{"id":"https://openalex.org/W4383109322","doi":"https://doi.org/10.1109/icra48891.2023.10161433","title":"TransVisDrone: Spatio-Temporal Transformer for Vision-based Drone-to-Drone Detection in Aerial Videos","display_name":"TransVisDrone: Spatio-Temporal Transformer for Vision-based Drone-to-Drone Detection in Aerial Videos","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383109322","doi":"https://doi.org/10.1109/icra48891.2023.10161433"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161433","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":"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/A5054519724","display_name":"Tushar Sangam","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tushar Sangam","raw_affiliation_strings":["University of Central Florida,Center for Research in Computer Vision lab (CRCV),USA","Center for Research in Computer Vision lab (CRCV), University of Central Florida, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida,Center for Research in Computer Vision lab (CRCV),USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"Center for Research in Computer Vision lab (CRCV), University of Central Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104109814","display_name":"Ishan Rajendrakumar Dave","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ishan Rajendrakumar Dave","raw_affiliation_strings":["University of Central Florida,Center for Research in Computer Vision lab (CRCV),USA","Center for Research in Computer Vision lab (CRCV), University of Central Florida, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida,Center for Research in Computer Vision lab (CRCV),USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"Center for Research in Computer Vision lab (CRCV), University of Central Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082613558","display_name":"Waqas Sultani","orcid":"https://orcid.org/0000-0002-9322-0728"},"institutions":[{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]},{"id":"https://openalex.org/I172780181","display_name":"University of the Punjab","ror":"https://ror.org/011maz450","country_code":"PK","type":"education","lineage":["https://openalex.org/I172780181"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Waqas Sultani","raw_affiliation_strings":["Information Technology University of the Punjab,Lahore,Pakistan","Information Technology University of the Punjab, Lahore, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology University of the Punjab,Lahore,Pakistan","institution_ids":["https://openalex.org/I172780181","https://openalex.org/I1323252656"]},{"raw_affiliation_string":"Information Technology University of the Punjab, Lahore, Pakistan","institution_ids":["https://openalex.org/I172780181","https://openalex.org/I1323252656"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080823547","display_name":"Mubarak Shah","orcid":"https://orcid.org/0000-0001-6172-5572"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mubarak Shah","raw_affiliation_strings":["University of Central Florida,Center for Research in Computer Vision lab (CRCV),USA","Center for Research in Computer Vision lab (CRCV), University of Central Florida, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida,Center for Research in Computer Vision lab (CRCV),USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"Center for Research in Computer Vision lab (CRCV), University of Central Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054519724"],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":4.1521,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.9550657,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6006","last_page":"6013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9993000030517578,"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":0.9993000030517578,"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/T11133","display_name":"UAV Applications and Optimization","score":0.9990000128746033,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9988999962806702,"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/drone","display_name":"Drone","score":0.9905875325202942},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7986981868743896},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.7141653299331665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5514546036720276},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.5418868660926819},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5009727478027344},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4374432861804962},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4246995151042938},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41882413625717163},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.16529881954193115}],"concepts":[{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.9905875325202942},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986981868743896},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7141653299331665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5514546036720276},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.5418868660926819},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5009727478027344},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4374432861804962},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4246995151042938},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41882413625717163},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.16529881954193115},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10161433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161433","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2109255472","https://openalex.org/W2346349911","https://openalex.org/W2565776924","https://openalex.org/W2607934962","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963855133","https://openalex.org/W2968065219","https://openalex.org/W2982770724","https://openalex.org/W2991359031","https://openalex.org/W2994810768","https://openalex.org/W3018757597","https://openalex.org/W3034467781","https://openalex.org/W3042011474","https://openalex.org/W3090039082","https://openalex.org/W3092462694","https://openalex.org/W3123599388","https://openalex.org/W3132799496","https://openalex.org/W3134909472","https://openalex.org/W3138516171","https://openalex.org/W3157894430","https://openalex.org/W3161886303","https://openalex.org/W3163951850","https://openalex.org/W3169909246","https://openalex.org/W3171516518","https://openalex.org/W3174053790","https://openalex.org/W3175195314","https://openalex.org/W3195539663","https://openalex.org/W3206848710","https://openalex.org/W3210279979","https://openalex.org/W3210311771","https://openalex.org/W3210586215","https://openalex.org/W3210997132","https://openalex.org/W3214993537","https://openalex.org/W4206720504","https://openalex.org/W4206775207","https://openalex.org/W4210760290","https://openalex.org/W4212975908","https://openalex.org/W4312274649","https://openalex.org/W4312560592","https://openalex.org/W4313066449","https://openalex.org/W4385245566","https://openalex.org/W4386075866","https://openalex.org/W6631190155","https://openalex.org/W6639102338","https://openalex.org/W6739901393","https://openalex.org/W6777046832","https://openalex.org/W6784094891","https://openalex.org/W6851175825"],"related_works":["https://openalex.org/W4229448053","https://openalex.org/W4247925126","https://openalex.org/W4327774218","https://openalex.org/W2059768187","https://openalex.org/W2949096641","https://openalex.org/W2970686063","https://openalex.org/W4320729701","https://openalex.org/W4254103348","https://openalex.org/W3210378990","https://openalex.org/W3034745255"],"abstract_inverted_index":{"Drone-to-drone":[0],"detection":[1,81],"using":[2],"visual":[3],"feed":[4],"has":[5],"crucial":[6],"applications,":[7],"such":[8],"as":[9],"detecting":[10,13,131],"drone":[11,14,80,90],"collisions,":[12],"attacks,":[15],"or":[16],"coordinating":[17],"flight":[18],"with":[19,62],"other":[20],"drones.":[21],"However,":[22],"existing":[23],"methods":[24],"are":[25],"computationally":[26],"costly,":[27],"follow":[28],"non-end-to-end":[29],"optimization,":[30],"and":[31,75,108,111,127],"have":[32],"complex":[33],"multi-stage":[34],"pipelines,":[35],"making":[36],"them":[37],"less":[38],"suitable":[39],"for":[40],"real-time":[41],"deployment":[42,122],"on":[43,97,124],"edge":[44,125],"devices.":[45],"In":[46],"this":[47],"work,":[48],"we":[49],"propose":[50],"a":[51,112],"simple":[52],"yet":[53],"effective":[54],"framework,":[55],"TransVisDrone,":[56],"that":[57],"provides":[58],"an":[59],"end-to-end":[60],"solution":[61],"higher":[63,113],"computational":[64],"efficiency.":[65],"We":[66,118],"utilize":[67],"CSPDarkNet-53":[68],"network":[69],"to":[70,78],"learn":[71],"object-related":[72],"spatial":[73],"features":[74],"VideoSwin":[76],"model":[77],"improve":[79],"in":[82,130],"challenging":[83,99],"scenarios":[84],"by":[85],"learning":[86],"spatio-temporal":[87],"dependencies":[88],"of":[89],"motion.":[91],"Our":[92],"method":[93],"achieves":[94],"state-of-the-art":[95],"performance":[96],"three":[98],"real-world":[100],"datasets":[101],"(Average":[102],"Precision@0.5IOU):":[103],"NPS":[104],"0.95,":[105],"FLDrones":[106],"0.75,":[107],"AOT":[109],"0.80,":[110],"throughput":[114],"than":[115],"previous":[116],"methods.":[117],"also":[119],"demonstrate":[120],"its":[121,128],"capability":[123],"devices":[126],"usefulness":[129],"drone-collision":[132],"(encounter).":[133],"Project:":[134],"https://tusharsangam.github.io/TransVisDrone-project-page/":[135]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}