{"id":"https://openalex.org/W4304098539","doi":"https://doi.org/10.1145/3503161.3547851","title":"Prompting for Multi-Modal Tracking","display_name":"Prompting for Multi-Modal Tracking","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304098539","doi":"https://doi.org/10.1145/3503161.3547851"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547851","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5101738258","display_name":"Jinyu Yang","orcid":"https://orcid.org/0000-0002-9765-9009"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinyu Yang","raw_affiliation_strings":["Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100356702","display_name":"Zhe Li","orcid":"https://orcid.org/0000-0003-1680-1083"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Li","raw_affiliation_strings":["Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063285882","display_name":"Feng Zheng","orcid":"https://orcid.org/0000-0002-1701-9141"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zheng","raw_affiliation_strings":["Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085971943","display_name":"Ale\u0161 Leonardis","orcid":"https://orcid.org/0000-0003-0773-3277"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ales Leonardis","raw_affiliation_strings":["University of Birmingham, Birmingham, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Birmingham, Birmingham, United Kingdom","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101738258"],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":7.5456,"has_fulltext":false,"cited_by_count":135,"citation_normalized_percentile":{"value":0.97892122,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3492","last_page":"3500"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9890999794006348,"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/modal","display_name":"Modal","score":0.7887333631515503},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.7532713413238525},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7373229265213013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6386169195175171},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.6195773482322693},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.592529833316803},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5689570903778076},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5651735663414001},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.501539945602417},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4911439120769501},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4566251039505005},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.43212682008743286},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.28663355112075806},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17870688438415527}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7887333631515503},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.7532713413238525},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7373229265213013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6386169195175171},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.6195773482322693},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.592529833316803},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5689570903778076},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5651735663414001},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.501539945602417},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4911439120769501},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4566251039505005},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.43212682008743286},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.28663355112075806},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17870688438415527},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547851","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1814075596","https://openalex.org/W1861492603","https://openalex.org/W2186518338","https://openalex.org/W2554509537","https://openalex.org/W2802652728","https://openalex.org/W2891033863","https://openalex.org/W2898200825","https://openalex.org/W2912429050","https://openalex.org/W2917353338","https://openalex.org/W2963905288","https://openalex.org/W2966759264","https://openalex.org/W2981547689","https://openalex.org/W2991778094","https://openalex.org/W2998027361","https://openalex.org/W3001584168","https://openalex.org/W3035453691","https://openalex.org/W3096609285","https://openalex.org/W3101990647","https://openalex.org/W3103242924","https://openalex.org/W3135367836","https://openalex.org/W3158472981","https://openalex.org/W3167186358","https://openalex.org/W3204540098","https://openalex.org/W3209993199","https://openalex.org/W3214586131","https://openalex.org/W4214737929","https://openalex.org/W4214759957","https://openalex.org/W4226126595","https://openalex.org/W4249502209","https://openalex.org/W6729688932"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Multi-modal":[0],"tracking":[1,39,72,107,122],"gains":[2],"attention":[3],"due":[4],"to":[5,8,18,27,76,95],"its":[6],"ability":[7,108],"be":[9],"more":[10],"accurate":[11],"and":[12,31],"robust":[13],"in":[14,25,48,62],"complex":[15],"scenarios":[16],"compared":[17],"traditional":[19],"RGB-based":[20],"tracking.":[21],"Its":[22],"key":[23],"lies":[24],"how":[26],"fuse":[28],"multi-modal":[29,38,71,78,85,93,121,134],"data":[30,44],"reduce":[32],"the":[33,49,77,92,100,106,126,143,146],"gap":[34],"between":[35],"modalities.":[36],"However,":[37],"still":[40],"severely":[41],"suffers":[42],"from":[43],"deficiency,":[45],"thus":[46],"resulting":[47],"insufficient":[50],"learning":[51,113],"of":[52,56,109,145],"fusion":[53,60],"modules.":[54],"Instead":[55],"building":[57],"such":[58],"a":[59,67,83,96],"module,":[61],"this":[63],"paper,":[64],"we":[65],"provide":[66],"new":[68],"perspective":[69],"on":[70,133,138],"by":[73,99,123],"attaching":[74],"importance":[75],"visual":[79],"prompts.":[80],"We":[81],"design":[82],"novel":[84],"prompt":[86,101],"tracker":[87],"(ProTrack),":[88],"which":[89],"can":[90,118],"transfer":[91],"inputs":[94],"single":[97],"modality":[98],"paradigm.":[102],"By":[103],"best":[104],"employing":[105],"pre-trained":[110],"RGB":[111],"trackers":[112],"at":[114],"scale,":[115],"our":[116],"ProTrack":[117],"achieve":[119],"high-performance":[120],"only":[124],"altering":[125],"inputs,":[127],"even":[128],"without":[129],"any":[130],"extra":[131],"training":[132],"data.":[135],"Extensive":[136],"experiments":[137],"5":[139],"benchmark":[140],"datasets":[141],"demonstrate":[142],"effectiveness":[144],"proposed":[147],"ProTrack.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":69},{"year":2024,"cited_by_count":47},{"year":2023,"cited_by_count":10}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}