{"id":"https://openalex.org/W4396505919","doi":"https://doi.org/10.1109/tcsvt.2024.3395352","title":"One-Stream Stepwise Decreasing for Vision-Language Tracking","display_name":"One-Stream Stepwise Decreasing for Vision-Language Tracking","publication_year":2024,"publication_date":"2024-04-30","ids":{"openalex":"https://openalex.org/W4396505919","doi":"https://doi.org/10.1109/tcsvt.2024.3395352"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3395352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3395352","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","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/A5061681385","display_name":"Guangtong Zhang","orcid":"https://orcid.org/0009-0001-1513-0313"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guangtong Zhang","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China","Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058101262","display_name":"Bineng Zhong","orcid":"https://orcid.org/0000-0003-3423-1539"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bineng Zhong","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China","Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049287545","display_name":"Qihua Liang","orcid":"https://orcid.org/0000-0003-2353-5246"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihua Liang","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China","Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019827327","display_name":"Zhiyi Mo","orcid":"https://orcid.org/0009-0008-6123-363X"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]},{"id":"https://openalex.org/I4210107865","display_name":"Wuzhou University","ror":"https://ror.org/01vv37n49","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210107865"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyi Mo","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China","Professor in the School of Data Science and Software Engineering, Wuzhou University, Wuzhou, China","Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Professor in the School of Data Science and Software Engineering, Wuzhou University, Wuzhou, China","institution_ids":["https://openalex.org/I4210107865"]},{"raw_affiliation_string":"Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100773117","display_name":"Ning Li","orcid":"https://orcid.org/0009-0006-3867-6753"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Li","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China","Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025660318","display_name":"Shuxiang Song","orcid":"https://orcid.org/0000-0003-0280-2640"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuxiang Song","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China","Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, China","institution_ids":["https://openalex.org/I29739308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5061681385"],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":9.6662,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.98477788,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"34","issue":"10","first_page":"9053","last_page":"9063"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.8597999811172485,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.8597999811172485,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T12031","display_name":"Speech and dialogue systems","score":0.760200023651123,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.7488999962806702,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-vision","display_name":"Computer vision","score":0.6295117139816284},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6213250756263733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5889955759048462},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4654354155063629},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3309262990951538},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09622830152511597}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6295117139816284},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6213250756263733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5889955759048462},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4654354155063629},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3309262990951538},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09622830152511597},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3395352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3395352","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8575283240","display_name":null,"funder_award_id":"U23A20383","funder_id":"https://openalex.org/F4320334117","funder_display_name":"National Natural Science Foundation of China-Shenzhen Robotics Research Center Project"}],"funders":[{"id":"https://openalex.org/F4320334117","display_name":"National Natural Science Foundation of China-Shenzhen Robotics Research Center Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2592463526","https://openalex.org/W2747053578","https://openalex.org/W2890678738","https://openalex.org/W2891033863","https://openalex.org/W2898200825","https://openalex.org/W2900474539","https://openalex.org/W2963109634","https://openalex.org/W2963351448","https://openalex.org/W2963534981","https://openalex.org/W2965373594","https://openalex.org/W3010072143","https://openalex.org/W3017266435","https://openalex.org/W3035511673","https://openalex.org/W3106127916","https://openalex.org/W3106542916","https://openalex.org/W3166396011","https://openalex.org/W3173871266","https://openalex.org/W3181069167","https://openalex.org/W3204540098","https://openalex.org/W3214586131","https://openalex.org/W4214759957","https://openalex.org/W4236612852","https://openalex.org/W4289535600","https://openalex.org/W4292828074","https://openalex.org/W4312323989","https://openalex.org/W4312751983","https://openalex.org/W4312805142","https://openalex.org/W4313156423","https://openalex.org/W4385569741","https://openalex.org/W4386066081","https://openalex.org/W4386075643","https://openalex.org/W4387969322","https://openalex.org/W6755207826","https://openalex.org/W6756015008","https://openalex.org/W6766904570","https://openalex.org/W6791353385","https://openalex.org/W6839144149"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Based":[0],"on":[1,201],"the":[2,7,26,35,70,96,114,170,187],"fixed":[3],"language":[4,23,41,71,75,79,107,119,140],"descriptions":[5,42],"in":[6,94,129,186],"initial":[8],"frames,":[9],"a":[10,15,54,74,91,123,131],"vision-language":[11,56,188,215],"tracker":[12,180,200],"typically":[13],"adopts":[14],"two-stream":[16],"model":[17,57,165],"structure":[18],"to":[19,39,102,112,138,146,149,192,213],"align":[20],"vision":[21],"and":[22,43,87,108,207],"features":[24,80,141],"at":[25],"feature":[27,155,160,172,176],"fusion":[28,161],"stages.":[29],"However,":[30],"this":[31],"paradigm":[32],"may":[33],"degrade":[34],"tracking":[36,184,189,216],"performance":[37,211],"due":[38],"inaccurate":[40,118],"lacks":[44],"further":[45],"modal":[46],"interaction.":[47],"To":[48],"address":[49],"these":[50],"issues,":[51],"we":[52,67,121],"propose":[53],"one-stream":[55,164],"called":[58],"One-stream":[59],"Stepwise":[60],"Decreasing":[61],"for":[62,153,175],"Vision-Language":[63],"Tracking":[64],"(OSDT).":[65],"Specifically,":[66],"first":[68],"encode":[69],"description":[72],"using":[73],"encoder.":[76],"The":[77],"obtained":[78],"are":[81,143],"then":[82],"combined":[83],"with":[84],"visual":[85,92,109,147,154],"images":[86],"entered":[88],"jointly":[89],"into":[90],"encoder,":[93],"which":[95,130],"encoder\u2019s":[97],"self-attention":[98],"mechanism":[99],"is":[100,136],"utilized":[101],"facilitate":[103],"more":[104,144],"interactions":[105],"between":[106],"features.":[110],"Moreover,":[111],"mitigate":[113],"problems":[115],"caused":[116],"by":[117],"descriptions,":[120],"design":[122],"stepwise":[124],"decreasing":[125],"multi-modal":[126],"interaction":[127],"framework,":[128],"Feature":[132],"Filter":[133],"Module":[134],"(FFM)":[135],"introduced":[137],"select":[139],"that":[142],"relevant":[145],"information":[148],"provide":[150],"semantic":[151],"guidance":[152],"extraction.":[156],"Furthermore,":[157],"without":[158],"additional":[159],"modules,":[162],"our":[163,179,199],"framework":[166],"can":[167,181],"efficiently":[168],"utilize":[169],"proposed":[171],"filtering":[173],"module":[174],"selection.":[177],"Consequently,":[178],"achieve":[182],"fast":[183],"speed":[185],"domain":[190],"compared":[191,212],"existing":[193],"state-of-the-art":[194,214],"methods.":[195,217],"We":[196],"extensively":[197],"evaluate":[198],"three":[202],"benchmarks,":[203],"i.e.":[204],"TNL2K,":[205],"LaSOT,":[206],"OTB99,":[208],"demonstrating":[209],"competing":[210]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}