{"id":"https://openalex.org/W4415708227","doi":"https://doi.org/10.1109/icme59968.2025.11209477","title":"Overcoming Feature Contamination by Unidirectional Information Modeling for Vision-Language Tracking","display_name":"Overcoming Feature Contamination by Unidirectional Information Modeling for Vision-Language Tracking","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708227","doi":"https://doi.org/10.1109/icme59968.2025.11209477"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101595308","display_name":"Jingchao Wang","orcid":"https://orcid.org/0000-0002-4719-6173"},"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":"Jingchao Wang","raw_affiliation_strings":["East China Normal University,School of Data Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Data Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042499646","display_name":"Zhijian Wu","orcid":"https://orcid.org/0000-0002-3040-3287"},"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":"Zhijian Wu","raw_affiliation_strings":["East China Normal University,School of Data Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Data Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453357","display_name":"Wenlong Zhang","orcid":"https://orcid.org/0000-0003-3756-5235"},"institutions":[{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenlong Zhang","raw_affiliation_strings":["Shanghai AI Laboratory,OpenScience Lab,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,OpenScience Lab,Shanghai,China","institution_ids":["https://openalex.org/I4210111163"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429037","display_name":"Wenhui Liu","orcid":"https://orcid.org/0009-0002-7766-8802"},"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":"Wenhui Liu","raw_affiliation_strings":["East China Normal University,School of Data Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Data Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326962","display_name":"Jianwei Zhang","orcid":"https://orcid.org/0000-0002-2103-7473"},"institutions":[{"id":"https://openalex.org/I23171815","display_name":"Zhengzhou University of Light Industry","ror":"https://ror.org/05fwr8z16","country_code":"CN","type":"education","lineage":["https://openalex.org/I23171815"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Zhang","raw_affiliation_strings":["Zhengzhou University of Light Industry,College of Software Engineering,Henan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhengzhou University of Light Industry,College of Software Engineering,Henan,China","institution_ids":["https://openalex.org/I23171815"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101940254","display_name":"Ding-jiang Huang","orcid":"https://orcid.org/0000-0002-5267-9671"},"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":"Dingjiang Huang","raw_affiliation_strings":["East China Normal University,School of Data Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Data Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9498000144958496,"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":0.9498000144958496,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.008100000210106373,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.006099999882280827,"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/robustness","display_name":"Robustness (evolution)","score":0.6542999744415283},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6110000014305115},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5149000287055969},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.38519999384880066},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3828999996185303},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3725000023841858},{"id":"https://openalex.org/keywords/feature-model","display_name":"Feature model","score":0.36410000920295715},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3601999878883362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7222999930381775},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6542999744415283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6126999855041504},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6110000014305115},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5724999904632568},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3725000023841858},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.36410000920295715},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3601999878883362},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.2542000114917755},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":31,"referenced_works":["https://openalex.org/W2470394683","https://openalex.org/W2747053578","https://openalex.org/W2891033863","https://openalex.org/W2962766617","https://openalex.org/W2963109634","https://openalex.org/W2990187711","https://openalex.org/W3012573144","https://openalex.org/W3035453691","https://openalex.org/W3035511673","https://openalex.org/W3108519869","https://openalex.org/W3167536469","https://openalex.org/W3168663926","https://openalex.org/W3173871266","https://openalex.org/W3174225630","https://openalex.org/W3181069167","https://openalex.org/W3204554907","https://openalex.org/W3205239873","https://openalex.org/W3214586131","https://openalex.org/W4289535600","https://openalex.org/W4292828074","https://openalex.org/W4312532041","https://openalex.org/W4312751983","https://openalex.org/W4313156423","https://openalex.org/W4380520387","https://openalex.org/W4382461147","https://openalex.org/W4386065544","https://openalex.org/W4386075643","https://openalex.org/W4387969322","https://openalex.org/W4390874039","https://openalex.org/W4402753915","https://openalex.org/W4402754150"],"related_works":[],"abstract_inverted_index":{"Benefiting":[0],"from":[1,30],"the":[2,31,35,41,48,51,68,90,101,117,125],"advantages":[3],"of":[4,43,50,107,129],"multi-modal":[5],"learning,":[6],"Vision-Language":[7,74],"Tracking":[8],"shows":[9],"greater":[10],"potential":[11],"than":[12],"Visual":[13],"Tracking.":[14,75],"Existing":[15],"work":[16],"utilizes":[17],"one-stream":[18],"structures":[19],"to":[20,65,84,103],"fuse":[21,67],"vision":[22],"and":[23,70,93,127,133],"language":[24,36,44,69,87,113],"features,":[25],"resulting":[26],"in":[27,116],"noise":[28],"propagation":[29],"search":[32,94],"region":[33,95],"into":[34,89],"features.":[37],"This":[38,99],"contamination":[39,115],"weakens":[40],"guidance":[42,88],"information,":[45],"consequently":[46],"limiting":[47],"robustness":[49],"tracking":[52],"model.":[53],"To":[54],"solve":[55],"this":[56],"problem,":[57],"we":[58,77],"propose":[59],"a":[60,79],"Unidirectional":[61],"Information":[62],"modeling":[63],"(UITracker)":[64],"explicitly":[66],"visual":[71,91],"features":[72],"for":[73],"Specifically,":[76],"introduce":[78],"plug-and-play":[80],"lightweight":[81],"modal":[82],"adapter":[83],"unidirectionally":[85],"inject":[86],"template":[92],"across":[96],"all":[97],"layers.":[98],"allows":[100],"tracker":[102],"make":[104],"full":[105],"use":[106],"rich":[108],"semantic":[109],"information":[110],"while":[111],"overcoming":[112],"feature":[114,118],"interaction":[119],"process.":[120],"Extensive":[121],"ablation":[122],"studies":[123],"demonstrate":[124],"superiority":[126],"effectiveness":[128],"our":[130],"UITracker.":[131],"Code":[132],"raw":[134],"results":[135],"are":[136],"available":[137],"at":[138],"https://github.com/jcwang0602/UITrack.":[139]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}