{"id":"https://openalex.org/W7163912881","doi":"https://doi.org/10.1109/tip.2026.3699088","title":"Language Supervised Multi-Camera Multi-Object Tracking","display_name":"Language Supervised Multi-Camera Multi-Object Tracking","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7163912881","doi":"https://doi.org/10.1109/tip.2026.3699088","pmid":"https://pubmed.ncbi.nlm.nih.gov/42258683"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3699088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3699088","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","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/A5003671793","display_name":"Kaige Mao","orcid":"https://orcid.org/0009-0009-3757-7114"},"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":"Kaige Mao","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0009-3757-7114","affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026880795","display_name":"Xiaopeng Hong","orcid":"https://orcid.org/0000-0002-0611-0636"},"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":"Xiaopeng Hong","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-0611-0636","affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138183155","display_name":"Xiaopeng Fan","orcid":"https://orcid.org/0000-0002-9660-3636"},"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":"Xiaopeng Fan","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-9660-3636","affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138141600","display_name":"Wangmeng Zuo","orcid":"https://orcid.org/0000-0002-3330-783X"},"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":"Wangmeng Zuo","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-3330-783X","affiliations":[{"raw_affiliation_string":"Faculty of Computing, 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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73111265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"6123","last_page":"6138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.8657000064849854,"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":0.8657000064849854,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.009399999864399433,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.007000000216066837,"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/tracking","display_name":"Tracking (education)","score":0.48420000076293945},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3707999885082245},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.33379998803138733},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3319999873638153},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.32269999384880066},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.28940001130104065},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.2870999872684479}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7141000032424927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7074999809265137},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.645799994468689},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3707999885082245},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.33379998803138733},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.32269999384880066},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2870999872684479},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2815000116825104},{"id":"https://openalex.org/C32283439","wikidata":"https://www.wikidata.org/wiki/Q1407014","display_name":"Radar tracker","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.27149999141693115},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2581000030040741},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2578999996185303}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3699088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3699088","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:42258683","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42258683","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1533755110","display_name":null,"funder_award_id":"AUGA5710011522","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3048430866","display_name":null,"funder_award_id":"62376070","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4935473288","display_name":null,"funder_award_id":"62076195","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5410805085","display_name":null,"funder_award_id":"62402138","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5430980299","display_name":null,"funder_award_id":"U22B2035","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"multi-camera":[1],"multi-object":[2],"tracking":[3],"(MCMOT)":[4],"algorithms":[5],"are":[6,14],"primarily":[7],"trained":[8,83],"using":[9],"per-detection":[10],"identity":[11],"annotations,":[12],"which":[13,49],"complicated":[15],"to":[16,72],"obtain.":[17],"In":[18,32,63],"contrast,":[19],"labeling":[20],"a":[21,26,39,45,78],"language":[22,116,122],"description":[23],"per-object":[24],"is":[25],"more":[27],"natural":[28],"and":[29,43,121],"human-friendly":[30],"way.":[31],"this":[33],"paper,":[34],"we":[35,65],"explore":[36],"MCMOT":[37],"in":[38,77,90,101,110,118],"language-supervised":[40],"manner":[41],"(LS-MCMOT)":[42],"propose":[44],"novel":[46],"approach":[47,86],"LaVST,":[48],"performs":[50],"language-to-vision":[51],"weakly-supervised":[52],"learning":[53],"based":[54],"on":[55],"reliable":[56],"pseudo-labels":[57],"generated":[58],"via":[59],"tracklet-level":[60],"cross-modality":[61],"matching.":[62],"addition,":[64],"design":[66],"an":[67,105],"ID-aware":[68],"projection":[69,76],"self-correction":[70],"mechanism":[71],"correct":[73],"inaccurate":[74],"image-to-ground":[75],"self-supervised":[79],"manner.":[80],"The":[81],"models":[82],"with":[84],"our":[85],"exhibit":[87],"promising":[88],"performance":[89],"LS-MCMOT.":[91],"Surprisingly,":[92],"they":[93],"perform":[94],"favorably":[95],"against":[96],"state-of-the-art":[97],"identity-supervised":[98],"methods,":[99],"especially":[100],"cross-dataset":[102],"evaluation":[103],"(with":[104],"average":[106],"gain":[107],"by":[108],"20.0%":[109],"IDF1),":[111],"underscoring":[112],"the":[113],"potential":[114],"of":[115],"annotations":[117,123],"MCMOT.":[119],"Codes":[120],"will":[124],"be":[125],"available":[126],"here.":[127]},"counts_by_year":[],"updated_date":"2026-06-20T20:08:15.867695","created_date":"2026-06-09T00:00:00"}