{"id":"https://openalex.org/W4417267315","doi":"https://doi.org/10.1109/iccv51701.2025.01846","title":"ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking","display_name":"ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417267315","doi":"https://doi.org/10.1109/iccv51701.2025.01846"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.19875","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiaokun Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiaokun Feng","raw_affiliation_strings":["School of Artificial Intelligence, UCAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, UCAS","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100718659","display_name":"Sheng Hu","orcid":"https://orcid.org/0000-0002-7983-5304"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyu Hu","raw_affiliation_strings":["School of Physical and Mathematical Sciences, NTU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Physical and Mathematical Sciences, NTU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740143","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0002-0019-4197"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuchen Li","raw_affiliation_strings":["School of Artificial Intelligence, UCAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, UCAS","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705648","display_name":"Deyu Zhang","orcid":"https://orcid.org/0000-0002-5676-1285"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dailing Zhang","raw_affiliation_strings":["School of Artificial Intelligence, UCAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, UCAS","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074710425","display_name":"Min Wu","orcid":"https://orcid.org/0000-0002-0668-8315"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meiqi Wu","raw_affiliation_strings":["CASIA,The Key Laboratory of Cognition and Decision Intelligence for Complex Systems"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CASIA,The Key Laboratory of Cognition and Decision Intelligence for Complex Systems","institution_ids":["https://openalex.org/I4210097554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345321","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0001-6595-7661"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["CASIA,The Key Laboratory of Cognition and Decision Intelligence for Complex Systems"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CASIA,The Key Laboratory of Cognition and Decision Intelligence for Complex Systems","institution_ids":["https://openalex.org/I4210097554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373698","display_name":"Xiao Dong Chen","orcid":"https://orcid.org/0000-0002-0150-0491"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaotang Chen","raw_affiliation_strings":["School of Artificial Intelligence, UCAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, UCAS","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102757787","display_name":"Kai Huang","orcid":"https://orcid.org/0000-0002-0250-6553"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaiqi Huang","raw_affiliation_strings":["School of Artificial Intelligence, UCAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, UCAS","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"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":0.37864145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19850","last_page":"19861"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.4503999948501587,"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":0.4503999948501587,"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":0.3756999969482422,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.017000000923871994,"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/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.6189000010490417},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6140999794006348},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.586899995803833},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.524399995803833},{"id":"https://openalex.org/keywords/sensory-cue","display_name":"Sensory cue","score":0.5013999938964844},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.48969998955726624},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4876999855041504},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4449999928474426},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41589999198913574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7851999998092651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.659600019454956},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.6189000010490417},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6140999794006348},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.586899995803833},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.555400013923645},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.524399995803833},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.5013999938964844},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.48969998955726624},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4876999855041504},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41589999198913574},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.37700000405311584},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.31779998540878296},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3125},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2921000123023987},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25780001282691956},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.2549999952316284},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.2547999918460846}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.19875","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.19875","pdf_url":"https://arxiv.org/pdf/2507.19875","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.19875","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.19875","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.19875","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.19875","pdf_url":"https://arxiv.org/pdf/2507.19875","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6893741669","display_name":null,"funder_award_id":"62176255","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"tracking":[1],"aims":[2],"to":[3,48,55,61,85,105,126,131,220],"locate":[4],"the":[5,9,22,50,57,62,65,73,80,113,132,135,138,160,176,190,198],"target":[6,51,82,89,133,162,204],"object":[7],"in":[8,21,30,95],"video":[10],"sequence":[11],"using":[12],"a":[13,17,148,237],"template":[14],"patch":[15],"and":[16,67,212,234,243],"language":[18],"description":[19],"provided":[20],"initial":[23,74,81],"frame.":[24],"To":[25],"achieve":[26,202],"robust":[27,171],"tracking,":[28],"especially":[29],"complex":[31,96],"long-term":[32,97],"scenarios":[33],"that":[34,122,188],"reflect":[35],"real-world":[36],"conditions":[37],"as":[38],"recently":[39],"highlighted":[40],"by":[41],"MGIT,":[42],"it":[43],"is":[44,100],"essential":[45],"not":[46],"only":[47,78],"characterize":[49],"features":[52,59],"but":[53],"also":[54],"utilize":[56,222],"context":[58,216,224],"related":[60],"target.":[63],"However,":[64],"visual":[66,177,184,194],"textual":[68,141,199,210],"target-context":[69,185],"cues":[70,104,157],"derived":[71],"from":[72],"prompts":[75,115],"generally":[76],"align":[77],"with":[79,116,159,192],"state.":[83],"Due":[84],"their":[86],"dynamic":[87,161],"nature,":[88],"states":[90,163],"are":[91],"constantly":[92],"changing,":[93],"particularly":[94],"sequences.":[98],"It":[99],"intractable":[101],"for":[102,112,175],"these":[103],"continuously":[106],"guide":[107],"Vision-Language":[108],"Trackers":[109],"(VLTs).":[110],"Furthermore,":[111],"text":[114],"diverse":[117],"expressions,":[118],"our":[119],"experiments":[120,230],"reveal":[121],"existing":[123],"VLTs":[124],"struggle":[125],"discern":[127],"which":[128,153],"words":[129,205,217],"pertain":[130],"or":[134],"context,":[136],"complicating":[137],"utilization":[139],"of":[140],"cues.":[142,195],"In":[143],"this":[144],"work,":[145],"we":[146,179,201],"present":[147],"novel":[149],"tracker":[150,191],"named":[151],"ATCTrack,":[152],"can":[154],"obtain":[155],"multimodal":[156],"Aligned":[158],"through":[164],"comprehensive":[165],"Target-Context":[166],"feature":[167],"modeling,":[168],"thereby":[169],"achieving":[170],"tracking.":[172],"Specifically,":[173],"(1)":[174],"modality,":[178,200],"propose":[180],"an":[181,214],"effective":[182],"temporal":[183],"modeling":[186],"approach":[187],"provides":[189],"timely":[193],"(2)":[196],"For":[197],"precise":[203],"identification":[206],"solely":[207],"based":[208],"on":[209,231],"content,":[211],"design":[213],"innovative":[215],"calibration":[218],"method":[219],"adaptively":[221],"auxiliary":[223],"words.":[225],"(3)":[226],"We":[227],"conduct":[228],"extensive":[229],"mainstream":[232],"benchmarks":[233],"ATCTrack":[235],"achieves":[236],"new":[238],"SOTA":[239],"performance.":[240],"The":[241],"code":[242],"models":[244],"will":[245],"be":[246],"released":[247],"at:":[248],"https://github.com/XiaokunFeng/ATCTrack.":[249]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}