{"id":"https://openalex.org/W7125949292","doi":"https://doi.org/10.1109/smc58881.2025.11343061","title":"TemVLT: Vision-Language Tracking via Mamba-based Temporal Information Learning","display_name":"TemVLT: Vision-Language Tracking via Mamba-based Temporal Information Learning","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125949292","doi":"https://doi.org/10.1109/smc58881.2025.11343061"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343061","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 Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-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/A5122839410","display_name":"Qishuai Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qishuai Nie","raw_affiliation_strings":["Huazhong University of Science and Technology,National Key Laboratory of Science and Technology on Multispectral Information Processing, School of Artificial Intelligence and Automation,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,National Key Laboratory of Science and Technology on Multispectral Information Processing, School of Artificial Intelligence and Automation,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108993656","display_name":"ZhiMin Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhimin Weng","raw_affiliation_strings":["Huazhong University of Science and Technology,National Key Laboratory of Science and Technology on Multispectral Information Processing, School of Artificial Intelligence and Automation,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,National Key Laboratory of Science and Technology on Multispectral Information Processing, School of Artificial Intelligence and Automation,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124084849","display_name":"Yuehuan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuehuan Wang","raw_affiliation_strings":["Huazhong University of Science and Technology,National Key Laboratory of Science and Technology on Multispectral Information Processing, School of Artificial Intelligence and Automation,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,National Key Laboratory of Science and Technology on Multispectral Information Processing, School of Artificial Intelligence and Automation,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5122839410"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.72957203,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2601","last_page":"2608"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6165000200271606,"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":0.6165000200271606,"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":0.09449999779462814,"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/T10860","display_name":"Speech and Audio Processing","score":0.0478999987244606,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/frame","display_name":"Frame (networking)","score":0.5814999938011169},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5745999813079834},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5461000204086304},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4839000105857849},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.44940000772476196},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.40529999136924744},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.40059998631477356},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072999715805054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5873000025749207},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5814999938011169},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5745999813079834},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5461000204086304},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.44940000772476196},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.40059998631477356},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3601999878883362},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2779954242","wikidata":"https://www.wikidata.org/wiki/Q6031227","display_name":"Information structure","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25429999828338623},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343061","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 Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6506732702255249,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2470394683","https://openalex.org/W2747053578","https://openalex.org/W2794744029","https://openalex.org/W2891033863","https://openalex.org/W2898200825","https://openalex.org/W2963109634","https://openalex.org/W3106542916","https://openalex.org/W3173871266","https://openalex.org/W3174225630","https://openalex.org/W3181069167","https://openalex.org/W4286251267","https://openalex.org/W4292828074","https://openalex.org/W4312751983","https://openalex.org/W4313156423","https://openalex.org/W4385569741","https://openalex.org/W4386066081","https://openalex.org/W4386066459","https://openalex.org/W4386075643","https://openalex.org/W4386083067","https://openalex.org/W4393147957","https://openalex.org/W4393159185","https://openalex.org/W4393159404","https://openalex.org/W4402702990","https://openalex.org/W4402704627","https://openalex.org/W4402753915","https://openalex.org/W4402981768"],"related_works":[],"abstract_inverted_index":{"The":[0],"vision-language":[1,52],"tracking":[2,99],"(VLT)":[3],"aims":[4],"to":[5,19,38,49,126],"improve":[6,127],"target":[7,28],"localization":[8],"by":[9],"leveraging":[10],"natural":[11],"language":[12,74,116,131],"(NL)":[13],"descriptions.":[14],"However,":[15],"most":[16,114],"trackers":[17],"fail":[18],"account":[20],"for":[21,166],"the":[22,25,31,77,104,112,120,128,136,150,154,168,171,182],"discrepancy":[23],"between":[24],"dynamically":[26],"evolving":[27],"states":[29,92,165],"and":[30,82,84,141,160,179],"initial":[32],"NL":[33],"during":[34],"tracking,":[35],"which":[36,72,110,145],"leads":[37],"limitations":[39],"in":[40,59,93,96,123,149,163,186],"model":[41],"performance.":[42,100],"Therefore,":[43],"developing":[44],"effective":[45],"temporal":[46,86,147],"modeling":[47],"methods":[48],"resolve":[50],"this":[51,62],"ambiguity":[53],"represents":[54],"a":[55,66],"critical":[56],"research":[57],"challenge":[58],"VLT.":[60],"In":[61],"paper,":[63],"we":[64,102,134],"propose":[65],"video-level":[67],"VLT":[68,187],"framework":[69],"called":[70],"TemVLT,":[71],"aggregates":[73,111],"information":[75,87,122,148],"under":[76],"guidance":[78],"of":[79,130,153,170,184],"dynamic":[80,124],"template,":[81],"stores":[83,161],"transmits":[85],"across":[88],"frames":[89],"via":[90,157],"hidden":[91,164],"Mamba,":[94],"resulting":[95],"more":[97],"robust":[98],"Specifically,":[101],"design":[103],"Language":[105],"Adaptive":[106],"Aggregation":[107],"(LAA)":[108],"module,":[109,144],"Top-k":[113],"important":[115],"tokens":[117],"based":[118],"on":[119,176],"appearance":[121],"template":[125],"stability":[129],"information.":[132],"Additionally,":[133],"introduce":[135],"Mambabased":[137],"Temporal":[138],"Information":[139],"Capture":[140],"Storage":[142],"(TCS)":[143],"captures":[146],"visual":[151],"features":[152],"current":[155],"frame":[156],"Mamba":[158],"layers":[159],"it":[162],"enhancing":[167],"context-awareness":[169],"next":[172],"frame.":[173],"Extensive":[174],"results":[175],"TNL2K,":[177],"LaSOT,":[178],"OTB99-Lang":[180],"confirm":[181],"superiority":[183],"TemVLT":[185],"over":[188],"existing":[189],"trackers.":[190]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-29T00:00:00"}
