annotate":[120],"MOT":[122],"datasets":[123],"scene-and":[125,133],"instance-level":[126,134],"descriptions.":[128,164],"We":[129],"then":[130],"encode":[131],"both":[132],"into":[137],"high-dimensional":[138],"embeddings,":[139],"which":[140],"are":[141,226],"utilized":[142],"guide":[144],"during":[148],"training.":[149],"At":[150],"inference,":[151],"our":[152,190,215],"LG-MOT":[153,191,216],"uses":[154],"without":[159],"relying":[160],"annotated":[162],"Extensive":[165],"experiments":[166],"three":[168],"benchmarks,":[169],"MOT17,":[170],"DanceTrack":[171,187],"SportsMOT,":[173],"reveal":[174],"merits":[176],"proposed":[179],"contributions":[180],"leading":[181],"state-of-the-art":[183],"performance.":[184],"On":[185],"test":[188],"set,":[189],"an":[193],"absolute":[194],"gain":[195],"2.2%":[197],"terms":[199],"target":[201],"object":[202],"association":[203],"(IDF1":[204],"score),":[205],"compared":[206],"baseline":[209],"using":[210],"only":[211],"features.":[213],"Further,":[214],"exhibits":[217],"strong":[218],"cross-domain":[219],"generalizability.":[220],"Source":[221],"code":[222],"pre-trained":[224],"models":[225],"available":[227],"https://github.com/WesLee88524/LG-MOT.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}