{"id":"https://openalex.org/W4414603352","doi":"https://doi.org/10.1109/lgrs.2025.3615554","title":"A Text-Guided Query Adaptive Vision Transformer for Pansharpening","display_name":"A Text-Guided Query Adaptive Vision Transformer for Pansharpening","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414603352","doi":"https://doi.org/10.1109/lgrs.2025.3615554"},"language":"en","primary_location":{"id":"doi:10.1109/lgrs.2025.3615554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lgrs.2025.3615554","pdf_url":null,"source":{"id":"https://openalex.org/S126920919","display_name":"IEEE Geoscience and Remote Sensing Letters","issn_l":"1545-598X","issn":["1545-598X","1558-0571"],"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 Geoscience and Remote Sensing Letters","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/A5090531606","display_name":"Haitao Yin","orcid":"https://orcid.org/0000-0003-2975-2188"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Yin","raw_affiliation_strings":["School of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-2975-2188","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yamin Zhu","orcid":"https://orcid.org/0009-0005-8591-8658"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yamin Zhu","raw_affiliation_strings":["School of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0005-8591-8658","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18607443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.965499997138977,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.965499997138977,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9488999843597412,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9431999921798706,"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/multispectral-image","display_name":"Multispectral image","score":0.6152999997138977},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4876999855041504},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4577000141143799},{"id":"https://openalex.org/keywords/image-resolution","display_name":"Image resolution","score":0.42590001225471497},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4203000068664551},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39559999108314514},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3779999911785126},{"id":"https://openalex.org/keywords/panchromatic-film","display_name":"Panchromatic film","score":0.3626999855041504},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.35260000824928284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8468999862670898},{"id":"https://openalex.org/C173163844","wikidata":"https://www.wikidata.org/wiki/Q1761440","display_name":"Multispectral image","level":2,"score":0.6152999997138977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.550599992275238},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4876999855041504},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4560999870300293},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.42590001225471497},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4203000068664551},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3779999911785126},{"id":"https://openalex.org/C107445234","wikidata":"https://www.wikidata.org/wiki/Q280995","display_name":"Panchromatic film","level":3,"score":0.3626999855041504},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.35260000824928284},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28619998693466187},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lgrs.2025.3615554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lgrs.2025.3615554","pdf_url":null,"source":{"id":"https://openalex.org/S126920919","display_name":"IEEE Geoscience and Remote Sensing Letters","issn_l":"1545-598X","issn":["1545-598X","1558-0571"],"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 Geoscience and Remote Sensing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2638013300","display_name":null,"funder_award_id":"BK20251876","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1980110630","https://openalex.org/W1991460509","https://openalex.org/W2139529730","https://openalex.org/W2142843085","https://openalex.org/W2462592242","https://openalex.org/W2766278341","https://openalex.org/W2792142731","https://openalex.org/W2935896423","https://openalex.org/W3096904276","https://openalex.org/W3111024962","https://openalex.org/W3121629662","https://openalex.org/W4285601348","https://openalex.org/W4288391574","https://openalex.org/W4365790514","https://openalex.org/W4385767946","https://openalex.org/W4387968697","https://openalex.org/W4392909612","https://openalex.org/W4398788597","https://openalex.org/W4402716157","https://openalex.org/W4404840410","https://openalex.org/W4405056103","https://openalex.org/W4407900637","https://openalex.org/W4412081524"],"related_works":[],"abstract_inverted_index":{"Pansharpening":[0],"aims":[1],"to":[2,56,81,113,127,169],"fuse":[3],"a":[4,11,20,95,105,155,167],"low":[5],"resolution":[6,13,22],"multispectral":[7],"(LRMS)":[8],"image":[9,171],"and":[10,17,58,64,70,122,139,184,197],"high":[12,21],"panchromatic":[14],"(PAN)":[15],"image,":[16],"then":[18],"synthesize":[19],"MS":[23],"(HRMS)":[24],"image.":[25],"Benefiting":[26],"from":[27,62],"its":[28],"potent":[29],"capacity":[30],"for":[31,102],"global":[32],"information":[33,61],"modeling,":[34],"vision":[35],"Transformer":[36],"(ViT)":[37],"has":[38],"achieved":[39],"remarkable":[40],"performance":[41],"in":[42,133],"pansharpening.":[43,103],"However,":[44],"most":[45],"ViT-based":[46],"methods":[47],"heavily":[48],"rely":[49],"on":[50,194],"cross-attention":[51],"with":[52,85],"static":[53,128],"modality":[54],"queries":[55,132],"extract":[57],"integrate":[59],"complementary":[60],"PAN":[63],"LRMS":[65],"images,":[66],"neglecting":[67],"the":[68,131,134,146,163,178,205],"adaptivity":[69],"specificity":[71],"of":[72,150,207],"different":[73,202],"modalities.":[74],"Moreover,":[75,143],"vision-only":[76],"representation":[77],"framework":[78],"often":[79],"struggles":[80],"balance":[82],"spatial":[83,183],"enhancement":[84],"spectral":[86,185],"fidelity.":[87],"To":[88],"tackle":[89],"these":[90],"issues,":[91],"this":[92],"letter":[93],"proposes":[94],"Text":[96],"guided":[97],"Query":[98,106],"Adaptive":[99,107],"ViT":[100],"(Text-QAViT)":[101],"Specifically,":[104],"Cross-Attention":[108],"(QACA)":[109],"block":[110,136,160,180],"is":[111],"designed":[112],"enhance":[114],"cross-modal":[115,119],"interaction,":[116],"which":[117,161],"comprises":[118],"query":[120],"projection":[121],"gating":[123],"selection":[124],"mechanism.":[125],"Compared":[126],"swapped":[129],"queries,":[130],"QACA":[135],"are":[137],"dynamic":[138],"exhibit":[140],"better":[141],"adaptability.":[142],"inspired":[144],"by":[145,201],"powerful":[147],"semantic":[148],"understanding":[149],"language-vision":[151],"model,":[152],"we":[153],"design":[154],"Text-Conditional":[156],"Batch":[157],"Normalization":[158],"(TCBN)":[159],"utilizes":[162],"text":[164],"embeddings":[165],"as":[166],"guidance":[168],"modulate":[170],"features.":[172],"By":[173],"leveraging":[174],"high-level":[175],"language":[176],"semantics,":[177],"TCBN":[179],"flexibly":[181],"balances":[182],"features,":[186],"thereby":[187],"effectively":[188],"enhancing":[189],"visual":[190],"quality.":[191],"Extensive":[192],"experiments":[193],"both":[195],"reduced-resolution":[196],"full-resolution":[198],"datasets":[199],"acquired":[200],"satellites":[203],"demonstrate":[204],"superiority":[206],"Text-QAViT":[208],"over":[209],"state-of-the-art":[210],"methods.":[211]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}