{"id":"https://openalex.org/W4353007050","doi":"https://doi.org/10.48550/arxiv.2303.10826","title":"Visual Prompt Multi-Modal Tracking","display_name":"Visual Prompt Multi-Modal Tracking","publication_year":2023,"publication_date":"2023-03-20","ids":{"openalex":"https://openalex.org/W4353007050","doi":"https://doi.org/10.48550/arxiv.2303.10826"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2303.10826","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.10826","pdf_url":"https://arxiv.org/pdf/2303.10826","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2303.10826","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042596690","display_name":"Jiawen Zhu","orcid":"https://orcid.org/0000-0003-1634-1814"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhu, Jiawen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058423267","display_name":"Simiao Lai","orcid":"https://orcid.org/0000-0003-2240-6880"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lai, Simiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363065","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0002-2506-4268"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391493","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6976-4004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Dong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5006986293","display_name":"Huchuan Lu","orcid":"https://orcid.org/0000-0002-6668-9758"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Huchuan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042596690"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9951000213623047,"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":0.9951000213623047,"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":0.9675999879837036,"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/T13731","display_name":"Advanced Computing and Algorithms","score":0.9332000017166138,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7778644561767578},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6921381950378418},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.615732729434967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6036890745162964},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5900024175643921},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.5464495420455933},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4750007390975952},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.44437167048454285},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4290730655193329},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34661194682121277},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13504713773727417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778644561767578},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6921381950378418},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.615732729434967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6036890745162964},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5900024175643921},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.5464495420455933},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4750007390975952},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.44437167048454285},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4290730655193329},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34661194682121277},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13504713773727417},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"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/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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2303.10826","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.10826","pdf_url":"https://arxiv.org/pdf/2303.10826","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2303.10826","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2303.10826","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2303.10826","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.10826","pdf_url":"https://arxiv.org/pdf/2303.10826","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.7099999785423279,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4353007050.pdf"},"referenced_works_count":0,"referenced_works":[],"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/W2436192316","https://openalex.org/W2970287324"],"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":[10,27,73,152],"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],"multimodal":[91],"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":2025,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}