{"id":"https://openalex.org/W7140657560","doi":"https://doi.org/10.1145/3803863","title":"GVLTrack: Global Vision-Language Tracking with Multi-Stage Modal Fusion","display_name":"GVLTrack: Global Vision-Language Tracking with Multi-Stage Modal Fusion","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7140657560","doi":"https://doi.org/10.1145/3803863"},"language":"en","primary_location":{"id":"doi:10.1145/3803863","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3803863","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5108239813","display_name":"Jian Tao","orcid":"https://orcid.org/0000-0002-1809-5138"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Tao","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1809-5138","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003029072","display_name":"Sixian Chan","orcid":"https://orcid.org/0000-0001-8916-1174"},"institutions":[{"id":"https://openalex.org/I4210123686","display_name":"Quzhou University","ror":"https://ror.org/024nfx323","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210123686"]},{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sixian Chan","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China and Zhejiang Key Laboratory of Intelligent Manufacturing for Aerodynamic Equipment, Quzhou University, Quzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-8916-1174","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China and Zhejiang Key Laboratory of Intelligent Manufacturing for Aerodynamic Equipment, Quzhou University, Quzhou, Zhejiang, China","institution_ids":["https://openalex.org/I55712492","https://openalex.org/I4210123686"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130674504","display_name":"Bai Cong","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Bai","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6177-3862","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaoqin Zhang","orcid":"https://orcid.org/0000-0003-0958-7285"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqin Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0958-7285","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.30413484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"5","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9605000019073486,"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":0.9605000019073486,"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":0.007499999832361937,"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":0.005200000014156103,"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/fuse","display_name":"Fuse (electrical)","score":0.784600019454956},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6743999719619751},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.6626999974250793},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6606000065803528},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6552000045776367},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.550599992275238},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5497999787330627},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5382999777793884},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5058000087738037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8348000049591064},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.784600019454956},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6743999719619751},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.6626999974250793},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6606000065803528},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6552000045776367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.608299970626831},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.599399983882904},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.550599992275238},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5497999787330627},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5382999777793884},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5058000087738037},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.48579999804496765},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4724999964237213},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3158999979496002},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2872999906539917},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C188540687","wikidata":"https://www.wikidata.org/wiki/Q63105","display_name":"Topicalization","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3803863","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3803863","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2672841088","display_name":null,"funder_award_id":"LZ26F020008, LY23F020023, LQZSZ25E050002","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G3467313957","display_name":null,"funder_award_id":"RF-A2024013","funder_id":"https://openalex.org/F4554350417","funder_display_name":"Fundamental Research Funds for the Provincial Universities of Zhejiang"},{"id":"https://openalex.org/G5239251208","display_name":null,"funder_award_id":"U24A20242, 62272267","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/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4554350417","display_name":"Fundamental Research Funds for the Provincial Universities of Zhejiang","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2250539671","https://openalex.org/W2251512949","https://openalex.org/W2470394683","https://openalex.org/W2747053578","https://openalex.org/W2799058067","https://openalex.org/W2962766617","https://openalex.org/W2963341956","https://openalex.org/W2963534981","https://openalex.org/W2985509612","https://openalex.org/W2987906097","https://openalex.org/W3010072143","https://openalex.org/W3016744474","https://openalex.org/W3092819179","https://openalex.org/W3106542916","https://openalex.org/W3108235634","https://openalex.org/W3138516171","https://openalex.org/W3173871266","https://openalex.org/W3181069167","https://openalex.org/W3205239873","https://openalex.org/W3214586131","https://openalex.org/W4206553383","https://openalex.org/W4211088651","https://openalex.org/W4214506192","https://openalex.org/W4214759957","https://openalex.org/W4221152520","https://openalex.org/W4226219503","https://openalex.org/W4283825622","https://openalex.org/W4292828074","https://openalex.org/W4307123832","https://openalex.org/W4312906427","https://openalex.org/W4313036965","https://openalex.org/W4313145013","https://openalex.org/W4313307856","https://openalex.org/W4324327989","https://openalex.org/W4353111412","https://openalex.org/W4361806794","https://openalex.org/W4386076142","https://openalex.org/W4388271799","https://openalex.org/W4392551959","https://openalex.org/W4400075398","https://openalex.org/W4402753324","https://openalex.org/W4402753915","https://openalex.org/W4402830565","https://openalex.org/W4404402940","https://openalex.org/W4405599438","https://openalex.org/W4408930345","https://openalex.org/W4409346692","https://openalex.org/W4410552372","https://openalex.org/W4413145064","https://openalex.org/W4413234096"],"related_works":[],"abstract_inverted_index":{"In":[0],"general,":[1],"local":[2,25,86],"Visual-Language":[3],"(VL)":[4],"trackers":[5],"search":[6],"targets":[7],"around":[8],"the":[9,24,29,32,39,78,81,94,123,140],"previous":[10,90],"bounding":[11,124],"box":[12,125],"by":[13],"initial":[14],"VL":[15],"annotations.":[16],"However,":[17],"there":[18],"is":[19,156],"an":[20,56],"inherent":[21],"contradiction":[22],"between":[23],"searching":[26],"perspective":[27],"of":[28,85,142],"tracker":[30],"and":[31,112,121,135],"orientation":[33],"descriptions":[34],"in":[35,49,80],"language":[36],"conducted":[37],"under":[38],"global":[40],"perspective.":[41],"Furthermore,":[42],"most":[43],"methods":[44],"only":[45],"fuse":[46,118],"modality":[47,120],"information":[48],"a":[50,66],"single":[51],"stage,":[52],"which":[53],"tends":[54],"to":[55,92,117],"insufficient":[57],"relation":[58],"modeling.":[59],"To":[60],"address":[61],"these":[62],"issues,":[63],"we":[64],"propose":[65],"Global":[67],"Vision-Language":[68],"Tracker":[69],"(GVLTrack)":[70],"with":[71],"multi-stage":[72],"modal":[73,101],"fusion.":[74],"First,":[75],"it":[76,155],"tracks":[77],"target":[79],"entire":[82],"image":[83],"instead":[84],"tracking":[87],"based":[88],"on":[89,132],"results":[91],"resolve":[93],"above":[95],"contradiction.":[96],"Second,":[97],"GVLTrack":[98],"incorporates":[99],"three":[100],"interaction":[102],"modules:":[103],"Consistent":[104],"Relationship":[105],"Modeling":[106],"(CRM),":[107],"VL-Guided":[108],"Query":[109],"(VLQ)":[110],"Initialization,":[111],"Recurrent":[113],"Cross-Modal":[114],"Decoder":[115],"(RC-Decoder)":[116],"vision-language":[119],"refine":[122],"progressively":[126],"comprehensively.":[127],"We":[128],"conduct":[129],"extensive":[130],"experiments":[131],"several":[133],"benchmarks":[134],"achieve":[136],"competitive":[137],"performance,":[138],"demonstrating":[139],"effectiveness":[141],"our":[143],"approach.":[144],"The":[145],"code":[146],"will":[147],"be":[148],"made":[149],"publicly":[150],"available":[151],"as":[152,154],"soon":[153],"accepted.":[157]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-27T00:00:00"}
