{"id":"https://openalex.org/W4401507877","doi":"https://doi.org/10.1109/tgrs.2024.3442575","title":"Wavelet Tree Transformer: Multihead Attention With Frequency-Selective Representation and Interaction for Remote Sensing Object Detection","display_name":"Wavelet Tree Transformer: Multihead Attention With Frequency-Selective Representation and Interaction for Remote Sensing Object Detection","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401507877","doi":"https://doi.org/10.1109/tgrs.2024.3442575"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2024.3442575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3442575","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"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 Geoscience and Remote Sensing","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/A5104157296","display_name":"Jiahao Pan","orcid":"https://orcid.org/0009-0002-8922-2445"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiahao Pan","raw_affiliation_strings":["School of Electronic Information, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749866","display_name":"Chu He","orcid":"https://orcid.org/0000-0003-3662-5769"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chu He","raw_affiliation_strings":["School of Electronic Information, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102571347","display_name":"Huang Wei","orcid":"https://orcid.org/0009-0005-0615-4857"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Huang","raw_affiliation_strings":["School of Electronic Information, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100953550","display_name":"Jidong Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jidong Cao","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058043055","display_name":"Ming Tong","orcid":"https://orcid.org/0009-0002-7302-652X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Tong","raw_affiliation_strings":["School of Electronic Information, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104157296"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":3.5178,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93420946,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"62","issue":null,"first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6817656755447388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5192608833312988},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.5074400305747986},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.5024604797363281},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48594987392425537},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4699941575527191},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4614630341529846},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.44732755422592163},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.402149498462677},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.16141340136528015},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10647344589233398},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10109201073646545}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6817656755447388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5192608833312988},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.5074400305747986},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.5024604797363281},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48594987392425537},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4699941575527191},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4614630341529846},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.44732755422592163},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.402149498462677},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.16141340136528015},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10647344589233398},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10109201073646545},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2024.3442575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3442575","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"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 Geoscience and Remote Sensing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6187398417","display_name":null,"funder_award_id":"41371342","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":106,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2020919250","https://openalex.org/W2085625911","https://openalex.org/W2113181621","https://openalex.org/W2117539524","https://openalex.org/W2152657318","https://openalex.org/W2161645016","https://openalex.org/W2194775991","https://openalex.org/W2251393295","https://openalex.org/W2603142085","https://openalex.org/W2604604482","https://openalex.org/W2769613401","https://openalex.org/W2809383394","https://openalex.org/W2891065437","https://openalex.org/W2919115771","https://openalex.org/W2962721361","https://openalex.org/W2962749812","https://openalex.org/W2963150697","https://openalex.org/W2963179609","https://openalex.org/W2963351448","https://openalex.org/W2964241181","https://openalex.org/W2964979676","https://openalex.org/W2978517431","https://openalex.org/W2982770724","https://openalex.org/W2988455866","https://openalex.org/W2991359031","https://openalex.org/W2991363140","https://openalex.org/W2992240579","https://openalex.org/W3015468748","https://openalex.org/W3025199923","https://openalex.org/W3034993937","https://openalex.org/W3035396860","https://openalex.org/W3038948729","https://openalex.org/W3039009902","https://openalex.org/W3090004407","https://openalex.org/W3096609285","https://openalex.org/W3107867277","https://openalex.org/W3113299742","https://openalex.org/W3113343294","https://openalex.org/W3131500599","https://openalex.org/W3136761610","https://openalex.org/W3138516171","https://openalex.org/W3155649272","https://openalex.org/W3162090017","https://openalex.org/W3170033848","https://openalex.org/W3170642968","https://openalex.org/W3172509117","https://openalex.org/W3172752666","https://openalex.org/W3174873843","https://openalex.org/W3186596917","https://openalex.org/W3203608457","https://openalex.org/W4205659311","https://openalex.org/W4206181696","https://openalex.org/W4207045938","https://openalex.org/W4210925408","https://openalex.org/W4213190624","https://openalex.org/W4214648418","https://openalex.org/W4214666412","https://openalex.org/W4221071851","https://openalex.org/W4225582357","https://openalex.org/W4225982893","https://openalex.org/W4226345037","https://openalex.org/W4285545380","https://openalex.org/W4288325606","https://openalex.org/W4292387403","https://openalex.org/W4292826140","https://openalex.org/W4293519398","https://openalex.org/W4294811189","https://openalex.org/W4295838474","https://openalex.org/W4309325582","https://openalex.org/W4312335509","https://openalex.org/W4312795296","https://openalex.org/W4312804579","https://openalex.org/W4312832682","https://openalex.org/W4312916726","https://openalex.org/W4313007769","https://openalex.org/W4323654151","https://openalex.org/W4324116440","https://openalex.org/W4362714880","https://openalex.org/W4365601179","https://openalex.org/W4366148662","https://openalex.org/W4379382445","https://openalex.org/W4381244723","https://openalex.org/W4381730126","https://openalex.org/W4382119132","https://openalex.org/W4385245566","https://openalex.org/W4385732035","https://openalex.org/W4386556626","https://openalex.org/W4391935863","https://openalex.org/W6620707391","https://openalex.org/W6748455662","https://openalex.org/W6761628794","https://openalex.org/W6771626834","https://openalex.org/W6776048684","https://openalex.org/W6779586474","https://openalex.org/W6779990023","https://openalex.org/W6785796391","https://openalex.org/W6794345597","https://openalex.org/W6795140394","https://openalex.org/W6795146805","https://openalex.org/W6796744688","https://openalex.org/W6797578546","https://openalex.org/W6810308439","https://openalex.org/W6851433281","https://openalex.org/W6856418075","https://openalex.org/W6861519249"],"related_works":["https://openalex.org/W2382174632","https://openalex.org/W2129959498","https://openalex.org/W2784060934","https://openalex.org/W2902714807","https://openalex.org/W2537489131","https://openalex.org/W2394084632","https://openalex.org/W2358293514","https://openalex.org/W2046633342","https://openalex.org/W2059273319","https://openalex.org/W2077021924"],"abstract_inverted_index":{"Vision":[0],"Transformer":[1,100],"has":[2],"achieved":[3],"remarkable":[4],"success":[5],"in":[6,58,98],"image":[7],"recognition":[8],"tasks":[9],"owing":[10],"to":[11,41,105,139,173,222],"its":[12,240],"global":[13,149],"modeling":[14,150],"ability.":[15,242],"However,":[16,47],"the":[17,36,92,99,103,131,136,166,175,178,186,196,228,231],"quadratic":[18],"computational":[19,157],"complexity":[20],"becomes":[21],"a":[22,76,88,123],"prominent":[23],"issue":[24],"when":[25],"dealing":[26],"with":[27,95,107,151],"high-resolution":[28],"remote":[29],"sensing":[30],"images.":[31],"Numerous":[32],"studies":[33],"have":[34],"explored":[35],"potential":[37],"of":[38,109,180,198,230],"spectral":[39],"analysis":[40],"reveal":[42],"for":[43,67,144,201],"more":[44,187],"discriminative":[45],"features.":[46,190],"neural":[48],"network":[49],"exhibit":[50],"frequency":[51,70,141,153],"tendency,":[52],"and":[53,111,117,183,209,219,235,238],"different":[54,59],"features":[55,142],"are":[56],"interested":[57],"frequencies.":[60],"Unfortunately,":[61],"there":[62],"is":[63,84,245],"no":[64],"well-established":[65],"criterion":[66],"selecting":[68],"appropriate":[69],"representations.":[71],"To":[72],"address":[73],"these":[74],"issues,":[75],"novel":[77],"wavelet":[78,93,124,132,137],"tree":[79,89,125,133],"head":[80,189],"attention":[81,97,171,182],"(WTHA-ViT)":[82],"model":[83,174,215,232],"proposed":[85],"which":[86,147],"combines":[87],"structure":[90],"on":[91,130,177,185,207,233],"frequencies":[94],"multihead":[96,170,181],"encoder,":[101],"possessing":[102],"ability":[104],"interact":[106],"cross-combinations":[108],"short":[110],"long-range":[112],"as":[113,115],"well":[114],"high":[116],"low-frequency":[118],"components.":[119],"First,":[120],"we":[121,164,226],"construct":[122],"reduction":[126],"module":[127],"(WTRM)":[128],"based":[129],"structure,":[134],"utilizing":[135],"decomposition":[138],"retain":[140],"suitable":[143],"each":[145],"patch,":[146],"enables":[148],"various":[152],"components":[154],"while":[155],"reducing":[156],"complexity.":[158],"Second,":[159],"guided":[160],"by":[161],"channel":[162,167],"correlations,":[163],"propose":[165],"lifting":[168],"scheme":[169],"(CLSMHA)":[172],"importance":[176],"heads":[179],"focus":[184],"salient":[188],"Finally,":[191],"our":[192,214],"WTHA-ViT":[193],"can":[194],"replace":[195],"backbone":[197],"detection":[199],"networks":[200],"dense":[202],"prediction":[203],"tasks.":[204],"Extensive":[205],"experiments":[206],"DOTA-V1.0":[208],"HRSID":[210],"datasets":[211,237],"demonstrate":[212],"that":[213],"exhibits":[216],"superior":[217],"performance":[218],"robustness":[220],"compared":[221],"state-of-the-art":[223],"networks.":[224],"Besides,":[225],"evaluate":[227],"transferability":[229],"DIOR":[234],"LEVIR":[236],"verify":[239],"generalization":[241],"The":[243],"code":[244],"available":[246],"at":[247],"<uri":[248],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[249],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/conquer-pan/WTHA-ViT</uri>.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}