{"id":"https://openalex.org/W7160249348","doi":"https://doi.org/10.1109/tip.2026.3687442","title":"Scale-Aware Prompting With Optimal Transport for Remote Sensing Image Captioning","display_name":"Scale-Aware Prompting With Optimal Transport for Remote Sensing Image Captioning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7160249348","doi":"https://doi.org/10.1109/tip.2026.3687442","pmid":"https://pubmed.ncbi.nlm.nih.gov/42081398"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3687442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3687442","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5009292015","display_name":"C L Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Zhang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-0473-113X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049165403","display_name":"Zhongle Ren","orcid":"https://orcid.org/0000-0002-5425-6437"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongle Ren","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-5425-6437","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043022387","display_name":"Biao Hou","orcid":"https://orcid.org/0000-0002-1996-186X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Hou","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-1996-186X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072879293","display_name":"Jiawei Ning","orcid":"https://orcid.org/0000-0002-7000-3325"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Ning","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-7000-3325","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125131693","display_name":"K X Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0006-3226-8986","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371213","display_name":"Weiwei Li","orcid":"https://orcid.org/0000-0002-7329-4236"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weibin Li","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-0047-8955","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135320081","display_name":"Licheng Jiao","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Licheng Jiao","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5310503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"4816","last_page":"4831"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9955999851226807,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9955999851226807,"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":0.0013000000035390258,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0005000000237487257,"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/closed-captioning","display_name":"Closed captioning","score":0.8686000108718872},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5432999730110168},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5066999793052673},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45579999685287476},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4205000102519989},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.41359999775886536},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4113999903202057},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.40209999680519104}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8686000108718872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7949000000953674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.578000009059906},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5432999730110168},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5066999793052673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4562000036239624},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.40779998898506165},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.40209999680519104},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.39800000190734863},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3513999879360199},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C183365957","wikidata":"https://www.wikidata.org/wiki/Q17140402","display_name":"Remote sensing application","level":3,"score":0.3165999948978424},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3687442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3687442","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:42081398","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42081398","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6169824600219727,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1602717822","display_name":null,"funder_award_id":"62401418","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1836536549","display_name":null,"funder_award_id":"62271377","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4116211245","display_name":null,"funder_award_id":"2024JH-CLYB-0047","funder_id":"https://openalex.org/F4320327827","funder_display_name":"Key Research and Development Project of Hainan Province"},{"id":"https://openalex.org/G439018681","display_name":null,"funder_award_id":"62171347","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6393146644","display_name":null,"funder_award_id":"YJSJ26008","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6432615666","display_name":null,"funder_award_id":"62371373","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G968938359","display_name":null,"funder_award_id":"62501450","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/F4320327827","display_name":"Key Research and Development Project of Hainan Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Remote":[0],"sensing":[1,14,18,166],"image":[2,127],"captioning":[3],"is":[4,27,86,122,158],"a":[5,50,82,118,152],"multimodal":[6],"foundation":[7],"task":[8],"for":[9,111,148,164],"fine-grained":[10,69,119],"understanding":[11],"of":[12,107,185,195],"remote":[13,17,165],"images.":[15],"However,":[16],"images":[19],"contain":[20],"complex":[21,93],"scenes":[22,94],"and":[23,41,66,75,102,109,130],"rich":[24],"objects,":[25],"it":[26],"very":[28],"challenging":[29],"to":[30,58,67,88,103,124,160],"accurately":[31],"describe":[32],"the":[33,36,47,105,137,140,172,183,186,193],"objects":[34,112],"in":[35,92],"scene":[37],"with":[38,54,155,182],"their":[39],"attributes":[40,108],"dependencies.":[42],"To":[43],"address":[44],"these":[45],"issues,":[46],"article":[48],"proposes":[49],"novel":[51],"scale-aware":[52,83],"prompting":[53],"optimal":[55,134],"transport":[56],"(SPOT)":[57],"learn":[59,143],"effective":[60,144],"multiscale":[61],"features":[62,74],"under":[63],"diverse":[64],"scenes,":[65],"build":[68],"cross-modal":[70,120],"alignment":[71,121],"between":[72],"semantic":[73],"linguistic":[76],"words":[77],"during":[78],"caption":[79,149,153],"generation.":[80,150],"Specifically,":[81],"prompt":[84],"extractor":[85],"constructed":[87],"explore":[89],"feature":[90,128,146],"integrations":[91],"through":[95,133],"learning":[96],"prompts":[97],"that":[98,171],"query":[99],"multi-scale":[100],"features,":[101],"enhance":[104],"representation":[106],"dependencies":[110],"by":[113,191],"embedding":[114],"positional":[115],"relations.":[116],"Besides,":[117],"designed":[123],"dynamically":[125],"match":[126],"representations":[129,147],"textual":[131],"semantics":[132],"transport.":[135],"Through":[136],"above":[138],"manner,":[139],"model":[141],"can":[142],"language-aligned":[145],"Finally,":[151],"Transformer":[154],"causal":[156],"self-attention":[157],"introduced":[159],"generate":[161],"accurate":[162],"captions":[163],"scenes.":[167],"Extensive":[168],"experiments":[169],"demonstrate":[170],"proposed":[173,187],"method":[174,188],"achieves":[175],"state-of-the-art":[176],"performance":[177],"on":[178],"three":[179],"public":[180],"datasets,":[181],"superiority":[184],"further":[189],"demonstrated":[190],"ablating":[192],"role":[194],"each":[196],"component.":[197]},"counts_by_year":[],"updated_date":"2026-05-08T13:12:06.581006","created_date":"2026-05-06T00:00:00"}