{"id":"https://openalex.org/W4390463190","doi":"https://doi.org/10.1587/transinf.2023edl8053","title":"Robust Visual Tracking Using Hierarchical Vision Transformer with Shifted Windows Multi-Head Self-Attention","display_name":"Robust Visual Tracking Using Hierarchical Vision Transformer with Shifted Windows Multi-Head Self-Attention","publication_year":2023,"publication_date":"2023-12-31","ids":{"openalex":"https://openalex.org/W4390463190","doi":"https://doi.org/10.1587/transinf.2023edl8053"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2023edl8053","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2023edl8053","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/1/E107.D_2023EDL8053/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/1/E107.D_2023EDL8053/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028272399","display_name":"Peng Gao","orcid":"https://orcid.org/0000-0003-2230-3937"},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng GAO","raw_affiliation_strings":["School of Cyber Science and Engineering, Qufu Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Qufu Normal University","institution_ids":["https://openalex.org/I202126657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080741869","display_name":"Xin-Yue ZHANG","orcid":null},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin-Yue ZHANG","raw_affiliation_strings":["School of Cyber Science and Engineering, Qufu Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Qufu Normal University","institution_ids":["https://openalex.org/I202126657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110956879","display_name":"Xiaoli Yang","orcid":"https://orcid.org/0000-0001-9355-3744"},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Li YANG","raw_affiliation_strings":["School of Cyber Science and Engineering, Qufu Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Qufu Normal University","institution_ids":["https://openalex.org/I202126657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003156605","display_name":"Jiancheng Ni","orcid":"https://orcid.org/0000-0001-5667-9807"},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian-Cheng NI","raw_affiliation_strings":["School of Cyber Science and Engineering, Qufu Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Qufu Normal University","institution_ids":["https://openalex.org/I202126657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455958","display_name":"Fei Wang","orcid":"https://orcid.org/0000-0003-3462-8472"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei WANG","raw_affiliation_strings":["School of Electronics and Information Engineering, Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3188,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58926456,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"E107.D","issue":"1","first_page":"161","last_page":"164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9983999729156494,"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":0.9983999729156494,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9437000155448914,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9424999952316284,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8690180778503418},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.8022549748420715},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.7867006063461304},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7439397573471069},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.648652195930481},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.5337314009666443},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5323173403739929},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5187525749206543},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.419791042804718},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4132077395915985},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3264576196670532},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.09306594729423523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8690180778503418},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.8022549748420715},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.7867006063461304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7439397573471069},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.648652195930481},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.5337314009666443},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5323173403739929},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5187525749206543},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.419791042804718},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4132077395915985},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3264576196670532},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.09306594729423523},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2023edl8053","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2023edl8053","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/1/E107.D_2023EDL8053/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2023edl8053","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2023edl8053","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/1/E107.D_2023EDL8053/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6857328452","display_name":null,"funder_award_id":"2023M732022","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390463190.pdf"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2470394683","https://openalex.org/W2794744029","https://openalex.org/W2898200825","https://openalex.org/W2963534981","https://openalex.org/W2975183808","https://openalex.org/W3001584168","https://openalex.org/W3034297219","https://openalex.org/W3108235634","https://openalex.org/W3108519869","https://openalex.org/W3138516171","https://openalex.org/W3205280353","https://openalex.org/W4206553383","https://openalex.org/W4321854270","https://openalex.org/W4385214091","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4384788979","https://openalex.org/W2511178891","https://openalex.org/W2126676984","https://openalex.org/W178060743","https://openalex.org/W2909390414","https://openalex.org/W2954509079","https://openalex.org/W3104472694","https://openalex.org/W2141888607","https://openalex.org/W2753886513","https://openalex.org/W1765993298"],"abstract_inverted_index":{"Despite":[0],"Siamese":[1,52],"trackers":[2],"attracting":[3],"much":[4],"attention":[5],"due":[6],"to":[7,23,62],"their":[8,24],"scalability":[9],"and":[10,41,92],"efficiency":[11],"in":[12,26,35],"recent":[13],"years,":[14],"researchers":[15],"have":[16],"ignored":[17],"the":[18,55,64,77,85,89,108],"background":[19,39],"appearance,":[20],"which":[21],"leads":[22],"inapplicability":[25],"recognizing":[27],"arbitrary":[28],"target":[29,70],"objects":[30],"with":[31,38],"various":[32],"variations,":[33],"especially":[34],"complex":[36],"scenarios":[37],"clutter":[40],"distractors.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46,83],"present":[47],"a":[48,67],"simple":[49],"yet":[50],"effective":[51],"tracker,":[53,82],"where":[54],"shifted":[56],"windows":[57],"multi-head":[58],"self-attention":[59],"is":[60],"produced":[61],"learn":[63],"characteristics":[65],"of":[66,79],"specific":[68],"given":[69],"object":[71],"for":[72],"visual":[73],"tracking.":[74],"To":[75],"validate":[76],"effectiveness":[78],"our":[80],"proposed":[81,109],"use":[84],"Swin":[86],"Transformer":[87],"as":[88],"backbone":[90],"network":[91],"introduced":[93],"an":[94],"auxiliary":[95],"feature":[96],"enhancement":[97],"network.":[98],"Extensive":[99],"experimental":[100],"results":[101],"on":[102],"two":[103],"evaluation":[104],"datasets":[105],"demonstrate":[106],"that":[107],"tracker":[110],"outperforms":[111],"other":[112],"baselines.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2025-10-10T00:00:00"}
