{"id":"https://openalex.org/W4386075647","doi":"https://doi.org/10.1109/cvpr52729.2023.00918","title":"Visual Prompt Multi-Modal Tracking","display_name":"Visual Prompt Multi-Modal Tracking","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4386075647","doi":"https://doi.org/10.1109/cvpr52729.2023.00918"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52729.2023.00918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.00918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5042596690","display_name":"Jiawen Zhu","orcid":"https://orcid.org/0000-0003-1634-1814"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiawen Zhu","raw_affiliation_strings":["Dalian University of Technology,China","Dalian University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058423267","display_name":"Simiao Lai","orcid":"https://orcid.org/0000-0003-2240-6880"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Simiao Lai","raw_affiliation_strings":["Dalian University of Technology,China","Dalian University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100638657","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0002-0747-1361"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Chen","raw_affiliation_strings":["Dalian University of Technology,China","Dalian University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391408","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0001-6420-8466"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Dalian University of Technology,China","Dalian University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006986293","display_name":"Huchuan Lu","orcid":"https://orcid.org/0000-0002-6668-9758"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huchuan Lu","raw_affiliation_strings":["Dalian University of Technology,China","Dalian University of Technology, China","Peng Cheng Laboratory, China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Dalian University of Technology, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Peng Cheng Laboratory, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042596690"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":33.4548,"has_fulltext":false,"cited_by_count":282,"citation_normalized_percentile":{"value":0.99857775,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"9516","last_page":"9526"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998999834060669,"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":0.9998999834060669,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9843999743461609,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9625999927520752,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7851181030273438},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7089451551437378},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6122546195983887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5983761548995972},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5858432054519653},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.5110810995101929},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5024735927581787},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4440380334854126},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.42462658882141113},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33368197083473206},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.140310138463974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7851181030273438},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7089451551437378},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6122546195983887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5983761548995972},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5858432054519653},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.5110810995101929},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5024735927581787},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4440380334854126},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.42462658882141113},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33368197083473206},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.140310138463974},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52729.2023.00918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.00918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[{"id":"https://openalex.org/G3432415074","display_name":null,"funder_award_id":"DUT22ZD210","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3443893577","display_name":null,"funder_award_id":"62293542,U1903215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8273014382","display_name":null,"funder_award_id":"2018AAA0102001","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1861492603","https://openalex.org/W1983594616","https://openalex.org/W2117539524","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2470394683","https://openalex.org/W2512653618","https://openalex.org/W2606627193","https://openalex.org/W2765667535","https://openalex.org/W2794744029","https://openalex.org/W2799058067","https://openalex.org/W2889986507","https://openalex.org/W2891033863","https://openalex.org/W2898200825","https://openalex.org/W2908510526","https://openalex.org/W2917353338","https://openalex.org/W2938696568","https://openalex.org/W2963188742","https://openalex.org/W2963534981","https://openalex.org/W2963905288","https://openalex.org/W2966759264","https://openalex.org/W2997131652","https://openalex.org/W2998027361","https://openalex.org/W2998756268","https://openalex.org/W3001584168","https://openalex.org/W3002567850","https://openalex.org/W3011060674","https://openalex.org/W3012425959","https://openalex.org/W3035020406","https://openalex.org/W3099681648","https://openalex.org/W3110562975","https://openalex.org/W3127756064","https://openalex.org/W3132864630","https://openalex.org/W3153607844","https://openalex.org/W3158472981","https://openalex.org/W3163168119","https://openalex.org/W3164689507","https://openalex.org/W3166396011","https://openalex.org/W3180199962","https://openalex.org/W3183904268","https://openalex.org/W3185341429","https://openalex.org/W3188267239","https://openalex.org/W3202534481","https://openalex.org/W3209993199","https://openalex.org/W3214586131","https://openalex.org/W4205991051","https://openalex.org/W4214737929","https://openalex.org/W4214759957","https://openalex.org/W4226126595","https://openalex.org/W4281838252","https://openalex.org/W4282005462","https://openalex.org/W4283808043","https://openalex.org/W4285595687","https://openalex.org/W4292434331","https://openalex.org/W4292948830","https://openalex.org/W4304098539","https://openalex.org/W4312668764","https://openalex.org/W4312751983","https://openalex.org/W4313046728","https://openalex.org/W4320036905","https://openalex.org/W4382240192","https://openalex.org/W4385245566","https://openalex.org/W6631943919","https://openalex.org/W6639102338","https://openalex.org/W6720898849","https://openalex.org/W6736832757","https://openalex.org/W6739901393","https://openalex.org/W6749631981","https://openalex.org/W6750327463","https://openalex.org/W6754472059","https://openalex.org/W6755863804","https://openalex.org/W6757817989","https://openalex.org/W6772012192","https://openalex.org/W6781018062","https://openalex.org/W6790221906","https://openalex.org/W6791353385","https://openalex.org/W6792050547","https://openalex.org/W6794654868","https://openalex.org/W6798057236","https://openalex.org/W6799063536","https://openalex.org/W6800542979","https://openalex.org/W6810336392","https://openalex.org/W6810601475","https://openalex.org/W6838701581","https://openalex.org/W6838865580","https://openalex.org/W6839670772","https://openalex.org/W6842407414","https://openalex.org/W6842567341","https://openalex.org/W6848569070","https://openalex.org/W6849641342"],"related_works":["https://openalex.org/W1583765404","https://openalex.org/W4214653257","https://openalex.org/W2055438207","https://openalex.org/W2521424917","https://openalex.org/W3040203686","https://openalex.org/W4249524554","https://openalex.org/W2349021146","https://openalex.org/W35583307","https://openalex.org/W4398294854","https://openalex.org/W2436192316"],"abstract_inverted_index":{"Visible-modal":[0],"object":[1],"tracking":[2,11,28,92,134],"gives":[3],"rise":[4],"to":[5,44,81,88,99],"a":[6,22,96,115],"series":[7],"of":[8,18,47,62,103,122,147],"downstream":[9,48,90,133],"multi-modal":[10,27,73,91,152],"tributaries.":[12],"To":[13],"inherit":[14],"the":[15,19,33,45,59,63,78,83,101,104,127,145],"powerful":[16],"representations":[17],"foundation":[20,86],"model,":[21],"natural":[23],"modus":[24],"operandi":[25],"for":[26,151],"is":[29,40,108],"full":[30,128],"fine-tuning":[31,129],"on":[32,131],"RGB-based":[34,105],"parameters.":[35],"Albeit":[36],"effective,":[37],"this":[38,55],"manner":[39],"not":[41],"optimal":[42],"due":[43],"scarcity":[46],"data":[49],"and":[50,139,154,165],"poor":[51],"transferability,":[52],"etc.":[53],"In":[54],"paper,":[56],"inspired":[57],"by":[58],"recent":[60],"success":[61],"prompt":[64,149],"learning":[65,150],"in":[66],"language":[67],"models,":[68],"we":[69],"develop":[70],"Visual":[71],"Prompt":[72],"Tracking":[74],"(ViPT),":[75],"which":[76],"learns":[77],"modal-relevant":[79],"prompts":[80],"adapt":[82],"frozen":[84],"pre-trained":[85,109],"model":[87,106,123],"various":[89],"tasks.":[93],"ViPT":[94,125,155],"finds":[95],"better":[97],"way":[98],"stimulate":[100],"knowledge":[102],"that":[107],"at":[110,169],"scale,":[111],"meanwhile":[112],"only":[113],"introducing":[114],"few":[116],"trainable":[117],"parameters":[118],"(less":[119],"than":[120],"1%":[121],"parameters).":[124],"outperforms":[126],"paradigm":[130],"multiple":[132],"tasks":[135],"including":[136],"RGB+Depth,":[137],"RGB+Thermal,":[138],"RGB+Event":[140],"tracking.":[141],"Extensive":[142],"experiments":[143],"show":[144],"potential":[146],"visual":[148],"tracking,":[153],"can":[156],"achieve":[157],"state-of-the-art":[158],"performance":[159],"while":[160],"satisfying":[161],"parameter":[162],"efficiency.":[163],"Code":[164],"models":[166],"are":[167],"available":[168],"https://github.com/jiawen-zhu/ViPT.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":139},{"year":2024,"cited_by_count":114},{"year":2023,"cited_by_count":13}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}