{"id":"https://openalex.org/W3144314306","doi":"https://doi.org/10.1109/iccv48922.2021.01028","title":"Learning Spatio-Temporal Transformer for Visual Tracking","display_name":"Learning Spatio-Temporal Transformer for Visual Tracking","publication_year":2021,"publication_date":"2021-10-01","ids":{"openalex":"https://openalex.org/W3144314306","doi":"https://doi.org/10.1109/iccv48922.2021.01028","mag":"3144314306"},"language":"en","primary_location":{"id":"doi:10.1109/iccv48922.2021.01028","doi":"https://doi.org/10.1109/iccv48922.2021.01028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv48922.2021.01028","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.17154","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101616088","display_name":"Bin Yan","orcid":"https://orcid.org/0000-0002-6228-3865","observed_orcids":["https://orcid.org/0000-0002-6228-3865"]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Yan","raw_affiliation_strings":["Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080495327","display_name":"Houwen Peng","orcid":"https://orcid.org/0000-0001-8544-8952","observed_orcids":["https://orcid.org/0000-0001-8544-8952"]},"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"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Houwen Peng","raw_affiliation_strings":["Microsoft Research Asia","(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072029041","display_name":"Jianlong Fu","orcid":"https://orcid.org/0000-0002-1025-2012","observed_orcids":["https://orcid.org/0000-0002-1025-2012"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlong Fu","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391493","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6976-4004","observed_orcids":["https://orcid.org/0000-0002-6976-4004"]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006986293","display_name":"Huchuan Lu","orcid":"https://orcid.org/0000-0002-6668-9758","observed_orcids":["https://orcid.org/0000-0002-6668-9758","https://orcid.org/0000-0003-3162-1929"]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huchuan Lu","raw_affiliation_strings":["Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":59.9911,"has_fulltext":true,"cited_by_count":1347,"citation_normalized_percentile":{"value":0.99887838,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"10428","last_page":"10437"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9951000213623047,"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":0.9951000213623047,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.002199999988079071,"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":0.0008999999845400453,"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/visual-tracking","display_name":"visual object tracking","score":0.9520000219345093},{"id":"https://openalex.org/keywords/spatiotemporal-transformer","display_name":"spatio-temporal transformer","score":0.9350000023841858},{"id":"https://openalex.org/keywords/encoder-decoder-transformer","display_name":"transformer encoder-decoder","score":0.9480000138282776},{"id":"https://openalex.org/keywords/bounding-box-prediction","display_name":"bounding box prediction","score":0.8019999861717224},{"id":"https://openalex.org/keywords/query-embedding","display_name":"query embedding","score":0.6029999852180481},{"id":"https://openalex.org/keywords/real-time-tracking","display_name":"real-time tracking","score":0.7089999914169312},{"id":"https://openalex.org/keywords/longitudinal-tracking","display_name":"long-term tracking","score":0.7960000038146973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7840515375137329},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6148433089256287},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6077991127967834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5824170708656311},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5565763115882874},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.524594247341156},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47929874062538147},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.45004379749298096},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4473622143268585},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.43146440386772156},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33980581164360046},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10078269243240356},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0895853340625763},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv48922.2021.01028","doi":"https://doi.org/10.1109/iccv48922.2021.01028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv48922.2021.01028","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.17154","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.17154","pdf_url":"https://arxiv.org/pdf/2103.17154","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3144314306","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2103.17154.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2103.17154","doi":"https://doi.org/10.48550/arxiv.2103.17154","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.17154","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.17154","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.17154","pdf_url":"https://arxiv.org/pdf/2103.17154","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3144314306.pdf","grobid_xml":"https://content.openalex.org/works/W3144314306.grobid-xml"},"referenced_works_count":76,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1836465849","https://openalex.org/W1857884451","https://openalex.org/W1861492603","https://openalex.org/W1915785815","https://openalex.org/W2139047213","https://openalex.org/W2154889144","https://openalex.org/W2158592639","https://openalex.org/W2194775991","https://openalex.org/W2222512263","https://openalex.org/W2340000481","https://openalex.org/W2470394683","https://openalex.org/W2518876086","https://openalex.org/W2557641257","https://openalex.org/W2558899534","https://openalex.org/W2605173812","https://openalex.org/W2608627404","https://openalex.org/W2626778328","https://openalex.org/W2767302379","https://openalex.org/W2794744029","https://openalex.org/W2797257757","https://openalex.org/W2799058067","https://openalex.org/W2886910176","https://openalex.org/W2888456413","https://openalex.org/W2891033863","https://openalex.org/W2896457183","https://openalex.org/W2898200825","https://openalex.org/W2901751835","https://openalex.org/W2908510526","https://openalex.org/W2933875464","https://openalex.org/W2936520980","https://openalex.org/W2944255943","https://openalex.org/W2947624463","https://openalex.org/W2950628590","https://openalex.org/W2962731685","https://openalex.org/W2962824803","https://openalex.org/W2963227409","https://openalex.org/W2963341956","https://openalex.org/W2963471260","https://openalex.org/W2963534981","https://openalex.org/W2964423614","https://openalex.org/W2985509612","https://openalex.org/W2987460522","https://openalex.org/W2989688045","https://openalex.org/W2989778648","https://openalex.org/W2990431089","https://openalex.org/W2997896013","https://openalex.org/W2998027361","https://openalex.org/W2998434318","https://openalex.org/W3013266062","https://openalex.org/W3030520226","https://openalex.org/W3032984651","https://openalex.org/W3034617042","https://openalex.org/W3035211844","https://openalex.org/W3035257046","https://openalex.org/W3035473155","https://openalex.org/W3035511673","https://openalex.org/W3035571898","https://openalex.org/W3035672751","https://openalex.org/W3035725297","https://openalex.org/W3047017093","https://openalex.org/W3094502228","https://openalex.org/W3104158266","https://openalex.org/W3108519869","https://openalex.org/W3115390238","https://openalex.org/W3119686997","https://openalex.org/W3127756064","https://openalex.org/W3142630836","https://openalex.org/W3167762749","https://openalex.org/W3168649818","https://openalex.org/W3173344965","https://openalex.org/W4303858517","https://openalex.org/W6703518758","https://openalex.org/W6755863804","https://openalex.org/W6784333009","https://openalex.org/W6790221906"],"related_works":["https://openalex.org/W4362736361","https://openalex.org/W3167536469","https://openalex.org/W4315783490","https://openalex.org/W4410416285","https://openalex.org/W4387553208","https://openalex.org/W7165176060","https://openalex.org/W4403918626","https://openalex.org/W4414264937","https://openalex.org/W3162457465","https://openalex.org/W7124911796"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,35,53,76],"new":[6],"tracking":[7,51,110],"architecture":[8],"with":[9],"an":[10],"encoder-decoder":[11,68],"transformer":[12],"as":[13,52,99],"the":[14,20,32,40,44,67,70,82],"key":[15],"component.":[16],"The":[17,87,112],"encoder":[18],"models":[19,139],"global":[21],"spatio-temporal":[22],"feature":[23],"dependencies":[24],"between":[25],"target":[26,45],"objects":[27,73,85],"and":[28,102,122,138],"search":[29],"regions,":[30],"while":[31,125],"decoder":[33],"learns":[34],"query":[36],"embedding":[37],"to":[38],"predict":[39],"spatial":[41],"positions":[42],"of":[43,72,84],"objects.":[46],"Our":[47],"method":[48,89],"casts":[49],"object":[50],"direct":[54],"bounding":[55,103],"box":[56,104],"prediction":[57,71],"problem,":[58],"without":[59],"using":[60],"any":[61,95],"proposals":[62],"or":[63],"predefined":[64],"anchors.":[65],"With":[66],"transformer,":[69],"just":[74],"uses":[75],"simple":[77],"fully-convolutional":[78],"network,":[79],"which":[80],"estimates":[81],"corners":[83],"directly.":[86],"whole":[88],"is":[90],"end-to-end,":[91],"does":[92],"not":[93],"need":[94],"postprocessing":[96],"steps":[97],"such":[98],"cosine":[100],"window":[101],"smoothing,":[105],"thus":[106],"largely":[107],"simplifying":[108],"existing":[109],"pipelines.":[111],"proposed":[113],"tracker":[114],"achieves":[115],"state-of-the-art":[116],"performance":[117],"on":[118],"multiple":[119],"challenging":[120],"short-term":[121],"long-term":[123],"benchmarks,":[124],"running":[126],"at":[127,142],"real-time":[128],"speed,":[129],"being":[130],"6\u00d7":[131],"faster":[132],"than":[133],"Siam":[134],"R-CNN":[135],"[54].":[136],"Code":[137],"are":[140],"open-sourced":[141],"https://github.com/researchmm/Stark.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":234},{"year":2025,"cited_by_count":338},{"year":2024,"cited_by_count":348},{"year":2023,"cited_by_count":284},{"year":2022,"cited_by_count":128},{"year":2021,"cited_by_count":15}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2021-04-13T00:00:00"}