{"id":"https://openalex.org/W3097289768","doi":"https://doi.org/10.1109/icpr48806.2021.9412156","title":"VTT: Long-term Visual Tracking with Transformers","display_name":"VTT: Long-term Visual Tracking with Transformers","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3097289768","doi":"https://doi.org/10.1109/icpr48806.2021.9412156","mag":"3097289768"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.qub.ac.uk/en/publications/d32ea621-1459-4bbd-b480-2672872715c4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032716292","display_name":"Tianling Bian","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianling Bian","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016123060","display_name":"Hua Yang","orcid":"https://orcid.org/0000-0001-5536-503X"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang Hua","raw_affiliation_strings":["School of Electronics, Electrical Engineering and Computer Science, Queen's University, Belfast, UK"],"affiliations":[{"raw_affiliation_string":"School of Electronics, Electrical Engineering and Computer Science, Queen's University, Belfast, UK","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459491","display_name":"Tao Song","orcid":"https://orcid.org/0000-0002-9146-9386"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tao Song","raw_affiliation_strings":["School of Electronics, Electrical Engineering and Computer Science, Queen's University, Belfast, UK"],"affiliations":[{"raw_affiliation_string":"School of Electronics, Electrical Engineering and Computer Science, Queen's University, Belfast, UK","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103101740","display_name":"Zhengui Xue","orcid":"https://orcid.org/0000-0002-7120-1622"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengui Xue","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036789442","display_name":"Ruhui Ma","orcid":"https://orcid.org/0000-0001-9592-8490"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruhui Ma","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102909686","display_name":"Neil M. Robertson","orcid":"https://orcid.org/0000-0003-2461-8799"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Neil Robertson","raw_affiliation_strings":["School of Electronics, Electrical Engineering and Computer Science, Queen's University, Belfast, UK"],"affiliations":[{"raw_affiliation_string":"School of Electronics, Electrical Engineering and Computer Science, Queen's University, Belfast, UK","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049487451","display_name":"Haibing Guan","orcid":"https://orcid.org/0000-0002-4714-7400"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibing Guan","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5032716292"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.7767,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.72580958,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"9585","last_page":"9592"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":1.0,"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":1.0,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9896000027656555,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.98580002784729,"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/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.8190455436706543},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7785404920578003},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6901715397834778},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.636090874671936},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.6154171824455261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5703988671302795},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4452529847621918},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.41759592294692993},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3872702419757843},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22458580136299133},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0617392361164093}],"concepts":[{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.8190455436706543},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7785404920578003},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6901715397834778},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.636090874671936},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.6154171824455261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5703988671302795},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4452529847621918},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.41759592294692993},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3872702419757843},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22458580136299133},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0617392361164093},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.qub.ac.uk/portal:openaire/d32ea621-1459-4bbd-b480-2672872715c4","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/d32ea621-1459-4bbd-b480-2672872715c4","pdf_url":null,"source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bian, T, Hua, Y, Song, T, Xue, Z, Ma, R, Robertson, N & Guan, H 2021, VTT: Long-term Visual Tracking with Transformers. in International Conference on Pattern Recognition (ICPR). International Conference on Pattern Recognition (ICPR): Proceedings, Institute of Electrical and Electronics Engineers Inc.","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.qub.ac.uk/portal:openaire/d32ea621-1459-4bbd-b480-2672872715c4","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/d32ea621-1459-4bbd-b480-2672872715c4","pdf_url":null,"source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bian, T, Hua, Y, Song, T, Xue, Z, Ma, R, Robertson, N & Guan, H 2021, VTT: Long-term Visual Tracking with Transformers. in International Conference on Pattern Recognition (ICPR). International Conference on Pattern Recognition (ICPR): Proceedings, Institute of Electrical and Electronics Engineers Inc.","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6899999976158142}],"awards":[{"id":"https://openalex.org/G4750678945","display_name":null,"funder_award_id":"61872234,61732010,61525204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1857884451","https://openalex.org/W1861492603","https://openalex.org/W1955514522","https://openalex.org/W2037971948","https://openalex.org/W2124211486","https://openalex.org/W2139363510","https://openalex.org/W2194775991","https://openalex.org/W2408241409","https://openalex.org/W2470394683","https://openalex.org/W2557641257","https://openalex.org/W2565639579","https://openalex.org/W2594694775","https://openalex.org/W2604701225","https://openalex.org/W2613718673","https://openalex.org/W2738318237","https://openalex.org/W2776035257","https://openalex.org/W2794669410","https://openalex.org/W2799058067","https://openalex.org/W2886910176","https://openalex.org/W2891033863","https://openalex.org/W2891378778","https://openalex.org/W2898200825","https://openalex.org/W2908510526","https://openalex.org/W2962766617","https://openalex.org/W2962825948","https://openalex.org/W2963150697","https://openalex.org/W2963249584","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963534981","https://openalex.org/W2964242925","https://openalex.org/W2966759264","https://openalex.org/W2981413347","https://openalex.org/W2985509612","https://openalex.org/W2997896013","https://openalex.org/W3096609285","https://openalex.org/W3103005696","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6639102338","https://openalex.org/W6720898849","https://openalex.org/W6736609394","https://openalex.org/W6739901393","https://openalex.org/W6746790618","https://openalex.org/W6749682181","https://openalex.org/W6753818355","https://openalex.org/W6757817989"],"related_works":["https://openalex.org/W2803618243","https://openalex.org/W256589335","https://openalex.org/W3020706491","https://openalex.org/W2012200063","https://openalex.org/W4385454113","https://openalex.org/W2804764393","https://openalex.org/W4386114301","https://openalex.org/W4386158955","https://openalex.org/W4384788979","https://openalex.org/W2511178891"],"abstract_inverted_index":{"Long-term":[0],"visual":[1,57],"tracking":[2,112],"is":[3,27],"a":[4,50,67],"challenging":[5],"problem.":[6],"State-of-the-art":[7],"long-term":[8,56,111],"trackers,":[9],"e.g.,":[10],"GlobalTrack,":[11],"utilize":[12],"region":[13],"proposal":[14],"networks":[15],"(RPNs)":[16],"to":[17,48,75],"generate":[18],"target":[19],"proposals.":[20],"However,":[21],"the":[22,25,46,60,96],"performance":[23],"of":[24],"trackers":[26],"affected":[28],"by":[29],"occlusions":[30],"and":[31,79,101,114],"large":[32,80],"scale":[33,81],"or":[34,82],"ratio":[35,83],"variations.":[36],"To":[37],"address":[38],"these":[39],"issues,":[40],"in":[41],"this":[42],"paper,":[43],"we":[44],"are":[45],"first":[47],"propose":[49],"novel":[51],"architecture":[52,70],"with":[53,77],"transformers":[54],"for":[55,71,98],"tracking.":[58],"Specifically,":[59],"proposed":[61],"Visual":[62],"Tracking":[63],"Transformer":[64],"(VTT)":[65],"utilizes":[66],"transformer":[68],"encoder-decoder":[69],"aggregating":[72],"global":[73],"information":[74],"deal":[76],"occlusion":[78],"variation.":[84],"Furthermore,":[85],"it":[86],"also":[87],"shows":[88],"better":[89],"discriminative":[90],"power":[91],"against":[92],"instance-level":[93],"distractors":[94],"without":[95],"need":[97],"extra":[99],"labeling":[100],"hard-sample":[102],"mining.":[103],"We":[104],"conduct":[105],"extensive":[106],"experiments":[107],"on":[108],"three":[109],"large-scale":[110],"datasets":[113],"have":[115],"achieved":[116],"state-of-the-art":[117],"performance.":[118]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}