{"id":"https://openalex.org/W7136139045","doi":"https://doi.org/10.1109/tpami.2026.3674357","title":"ChatTracker: Enhancing Visual Tracking via LLM-Driven Iterative Description Refinement","display_name":"ChatTracker: Enhancing Visual Tracking via LLM-Driven Iterative Description Refinement","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7136139045","doi":"https://doi.org/10.1109/tpami.2026.3674357","pmid":"https://pubmed.ncbi.nlm.nih.gov/41838509"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3674357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3674357","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":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/sis_research/11084","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yu Zhang","orcid":"https://orcid.org/0009-0003-4135-2969"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-4135-2969","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126352281","display_name":"Yiming Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Sun","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-8125-4730","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mi Zhang","orcid":"https://orcid.org/0000-0003-3567-3478"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mi Zhang","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3567-3478","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051817486","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0003-1072-008X"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yu","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-7723-6489","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101499520","display_name":"Shaoxiang Chen","orcid":"https://orcid.org/0000-0002-7627-7124"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoxiang Chen","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7627-7124","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428136","display_name":"Yanfang Li","orcid":"https://orcid.org/0000-0002-1487-365X"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9427-7665","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Changbo Wang","orcid":"https://orcid.org/0000-0001-8940-6418"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changbo Wang","raw_affiliation_strings":["School of Data Science and Engineering, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8940-6418","affiliations":[{"raw_affiliation_string":"School of Data Science and Engineering, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062252650","display_name":"Jianke Zhu","orcid":"https://orcid.org/0000-0003-1831-0106"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianke Zhu","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1831-0106","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122153177","display_name":"Steven C.H. Hoi","orcid":null},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Steven C.H. Hoi","raw_affiliation_strings":["Singapore Management University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4584-3453","affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25681904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"8","first_page":"8831","last_page":"8847"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5410000085830688,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5410000085830688,"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/T10028","display_name":"Topic Modeling","score":0.15039999783039093,"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"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.10029999911785126,"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/iterative-method","display_name":"Iterative method","score":0.43630000948905945},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4284000098705292},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.41190001368522644},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4032999873161316},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34389999508857727},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.32429999113082886},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.32359999418258667},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.31940001249313354}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7121999859809875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7075999975204468},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7003999948501587},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.31940001249313354},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.305400013923645},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2583000063896179},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2026.3674357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3674357","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:41838509","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41838509","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},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-12085","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/11084","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TPAMI.2026.3674357","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-12085","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/11084","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TPAMI.2026.3674357","raw_type":"Journal Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2368578961","display_name":null,"funder_award_id":"62376244","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3301940929","display_name":null,"funder_award_id":"62472178","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3585723920","display_name":null,"funder_award_id":"62572194","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"object":[1,8],"tracking":[2,53,98,134,160,175,209],"focuses":[3],"on":[4,14,67],"locating":[5],"a":[6,10,141,170,185],"target":[7,158],"within":[9],"video":[11],"sequence":[12],"based":[13],"an":[15],"initial":[16],"bounding":[17],"box.":[18],"Recently,":[19],"Vision-Language":[20],"(VL)":[21],"trackers":[22,42,49,224],"have":[23],"been":[24],"proposed":[25,238],"to":[26,32,63,113,127,148,188,206,288],"utilize":[27,164],"additional":[28],"natural":[29],"language":[30,78,130,213,268],"descriptions":[31,131,155,214],"enhance":[33,133,218],"versatility":[34],"in":[35,50,95,120,232,291],"various":[36,222,245],"applications.":[37],"Despite":[38],"this":[39,58,81,108,137],"potential,":[40],"VL":[41,97,174,194,223,292],"still":[43],"underperform":[44],"the":[45,73,86,115,121,151,157,190,219,233,242,272,278,283],"State-of-the-Art":[46],"(SoTA)":[47],"visual":[48,196,246],"terms":[51],"of":[52,76,92,117,156,192,221,244,274],"accuracy.":[54],"We":[55,276],"find":[56],"that":[57,89,201],"inferiority":[59],"is":[60,177],"primarily":[61],"due":[62],"their":[64],"heavy":[65],"reliance":[66],"manual":[68,104,279],"textual":[69,93,285],"annotations,":[70],"which":[71,179,270],"include":[72],"frequent":[74],"provision":[75],"ambiguous":[77,152],"descriptions.":[79],"In":[80,211],"paper,":[82],"we":[83,110,139],"identify,":[84],"for":[85],"first":[87],"time,":[88],"over":[90],"10%":[91],"annotations":[94,231],"existing":[96,207],"datasets":[99],"suffer":[100],"from":[101],"inaccuracies":[102],"through":[103],"evaluation.":[105],"To":[106,136,162],"address":[107],"problem,":[109],"propose":[111,140],"ChatTracker":[112,202,217],"leverage":[114],"wealth":[116],"world":[118],"knowledge":[119],"Multimodal":[122],"Large":[123],"Language":[124,144],"Model":[125],"(MLLM)":[126],"generate":[128],"high-quality":[129],"and":[132,153,195,225,257,282],"performance.":[135],"end,":[138],"novel":[142],"Reflection-based":[143],"Description":[145],"Refinement":[146],"Module":[147],"iteratively":[149],"refine":[150],"inaccurate":[154],"with":[159],"feedback.":[161],"further":[163],"semantic":[165],"information":[166],"produced":[167],"by":[168,216,264],"MLLM,":[169],"simple":[171],"yet":[172],"effective":[173],"framework":[176,239],"proposed,":[178],"can":[180,240],"be":[181],"easily":[182],"integrated":[183],"as":[184],"plug-and-play":[186],"module":[187],"boost":[189],"performance":[191,205,220,243],"both":[193],"trackers.":[197],"Experimental":[198],"results":[199,281],"show":[200],"achieves":[203],"comparable":[204],"SoTA":[208],"methods.":[210],"addition,":[212],"generated":[215,284],"exhibit":[226],"better":[227],"text-to-image":[228],"alignment":[229],"than":[230],"original":[234],"dataset.":[235],"Moreover,":[236],"our":[237],"improve":[241],"tasks,":[247],"including":[248],"Referring":[249,253,258],"Expression":[250,254],"Comprehension":[251],"(REC),":[252],"Segmentation":[255,261],"(RES),":[256],"Video":[259],"Object":[260],"(R-VOS)":[262],"tasks":[263],"providing":[265],"more":[266],"accurate":[267],"descriptions,":[269,286],"demonstrates":[271],"universality":[273],"ChatTracker.":[275],"release":[277],"evaluation":[280],"aiming":[287],"drive":[289],"advancements":[290],"tracking.":[293]},"counts_by_year":[],"updated_date":"2026-07-07T06:14:10.401900","created_date":"2026-03-17T00:00:00"}