{"id":"https://openalex.org/W4402981768","doi":"https://doi.org/10.1109/icme57554.2024.10687451","title":"Joint Language Prompt and Object Tracking","display_name":"Joint Language Prompt and Object Tracking","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402981768","doi":"https://doi.org/10.1109/icme57554.2024.10687451"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687451","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/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":true,"raw_author_name":"ZhiMin Weng","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101490398","display_name":"Jinpu Zhang","orcid":"https://orcid.org/0000-0002-0617-0452"},"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":"JinPu Zhang","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030517812","display_name":"Yuehuan Wang","orcid":"https://orcid.org/0000-0001-7046-7587"},"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,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108993656"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.972,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80315768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.8640000224113464,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.8640000224113464,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7360105514526367},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6588988304138184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.583303689956665},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.579391360282898},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49414733052253723},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4358299970626831},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34581196308135986},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09582322835922241}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360105514526367},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6588988304138184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.583303689956665},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.579391360282898},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49414733052253723},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4358299970626831},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34581196308135986},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09582322835922241},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687451","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2470394683","https://openalex.org/W2747053578","https://openalex.org/W2799058067","https://openalex.org/W2891033863","https://openalex.org/W3001584168","https://openalex.org/W3010072143","https://openalex.org/W3090155371","https://openalex.org/W3106542916","https://openalex.org/W3167536469","https://openalex.org/W3173871266","https://openalex.org/W3181069167","https://openalex.org/W3185341429","https://openalex.org/W3214586131","https://openalex.org/W4205991051","https://openalex.org/W4214759957","https://openalex.org/W4292828074","https://openalex.org/W4304098539","https://openalex.org/W4311766677","https://openalex.org/W4312751983","https://openalex.org/W4312805142","https://openalex.org/W4385569741","https://openalex.org/W4386066081","https://openalex.org/W4386066459","https://openalex.org/W4386075643","https://openalex.org/W4386075647","https://openalex.org/W4387968153"],"related_works":["https://openalex.org/W4389065903","https://openalex.org/W2385949326","https://openalex.org/W1966005655","https://openalex.org/W3135795035","https://openalex.org/W2789220062","https://openalex.org/W2811496562","https://openalex.org/W2094665863","https://openalex.org/W2071984725","https://openalex.org/W2185534064","https://openalex.org/W2136595788"],"abstract_inverted_index":{"Recently,":[0],"utilizing":[1],"natural":[2],"language":[3,59,80,112,124,133],"descriptions":[4,60],"to":[5,63,109],"assist":[6],"in":[7,46,155],"object":[8],"tracking":[9,16,65,157],"is":[10,18,107],"becoming":[11],"a":[12,67],"trend.":[13],"However,":[14],"The":[15],"performance":[17,129],"compromised":[19],"with":[20,66,130],"the":[21,24,40,73,102,123,151],"absence":[22],"of":[23,43,70,122,153],"Vision-Language":[25],"(VL)":[26],"datasets.":[27,71,139],"In":[28],"this":[29],"paper,":[30],"we":[31],"develop":[32],"Joint":[33],"Language":[34,103],"Prompt":[35],"and":[36,57,85,97,136,148],"Object":[37],"Tracking":[38],"(JLPT),":[39],"first":[41],"application":[42],"prompt":[44,134],"learning":[45],"VL":[47,138,156],"tracking.":[48],"JLPT":[49,126,154],"preserves":[50],"knowledge":[51],"from":[52],"large-scale":[53],"pretrained":[54],"vision-based":[55],"models":[56],"adopts":[58],"as":[61],"prompts":[62,81,113],"aid":[64],"limited":[68,137],"amount":[69],"Specifically,":[72],"Multimodal":[74],"Fusion":[75],"Prompter":[76],"(MFP)":[77],"constructs":[78],"precise":[79],"by":[82],"dimension":[83],"compression":[84],"correlation":[86],"operation":[87],"on":[88,115,142],"heterologous":[89],"modal.":[90],"It":[91],"can":[92],"adaptively":[93],"reinforce":[94],"target":[95,116],"features":[96],"attenuate":[98],"interference":[99],"features.":[100],"Additionally,":[101],"Rectification":[104],"Moudle":[105],"(LRM)":[106],"introduced":[108],"dynamically":[110],"adjust":[111],"based":[114],"appearance":[117],"variations,":[118],"providing":[119],"temporal":[120],"adaptability":[121],"prompts.":[125],"achieves":[127],"notable":[128],"minimal":[131],"trainable":[132],"parameters":[135],"Extensive":[140],"experiments":[141],"TNL2K,":[143],"LaSOT,":[144],"LaSOT<inf":[145],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[146],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">ext</inf>,":[147],"OTB99-L":[149],"confirm":[150],"superiority":[152],"over":[158],"existing":[159],"trackers.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}