{"id":"https://openalex.org/W4406025400","doi":"https://doi.org/10.1109/tim.2024.3522698","title":"Multigranularity Localization Transformer With Collaborative Understanding for Referring Multiobject Tracking","display_name":"Multigranularity Localization Transformer With Collaborative Understanding for Referring Multiobject Tracking","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406025400","doi":"https://doi.org/10.1109/tim.2024.3522698"},"language":"en","primary_location":{"id":"doi:10.1109/tim.2024.3522698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tim.2024.3522698","pdf_url":null,"source":{"id":"https://openalex.org/S10892749","display_name":"IEEE Transactions on Instrumentation and Measurement","issn_l":"0018-9456","issn":["0018-9456","1557-9662"],"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 Instrumentation and Measurement","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":"https://openalex.org/A5013026483","display_name":"Jiajun Chen","orcid":"https://orcid.org/0009-0008-9584-202X"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Chen","raw_affiliation_strings":["School of Robotics, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0008-9584-202X","affiliations":[{"raw_affiliation_string":"School of Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101566662","display_name":"Jiacheng Lin","orcid":"https://orcid.org/0000-0003-1393-5027"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiacheng Lin","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-1393-5027","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089792276","display_name":"Guojin Zhong","orcid":"https://orcid.org/0000-0002-6054-3694"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojin Zhong","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-6054-3694","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035821863","display_name":"You Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"You Yao","raw_affiliation_strings":["USC Viterbi School of Engineering, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0009-0001-8902-4193","affiliations":[{"raw_affiliation_string":"USC Viterbi School of Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396723","display_name":"Zhiyong Li","orcid":"https://orcid.org/0000-0001-9720-5915"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Li","raw_affiliation_strings":["School of Robotics, Hunan University, Changsha, China","College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-9720-5915","affiliations":[{"raw_affiliation_string":"School of Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0621,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.9033818,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"74","issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9958000183105469,"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":0.9958000183105469,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9883000254631042,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9538999795913696,"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/granularity","display_name":"Granularity","score":0.8937214612960815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7548800706863403},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.6612731218338013},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5694648027420044},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5672847628593445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5436668992042542},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48861151933670044},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.46538272500038147},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.45633500814437866},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.44941577315330505},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.41294926404953003},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3989231586456299},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11689496040344238}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.8937214612960815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7548800706863403},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.6612731218338013},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5694648027420044},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5672847628593445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5436668992042542},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48861151933670044},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.46538272500038147},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.45633500814437866},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.44941577315330505},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.41294926404953003},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3989231586456299},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11689496040344238},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tim.2024.3522698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tim.2024.3522698","pdf_url":null,"source":{"id":"https://openalex.org/S10892749","display_name":"IEEE Transactions on Instrumentation and Measurement","issn_l":"0018-9456","issn":["0018-9456","1557-9662"],"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 Instrumentation and Measurement","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4041047505","display_name":null,"funder_award_id":"U23A20341","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8354495100","display_name":null,"funder_award_id":"U21A20518","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2124781496","https://openalex.org/W2129440600","https://openalex.org/W2138621090","https://openalex.org/W2194775991","https://openalex.org/W2511791013","https://openalex.org/W2603203130","https://openalex.org/W2747053578","https://openalex.org/W2963351448","https://openalex.org/W3084173793","https://openalex.org/W3086436251","https://openalex.org/W3096609285","https://openalex.org/W3104778224","https://openalex.org/W3115390238","https://openalex.org/W3119686997","https://openalex.org/W3165926952","https://openalex.org/W3173871266","https://openalex.org/W3184439416","https://openalex.org/W4226024706","https://openalex.org/W4286904999","https://openalex.org/W4292828074","https://openalex.org/W4293370658","https://openalex.org/W4308351635","https://openalex.org/W4312473433","https://openalex.org/W4312619242","https://openalex.org/W4312751451","https://openalex.org/W4312956471","https://openalex.org/W4313007081","https://openalex.org/W4366668491","https://openalex.org/W4377864668","https://openalex.org/W4382240009","https://openalex.org/W4385245566","https://openalex.org/W4385714071","https://openalex.org/W4386075643","https://openalex.org/W4386076180","https://openalex.org/W4386076331","https://openalex.org/W4386083103","https://openalex.org/W4386621530","https://openalex.org/W4387623721","https://openalex.org/W4388716333","https://openalex.org/W4390889789","https://openalex.org/W4392904092","https://openalex.org/W4392904527","https://openalex.org/W4394596409","https://openalex.org/W4394973509","https://openalex.org/W4401506914","https://openalex.org/W4401870936","https://openalex.org/W4402726924","https://openalex.org/W4402753581","https://openalex.org/W4404612908","https://openalex.org/W6755477022","https://openalex.org/W6757817989","https://openalex.org/W6776700526","https://openalex.org/W6784094891","https://openalex.org/W6784971059","https://openalex.org/W6788023325","https://openalex.org/W6791353385","https://openalex.org/W6798838024","https://openalex.org/W6839144149","https://openalex.org/W6850787431","https://openalex.org/W6852713287","https://openalex.org/W6853002730","https://openalex.org/W6856005155","https://openalex.org/W6856594407","https://openalex.org/W6859424926","https://openalex.org/W6865108300"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W1534274833","https://openalex.org/W2378857091","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093"],"abstract_inverted_index":{"As":[0],"an":[1],"essential":[2],"component":[3],"of":[4,30,100,130,158],"vision-based":[5],"measurement":[6],"(VBM),":[7],"referring":[8],"multiobject":[9],"tracking":[10,15,91],"(RMOT)":[11],"involves":[12],"localizing":[13],"and":[14,60,83,92,110,161,166],"specific":[16],"objects":[17,133],"in":[18,97,163],"video":[19],"frames":[20],"using":[21],"linguistic":[22,31,67,93,118],"prompts":[23,32,119],"as":[24],"references.":[25],"To":[26],"enhance":[27],"the":[28,105,121,127,146,155],"effectiveness":[29],"when":[33],"training,":[34],"we":[35],"introduce":[36],"a":[37,135],"novel":[38],"multigranularity":[39,46,78,84,117],"localization":[40,47,123],"transformer":[41,48],"with":[42,49,116],"collaborative":[43,50],"understanding,":[44],"termed":[45],"understanding":[51,126],"(MGLT).":[52],"Unlike":[53],"previous":[54],"methods":[55],"focused":[56],"on":[57,139,154],"visual-language":[58],"fusion":[59],"postprocessing,":[61],"MGLT":[62,73,144],"reevaluates":[63],"RMOT":[64],"by":[65,103,125],"preventing":[66],"clues":[68],"from":[69],"attenuating":[70],"during":[71],"propagation.":[72],"comprises":[74],"two":[75],"key":[76],"components:":[77],"implicit":[79],"query":[80],"bootstrapping":[81,104],"(MGIQB)":[82],"track-prompt":[85],"alignment":[86],"(MGTPA).":[87],"MGIQB":[88],"ensures":[89],"that":[90,143],"features":[94],"are":[95],"preserved":[96],"later":[98],"layers":[99],"network":[101],"propagation":[102],"model":[106],"to":[107],"generate":[108],"text-relevant":[109],"temporal-enhanced":[111],"track":[112],"queries.":[113],"Simultaneously,":[114],"MGTPA":[115],"enhances":[120],"model\u2019s":[122],"ability":[124],"relative":[128],"positions":[129],"different":[131],"referred":[132],"within":[134],"frame.":[136],"Extensive":[137],"experiments":[138],"well-recognized":[140],"benchmarks":[141],"demonstrate":[142],"achieves":[145],"state-of-the-art":[147],"performance.":[148],"Notably,":[149],"it":[150],"shows":[151],"significant":[152],"improvements":[153],"Refer-KITTI":[156],"dataset":[157],"2.73%,":[159],"7.95%,":[160],"3.18%":[162],"HOTA,":[164],"AssA,":[165],"IDF1,":[167],"respectively.":[168],"The":[169],"code":[170],"will":[171],"be":[172],"available":[173],"athttps://github.com/JiajunChern/MGLT.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}