{"id":"https://openalex.org/W7128442801","doi":"https://doi.org/10.1109/tcsvt.2026.3662475","title":"TGCADNet: Text-Guided Context-Aware Detection via CLIP for Small Objects in UAV Scenes","display_name":"TGCADNet: Text-Guided Context-Aware Detection via CLIP for Small Objects in UAV Scenes","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128442801","doi":"https://doi.org/10.1109/tcsvt.2026.3662475"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3662475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3662475","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/A5025062175","display_name":"Fengqian Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengqian Sun","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4821-1985","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044684024","display_name":"Deqiang Cheng","orcid":"https://orcid.org/0000-0001-8831-1994"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deqiang Cheng","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8831-1994","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052048093","display_name":"Ping Zheng","orcid":"https://orcid.org/0000-0002-9088-1774"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Zheng","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9088-1774","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082518848","display_name":"Tianshu Song","orcid":"https://orcid.org/0000-0003-3592-0651"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshu Song","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3592-0651","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liangliang Chen","orcid":"https://orcid.org/0000-0001-9097-0657"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangliang Chen","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9097-0657","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058118704","display_name":"Kou Qiqi","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiqi Kou","raw_affiliation_strings":["School of Computer Science and Technology and the School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2873-2636","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology and the School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":19.7937,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.98851061,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"36","issue":"6","first_page":"7846","last_page":"7859"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5687000155448914,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.5687000155448914,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.25600001215934753,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.06499999761581421,"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/key","display_name":"Key (lock)","score":0.7073000073432922},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6942999958992004},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6037999987602234},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5896000266075134},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5200999975204468},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46779999136924744},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4185999929904938},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.3840999901294708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8475000262260437},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7073000073432922},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6945000290870667},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6942999958992004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6923999786376953},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6037999987602234},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5896000266075134},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5200999975204468},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46779999136924744},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3840999901294708},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.310699999332428},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.30489999055862427},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25209999084472656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3662475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3662475","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/G165681500","display_name":null,"funder_award_id":"2024M763543","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G4332863609","display_name":null,"funder_award_id":"52204177","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/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"highlighted":[3],"the":[4,85,124,153,166,171,179,194,198],"importance":[5],"of":[6,106,155,168,185,206],"contextual":[7],"information":[8],"for":[9,99],"small":[10,79,229],"object":[11,80],"detection.":[12,102],"However,":[13],"existing":[14],"methods":[15,218],"rely":[16],"solely":[17],"on":[18,170,193],"visual":[19],"features":[20,121,145],"and":[21,41,61,95,111,143,157,174,189,200,208,222,233],"lack":[22],"additional":[23],"semantic":[24,93],"guidance,":[25],"which":[26],"limits":[27],"their":[28,54],"ability":[29],"to":[30,42,122,146,178],"model":[31,125],"key":[32,129],"scene-level":[33,130],"context":[34,46,131],"in":[35,47,56,126,161,187,191,210,219,227,231],"semantically":[36],"rich,":[37],"globally":[38,133],"complex":[39,63,134],"environments":[40],"suppress":[43],"irrelevant":[44],"local":[45,149,159],"densely":[48],"cluttered":[49,158],"scenes.":[50,64,163,237],"These":[51],"limitations":[52],"hinder":[53],"effectiveness":[55,167,226],"Unmanned":[57],"Aerial":[58],"Vehicle":[59],"(UAV)":[60],"similar":[62,234],"To":[65],"address":[66],"these":[67],"challenges,":[68],"we":[69],"propose":[70],"TGCADNet":[71,76,103,169,181,203,214],"(Text-Guided":[72],"Context-Aware":[73,109],"Detection":[74],"Network).":[75],"is":[77],"a":[78],"detection":[81],"framework":[82],"that":[83],"leverages":[84],"CLIP":[86],"(Contrastive":[87],"Language\u2013":[88],"Image":[89],"Pretraining)":[90],"model\u2019s":[91],"global":[92],"understanding":[94],"image-text":[96],"alignment":[97],"capabilities":[98],"enhancing":[100],"context-aware":[101],"mainly":[104],"consists":[105],"Text-Guided":[107,112],"Scene-level":[108],"(TG-SCA)":[110],"Local-Context":[113],"Filtering":[114],"(TG-LCF).":[115],"Specifically,":[116],"TG-SCA":[117],"uses":[118],"CLIP-generated":[119],"text":[120,142],"guide":[123],"accurately":[127],"extracting":[128],"from":[132],"environments.":[135],"Meanwhile,":[136],"TG-LCF":[137],"performs":[138],"interactive":[139],"computation":[140],"between":[141],"image":[144],"filter":[147],"high-quality":[148],"context,":[150],"thereby":[151],"reducing":[152],"impact":[154],"dense":[156],"regions":[160],"UAV":[162,232],"We":[164],"validate":[165],"VisDrone,":[172],"UAVDT,":[173],"AI-TOD-v2":[175,201],"datasets.":[176],"Compared":[177],"baseline,":[180],"achieves":[182],"an":[183],"improvement":[184],"1.8":[186],"mAP@50":[188],"1.3":[190],"mAP@50:95":[192],"VisDrone":[195],"dataset.":[196],"On":[197],"UAVDT":[199],"datasets,":[202],"observes":[204],"improvements":[205],"2.5":[207],"2.3":[209],"mAP@50,":[211],"respectively.":[212],"Furthermore,":[213],"surpasses":[215],"recent":[216],"SOTA":[217],"both":[220],"accuracy":[221],"efficiency,":[223],"demonstrating":[224],"its":[225],"detecting":[228],"objects":[230],"remote":[235],"sensing":[236]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-02-10T00:00:00"}