{"id":"https://openalex.org/W4406857562","doi":"https://doi.org/10.1109/tmm.2025.3535323","title":"Improving Visual Object Tracking Through Visual Prompting","display_name":"Improving Visual Object Tracking Through Visual Prompting","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406857562","doi":"https://doi.org/10.1109/tmm.2025.3535323"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3535323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535323","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5084769031","display_name":"Shih-Fang Chen","orcid":"https://orcid.org/0000-0002-8438-400X"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Shih-Fang Chen","raw_affiliation_strings":["Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010007692","display_name":"Jun-Cheng Chen","orcid":"https://orcid.org/0000-0002-0209-8932"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jun-Cheng Chen","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075510768","display_name":"I\u2010Hong Jhuo","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I-Hong Jhuo","raw_affiliation_strings":["Microsoft, Seattle, WA, USA","Microsoft, Seattle, Washington, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Seattle, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Seattle, Washington, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002217153","display_name":"Yen\u2010Yu Lin","orcid":"https://orcid.org/0000-0002-7183-6070"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yen-Yu Lin","raw_affiliation_strings":["Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084769031"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":3.6769,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90250274,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"2682","last_page":"2694"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9789000153541565,"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":0.9789000153541565,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.954800009727478,"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":0.9347000122070312,"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/computer-science","display_name":"Computer science","score":0.8385280966758728},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6980692148208618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6072722673416138},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5542711615562439},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.544568657875061},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.49967288970947266},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4913457930088043},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4285638630390167},{"id":"https://openalex.org/keywords/visual-communication","display_name":"Visual communication","score":0.4146437644958496},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35397887229919434},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.22607821226119995},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2097100019454956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8385280966758728},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6980692148208618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6072722673416138},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5542711615562439},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.544568657875061},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.49967288970947266},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4913457930088043},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4285638630390167},{"id":"https://openalex.org/C105842133","wikidata":"https://www.wikidata.org/wiki/Q1899679","display_name":"Visual communication","level":2,"score":0.4146437644958496},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35397887229919434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.22607821226119995},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2097100019454956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3535323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535323","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5960119058","display_name":null,"funder_award_id":"AS-CDA-110-M09","funder_id":"https://openalex.org/F4320321041","funder_display_name":"Academia Sinica"}],"funders":[{"id":"https://openalex.org/F4320321041","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2158592639","https://openalex.org/W2518876086","https://openalex.org/W2605173812","https://openalex.org/W2794744029","https://openalex.org/W2799058067","https://openalex.org/W2886910176","https://openalex.org/W2889986507","https://openalex.org/W2891033863","https://openalex.org/W2898200825","https://openalex.org/W2962766617","https://openalex.org/W2963074722","https://openalex.org/W2963227409","https://openalex.org/W2963534981","https://openalex.org/W2964105864","https://openalex.org/W2966759264","https://openalex.org/W2982770724","https://openalex.org/W3001584168","https://openalex.org/W3035453691","https://openalex.org/W3035571898","https://openalex.org/W3108519869","https://openalex.org/W3167536469","https://openalex.org/W3167762749","https://openalex.org/W3204540098","https://openalex.org/W3204554907","https://openalex.org/W3214586131","https://openalex.org/W4214759957","https://openalex.org/W4304481542","https://openalex.org/W4312392346","https://openalex.org/W4312472480","https://openalex.org/W4312516520","https://openalex.org/W4312532041","https://openalex.org/W4312543717","https://openalex.org/W4312651496","https://openalex.org/W4312751983","https://openalex.org/W4312805142","https://openalex.org/W4313036965","https://openalex.org/W4313159533","https://openalex.org/W4313555658","https://openalex.org/W4320036892","https://openalex.org/W4320036905","https://openalex.org/W4382461147","https://openalex.org/W4382467859","https://openalex.org/W4382469255","https://openalex.org/W4385214091","https://openalex.org/W4386065544","https://openalex.org/W4386066081","https://openalex.org/W4386066394","https://openalex.org/W4386066459","https://openalex.org/W4386075647","https://openalex.org/W4386075784","https://openalex.org/W4386076331","https://openalex.org/W4386083067","https://openalex.org/W4386174901","https://openalex.org/W4387272108","https://openalex.org/W4389154149","https://openalex.org/W4390871890","https://openalex.org/W4390871892","https://openalex.org/W4390872215","https://openalex.org/W4390872749","https://openalex.org/W4390874039","https://openalex.org/W4390874575","https://openalex.org/W4391341416","https://openalex.org/W4393159185","https://openalex.org/W4393159404","https://openalex.org/W4402702990","https://openalex.org/W4402704627","https://openalex.org/W4402753518","https://openalex.org/W4402754150","https://openalex.org/W4409261941","https://openalex.org/W6747943641","https://openalex.org/W6757817989","https://openalex.org/W6759534164","https://openalex.org/W6765307894","https://openalex.org/W6790772501","https://openalex.org/W6791353385","https://openalex.org/W6800751262","https://openalex.org/W6805147364","https://openalex.org/W6839144149","https://openalex.org/W6841667650","https://openalex.org/W6851607685","https://openalex.org/W6851800889","https://openalex.org/W6852835101","https://openalex.org/W6857158520","https://openalex.org/W6858065216","https://openalex.org/W6863234681"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W2156434174","https://openalex.org/W2071701083","https://openalex.org/W2383687187","https://openalex.org/W2081517010","https://openalex.org/W2121496884","https://openalex.org/W2965594636","https://openalex.org/W2164674712"],"abstract_inverted_index":{"Learning":[0],"a":[1,6,38,55,103],"discriminative":[2,31],"model":[3,63,77],"to":[4,14,28,49,65,116,122],"distinguish":[5],"target":[7,20,108,152],"from":[8],"its":[9],"surrounding":[10],"distractors":[11,24],"is":[12,25,145],"essential":[13],"generic":[15,44],"visual":[16,40,70,104,125,143,177],"object":[17,97],"tracking.":[18,80],"Dynamic":[19],"representation":[21],"adaptation":[22],"against":[23],"challenging":[26],"due":[27],"the":[29,60,73,87,112,117,124,129,135,142,160,164,173,176,194,200,204,217,227],"limited":[30],"capabilities":[32],"of":[33,75,114,175,203],"prevailing":[34],"trackers.":[35],"We":[36],"present":[37],"new":[39],"Prompting":[41],"mechanism":[42],"for":[43,79],"Visual":[45],"Object":[46],"Tracking":[47],"(PiVOT)":[48],"address":[50],"this":[51],"issue.":[52],"PiVOT":[53,100,119],"proposes":[54],"prompt":[56,105,126,144,157],"generation":[57],"network":[58],"with":[59],"pre-trained":[61],"foundation":[62,76,206],"CLIP":[64,82,115,121,189],"automatically":[66],"generate":[67,167],"and":[68,134,198,225],"refine":[69,123],"prompts,":[71],"enabling":[72],"transfer":[74,111],"knowledge":[78,113],"While":[81],"offers":[83],"broad":[84],"category-level":[85],"knowledge,":[86],"tracker,":[88,118],"trained":[89],"on":[90,128],"instance-specific":[91],"data,":[92],"excels":[93],"at":[94],"recognizing":[95],"unique":[96],"instances.":[98],"Thus,":[99],"first":[101],"compiles":[102],"highlighting":[106],"potential":[107,139,151],"locations.":[109],"To":[110],"leverages":[120],"based":[127],"similarities":[130],"between":[131],"candidate":[132],"objects":[133,224],"reference":[136],"templates":[137],"across":[138,210],"targets.":[140],"Once":[141],"refined,":[146],"it":[147],"can":[148,166,221],"better":[149],"highlight":[150],"locations,":[153],"thereby":[154,192],"reducing":[155,181],"irrelevant":[156],"information.":[158],"With":[159],"proposed":[161,184,218],"prompting":[162,219],"mechanism,":[163],"tracker":[165],"improved":[168],"instance-aware":[169],"feature":[170],"maps":[171],"through":[172],"guidance":[174],"prompt,":[178],"thus":[179],"effectively":[180],"distractors.":[182],"The":[183],"method":[185,220],"does":[186],"not":[187],"involve":[188],"during":[190],"training,":[191],"keeping":[193],"same":[195],"training":[196],"complexity":[197],"preserving":[199],"generalization":[201],"capability":[202],"pretrained":[205],"model.":[207],"Extensive":[208],"experiments":[209],"multiple":[211],"benchmarks":[212],"indicate":[213],"that":[214],"PiVOT,":[215],"using":[216],"suppress":[222],"distracting":[223],"enhance":[226],"tracker.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
