{"id":"https://openalex.org/W4387885793","doi":"https://doi.org/10.1109/tcsvt.2023.3326695","title":"ViT Spatio-Temporal Feature Fusion for Aerial Object Tracking","display_name":"ViT Spatio-Temporal Feature Fusion for Aerial Object Tracking","publication_year":2023,"publication_date":"2023-10-23","ids":{"openalex":"https://openalex.org/W4387885793","doi":"https://doi.org/10.1109/tcsvt.2023.3326695"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3326695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3326695","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5101954592","display_name":"Chuangye Guo","orcid":"https://orcid.org/0009-0004-4781-6952"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chuangye Guo","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, China","Key Laboratory of Intelligent Interaction and Applications of Ministry of Industry and Information Technology, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Interaction and Applications of Ministry of Industry and Information Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004","https://openalex.org/I890469752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389892","display_name":"Kang Liu","orcid":"https://orcid.org/0000-0002-2621-925X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang Liu","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, China","Key Laboratory of Intelligent Interaction and Applications of Ministry of Industry and Information Technology, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Interaction and Applications of Ministry of Industry and Information Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004","https://openalex.org/I890469752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102570825","display_name":"Deng Dong-hu","orcid":"https://orcid.org/0009-0005-7412-6719"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donghu Deng","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, China","Key Laboratory of Intelligent Interaction and Applications of Ministry of Industry and Information Technology, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Interaction and Applications of Ministry of Industry and Information Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004","https://openalex.org/I890469752"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106943753","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0003-2924-946X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, China","Key Laboratory of Intelligent Interaction and Applications of Ministry of Industry and Information Technology, Northwestern Polytechnical University, Xi'an, China","Shanghai Artificial Intelligence Laboratory, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Interaction and Applications of Ministry of Industry and Information Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004","https://openalex.org/I890469752"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101954592"],"corresponding_institution_ids":["https://openalex.org/I17145004","https://openalex.org/I890469752"],"apc_list":null,"apc_paid":null,"fwci":1.324,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83141542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"34","issue":"8","first_page":"6749","last_page":"6761"},"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9857000112533569,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9596999883651733,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7492656707763672},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7447865009307861},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7355112433433533},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.7004481554031372},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5736849308013916},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5436888933181763},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.487037718296051},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.48652949929237366},{"id":"https://openalex.org/keywords/tracking-system","display_name":"Tracking system","score":0.46297380328178406},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.12752801179885864},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.1029939353466034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7492656707763672},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7447865009307861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7355112433433533},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.7004481554031372},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5736849308013916},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5436888933181763},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.487037718296051},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48652949929237366},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.46297380328178406},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12752801179885864},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.1029939353466034},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3326695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3326695","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3103725251","display_name":null,"funder_award_id":"2022ZD0160403","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4404144043","display_name":null,"funder_award_id":"62376216","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4820425477","display_name":null,"funder_award_id":"61871470","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1964846093","https://openalex.org/W2117539524","https://openalex.org/W2158592639","https://openalex.org/W2470394683","https://openalex.org/W2518013266","https://openalex.org/W2518876086","https://openalex.org/W2557641257","https://openalex.org/W2599547527","https://openalex.org/W2604701225","https://openalex.org/W2794744029","https://openalex.org/W2799058067","https://openalex.org/W2891033863","https://openalex.org/W2898200825","https://openalex.org/W2927438889","https://openalex.org/W2963534981","https://openalex.org/W2966759264","https://openalex.org/W2987346479","https://openalex.org/W2987460522","https://openalex.org/W2990187711","https://openalex.org/W2998027361","https://openalex.org/W3034297219","https://openalex.org/W3035466700","https://openalex.org/W3112530000","https://openalex.org/W3123853823","https://openalex.org/W3138516171","https://openalex.org/W3159231306","https://openalex.org/W3170906437","https://openalex.org/W3181286780","https://openalex.org/W3188394685","https://openalex.org/W3197283120","https://openalex.org/W3203510176","https://openalex.org/W3204554907","https://openalex.org/W3210997334","https://openalex.org/W3214549945","https://openalex.org/W3214586131","https://openalex.org/W4210525157","https://openalex.org/W4214506192","https://openalex.org/W4225347798","https://openalex.org/W4226528771","https://openalex.org/W4236612852","https://openalex.org/W4296079497","https://openalex.org/W4304481542","https://openalex.org/W4312255167","https://openalex.org/W4312263794","https://openalex.org/W4312396550","https://openalex.org/W4312443924","https://openalex.org/W4312651496","https://openalex.org/W4312734171","https://openalex.org/W4312735552","https://openalex.org/W4313156423","https://openalex.org/W4313177625","https://openalex.org/W4319300771","https://openalex.org/W4319777952","https://openalex.org/W4322576880","https://openalex.org/W4362501010","https://openalex.org/W4368755498","https://openalex.org/W4386066394","https://openalex.org/W4386066459","https://openalex.org/W4386075784","https://openalex.org/W4386076238","https://openalex.org/W6772048929","https://openalex.org/W6845518869","https://openalex.org/W6852669933"],"related_works":["https://openalex.org/W2394134009","https://openalex.org/W1971984615","https://openalex.org/W2046099857","https://openalex.org/W2806679586","https://openalex.org/W4315836311","https://openalex.org/W2393252924","https://openalex.org/W2318603563","https://openalex.org/W2787600244","https://openalex.org/W4285271403","https://openalex.org/W2091015105"],"abstract_inverted_index":{"The":[0,21],"object":[1,25,35,48,56,93,100,179],"tracking":[2,26,32,49,76,94,189],"technology":[3],"for":[4,64,137,177],"aerial":[5,55,66,191],"remote":[6,67],"sensing":[7,68],"images":[8,69],"has":[9,194],"made":[10],"significant":[11],"development,":[12],"but":[13],"it":[14],"is":[15,70,106,135,168],"still":[16],"a":[17,83,161],"very":[18],"challenging":[19],"work.":[20],"related":[22],"difficulties":[23],"of":[24,30,77,92,102,114,120,128,157,190],"include":[27],"the":[28,65,90,99,103,111,115,118,121,124,146,151],"accumulation":[29],"long-term":[31],"errors,":[33],"similar":[34],"interference,":[36],"partial":[37],"or":[38],"full":[39],"occlusion,":[40],"scale":[41],"change,":[42],"etc,":[43],"which":[44,72,142],"can":[45,73,143,186],"lead":[46],"to":[47,108,172,182],"failure.":[50],"In":[51,96],"this":[52,97],"paper,":[53],"an":[54],"tracker":[57],"with":[58,163],"ViT":[59],"Spatio-Temporal":[60],"Feature":[61],"Fusion":[62],"(STFF)":[63],"proposed,":[71],"achieve":[74,187],"accurate":[75,188],"aviation":[78,178],"objects.":[79],"Firstly,":[80],"we":[81],"propose":[82],"spatial-temporal":[84],"feature":[85,139,152],"fusion":[86],"strategy":[87],"based":[88],"on":[89,198],"characteristics":[91],"timing.":[95],"strategy,":[98],"information":[101,127,140,155],"previous":[104],"frames":[105],"applied":[107],"enhance":[109,145],"both":[110],"real-time":[112],"responsiveness":[113],"model":[116],"and":[117,132,149,154,165,170,193,201],"performance":[119,197],"tracker.":[122],"Secondly,":[123],"dynamic":[125],"change":[126],"objects":[129,192],"in":[130],"space":[131],"time":[133],"context":[134],"used":[136],"spatio-temporal":[138],"fusion,":[141],"further":[144],"appropriate":[147],"correlation":[148],"promote":[150],"aggregation":[153],"transmission":[156],"visual":[158],"tracking.":[159,180],"Finally,":[160],"dataset":[162],"real":[164],"virtual":[166],"scenarios":[167],"collected":[169],"constructed":[171],"address":[173],"training":[174],"data":[175],"requirements":[176],"According":[181],"our":[183,202],"experiments,":[184],"STFF":[185],"achieved":[195],"excellent":[196],"UAV123,":[199],"DTB70":[200],"benchmarks.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}