{"id":"https://openalex.org/W4383108846","doi":"https://doi.org/10.1109/icra48891.2023.10161487","title":"SGDViT: Saliency-Guided Dynamic Vision Transformer for UAV Tracking","display_name":"SGDViT: Saliency-Guided Dynamic Vision Transformer for UAV Tracking","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108846","doi":"https://doi.org/10.1109/icra48891.2023.10161487"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5036991650","display_name":"Liangliang Yao","orcid":"https://orcid.org/0000-0002-8435-5954"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangliang Yao","raw_affiliation_strings":["School of Mechanical Engineering, Tongji University,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Tongji University,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110931195","display_name":"Changhong Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhong Fu","raw_affiliation_strings":["School of Mechanical Engineering, Tongji University,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Tongji University,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101819709","display_name":"Sihang Li","orcid":"https://orcid.org/0000-0003-3053-5770"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sihang Li","raw_affiliation_strings":["School of Mechanical Engineering, Tongji University,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Tongji University,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101169216","display_name":"Guangze Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Guangze Zheng","raw_affiliation_strings":["the University of Hong Kong,Department of Computer Science,Hong Kong,China","Department of Computer Science, the University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"the University of Hong Kong,Department of Computer Science,Hong Kong,China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Computer Science, the University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100777712","display_name":"Junjie Ye","orcid":"https://orcid.org/0000-0002-4316-166X"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Ye","raw_affiliation_strings":["School of Mechanical Engineering, Tongji University,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Tongji University,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3353","last_page":"3359"},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9986000061035156,"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":0.9936000108718872,"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/computer-science","display_name":"Computer science","score":0.8132722973823547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7138481140136719},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6619424819946289},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6549322009086609},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5490074157714844},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.48990148305892944},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.43679141998291016},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4221305251121521},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2298327088356018},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.19181549549102783},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10521647334098816}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132722973823547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7138481140136719},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6619424819946289},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6549322009086609},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5490074157714844},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.48990148305892944},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.43679141998291016},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4221305251121521},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2298327088356018},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.19181549549102783},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10521647334098816},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10161487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"},{"score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G468934012","display_name":null,"funder_award_id":"62173249","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8500223103","display_name":"\u9762\u5411\u8fb9\u7f18\u667a\u80fd\u89c6\u89c9\u611f\u77e5\u7684\u65e0\u4eba\u673a\u957f\u65f6\u76ee\u6807\u8ddf\u8e2a\u5173\u952e\u7406\u8bba\u53ca\u5176 \u5e94\u7528","funder_award_id":"20ZR1460100","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"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":56,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2117539524","https://openalex.org/W2160613239","https://openalex.org/W2470394683","https://openalex.org/W2518876086","https://openalex.org/W2547875792","https://openalex.org/W2592463526","https://openalex.org/W2604701225","https://openalex.org/W2618530766","https://openalex.org/W2776035257","https://openalex.org/W2794744029","https://openalex.org/W2799058067","https://openalex.org/W2886910176","https://openalex.org/W2898200825","https://openalex.org/W2912465472","https://openalex.org/W2927438889","https://openalex.org/W2963030525","https://openalex.org/W2963534981","https://openalex.org/W2964423614","https://openalex.org/W2980770827","https://openalex.org/W2987346479","https://openalex.org/W2987460522","https://openalex.org/W2998434318","https://openalex.org/W3003412316","https://openalex.org/W3035466700","https://openalex.org/W3098389804","https://openalex.org/W3101676691","https://openalex.org/W3108519869","https://openalex.org/W3115390238","https://openalex.org/W3120974171","https://openalex.org/W3138516171","https://openalex.org/W3167454939","https://openalex.org/W3167536469","https://openalex.org/W3168124404","https://openalex.org/W3169909246","https://openalex.org/W3172553658","https://openalex.org/W3179950005","https://openalex.org/W3203510176","https://openalex.org/W3205280353","https://openalex.org/W3214586131","https://openalex.org/W4214506192","https://openalex.org/W4226244084","https://openalex.org/W4385245566","https://openalex.org/W4385364879","https://openalex.org/W6639102338","https://openalex.org/W6720898849","https://openalex.org/W6726654379","https://openalex.org/W6729448088","https://openalex.org/W6739901393","https://openalex.org/W6753818355","https://openalex.org/W6780018109","https://openalex.org/W6788023325","https://openalex.org/W6796494063","https://openalex.org/W6798321724","https://openalex.org/W6810521590","https://openalex.org/W6849683692"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W2951819827","https://openalex.org/W2849310602","https://openalex.org/W2770593030","https://openalex.org/W3134175397","https://openalex.org/W2965594636","https://openalex.org/W2912550626"],"abstract_inverted_index":{"Vision-based":[0],"object":[1,79],"tracking":[2,25,152],"has":[3,43],"boosted":[4],"extensive":[5],"autonomous":[6],"applications":[7],"for":[8,69],"unmanned":[9],"aerial":[10],"vehicles":[11],"(UAVs).":[12],"However,":[13],"the":[14,85,110,114,129,139],"dynamic":[15,65],"changes":[16],"in":[17,23,45],"flight":[18],"maneuver":[19],"and":[20,33,50,88,92,127,136,154,165],"viewpoint":[21],"encountered":[22],"UAV":[24,70,151],"pose":[26],"significant":[27],"difficulties,":[28],"e.g.,":[29],"aspect":[30],"ratio":[31],"change,":[32],"scale":[34],"variation.":[35],"The":[36,72,134,162],"conventional":[37],"cross-correlation":[38,86],"operation,":[39],"while":[40],"commonly":[41],"used,":[42],"limitations":[44],"effectively":[46,89],"capturing":[47],"perceptual":[48],"similarity":[49],"incorporates":[51],"extraneous":[52],"background":[53,93],"information.":[54,94,133],"To":[55],"mitigate":[56],"these":[57],"limitations,":[58],"this":[59],"work":[60],"presents":[61],"a":[62,76,96,118],"novel":[63],"saliency-guided":[64],"vision":[66],"Transformer":[67,115,122],"(SGDViT)":[68],"tracking.":[71],"proposed":[73,140],"method":[74],"designs":[75],"new":[77],"task-specific":[78],"saliency":[80,97,120,125],"mining":[81],"network":[82],"to":[83],"refine":[84],"operation":[87,100],"discriminate":[90],"foreground":[91],"Additionally,":[95],"adaptation":[98],"embedding":[99],"dynamically":[101],"generates":[102],"tokens":[103],"based":[104],"on":[105,131,148],"initial":[106],"saliency,":[107],"thereby":[108],"reducing":[109],"computational":[111],"complexity":[112],"of":[113,138],"architecture.":[116],"Finally,":[117],"lightweight":[119],"filtering":[121],"further":[123],"refines":[124],"information":[126],"increases":[128],"focus":[130],"appearance":[132],"efficacy":[135],"robustness":[137],"approach":[141],"have":[142],"been":[143],"thoroughly":[144],"assessed":[145],"through":[146],"experiments":[147],"three":[149],"widely-used":[150],"benchmarks":[153],"real-world":[155],"scenarios,":[156],"with":[157],"results":[158],"demonstrating":[159],"its":[160],"superiority.":[161],"source":[163],"code":[164],"demo":[166],"videos":[167],"are":[168],"available":[169],"at":[170],"https://github.com/vision4robotics/SGDViT.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":7}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}