{"id":"https://openalex.org/W4412748023","doi":"https://doi.org/10.1109/jstars.2025.3593887","title":"Dual-Stream Spatially Aware Transformer for Remote Sensing Image Captioning","display_name":"Dual-Stream Spatially Aware Transformer for Remote Sensing Image Captioning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412748023","doi":"https://doi.org/10.1109/jstars.2025.3593887"},"language":"en","primary_location":{"id":"doi:10.1109/jstars.2025.3593887","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2025.3593887","pdf_url":null,"source":{"id":"https://openalex.org/S117727964","display_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","issn_l":"1939-1404","issn":["1939-1404","2151-1535"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/jstars.2025.3593887","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087102984","display_name":"Haifeng Sima","orcid":"https://orcid.org/0000-0002-2049-3637"},"institutions":[{"id":"https://openalex.org/I4210166499","display_name":"Henan Polytechnic University","ror":"https://ror.org/05vr1c885","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210166499"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haifeng Sima","raw_affiliation_strings":["School of Computer Science and Technology &amp; School of Software, Henan Polytechnic University, Jiaozuo, China","School of Computer Science and Technology &amp; Software, Henan Polytechnic University, Jiaozuo, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology &amp; School of Software, Henan Polytechnic University, Jiaozuo, China","institution_ids":["https://openalex.org/I4210166499"]},{"raw_affiliation_string":"School of Computer Science and Technology &amp; Software, Henan Polytechnic University, Jiaozuo, China","institution_ids":["https://openalex.org/I4210166499"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060402293","display_name":"Xuhui Ding","orcid":"https://orcid.org/0000-0001-5682-9019"},"institutions":[{"id":"https://openalex.org/I4210166499","display_name":"Henan Polytechnic University","ror":"https://ror.org/05vr1c885","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210166499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangtao Ding","raw_affiliation_strings":["School of Computer Science and Technology &amp; School of Software, Henan Polytechnic University, Jiaozuo, China","School of Computer Science and Technology &amp; Software, Henan Polytechnic University, Jiaozuo, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology &amp; School of Software, Henan Polytechnic University, Jiaozuo, China","institution_ids":["https://openalex.org/I4210166499"]},{"raw_affiliation_string":"School of Computer Science and Technology &amp; Software, Henan Polytechnic University, Jiaozuo, China","institution_ids":["https://openalex.org/I4210166499"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100666573","display_name":"Jianlong Wang","orcid":"https://orcid.org/0000-0002-4726-8544"},"institutions":[{"id":"https://openalex.org/I4210166499","display_name":"Henan Polytechnic University","ror":"https://ror.org/05vr1c885","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210166499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"JianLong Wang","raw_affiliation_strings":["School of Computer Science and Technology &amp; School of Software, Henan Polytechnic University, Jiaozuo, China","School of Computer Science and Technology &amp; Software, Henan Polytechnic University, Jiaozuo, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology &amp; School of Software, Henan Polytechnic University, Jiaozuo, China","institution_ids":["https://openalex.org/I4210166499"]},{"raw_affiliation_string":"School of Computer Science and Technology &amp; Software, Henan Polytechnic University, Jiaozuo, China","institution_ids":["https://openalex.org/I4210166499"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113185011","display_name":"Mingliang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingliang Xu","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5087102984"],"corresponding_institution_ids":["https://openalex.org/I4210166499"],"apc_list":{"value":1250,"currency":"USD","value_usd":1250},"apc_paid":{"value":1250,"currency":"USD","value_usd":1250},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21300544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":null,"first_page":"19546","last_page":"19562"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991000294685364,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991000294685364,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9983999729156494,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9961000084877014,"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":0.8556270003318787},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7506075501441956},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5125789046287537},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.44493311643600464},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.3802338242530823},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36954301595687866},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3620378375053406},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.16317662596702576},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.109596848487854},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09980282187461853}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8556270003318787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506075501441956},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5125789046287537},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.44493311643600464},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3802338242530823},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36954301595687866},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3620378375053406},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.16317662596702576},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.109596848487854},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09980282187461853},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstars.2025.3593887","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2025.3593887","pdf_url":null,"source":{"id":"https://openalex.org/S117727964","display_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","issn_l":"1939-1404","issn":["1939-1404","2151-1535"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b8361c0fa2b54cd69471e3176c0f74da","is_oa":true,"landing_page_url":"https://doaj.org/article/b8361c0fa2b54cd69471e3176c0f74da","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 18, Pp 19546-19562 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/jstars.2025.3593887","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2025.3593887","pdf_url":null,"source":{"id":"https://openalex.org/S117727964","display_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","issn_l":"1939-1404","issn":["1939-1404","2151-1535"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W62621907","https://openalex.org/W825973156","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W1980038761","https://openalex.org/W2064675550","https://openalex.org/W2086866337","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2506483933","https://openalex.org/W2510520237","https://openalex.org/W2515866431","https://openalex.org/W2603566245","https://openalex.org/W2745461083","https://openalex.org/W2779054585","https://openalex.org/W2896348597","https://openalex.org/W2911584214","https://openalex.org/W2920981979","https://openalex.org/W2963084599","https://openalex.org/W2963418739","https://openalex.org/W2979924880","https://openalex.org/W2986670728","https://openalex.org/W3011916860","https://openalex.org/W3034655362","https://openalex.org/W3042724941","https://openalex.org/W3089915566","https://openalex.org/W3117344638","https://openalex.org/W3154766321","https://openalex.org/W3167976421","https://openalex.org/W3171038842","https://openalex.org/W3194015448","https://openalex.org/W4206028074","https://openalex.org/W4206111836","https://openalex.org/W4211112734","https://openalex.org/W4212819272","https://openalex.org/W4213449032","https://openalex.org/W4285744637","https://openalex.org/W4320487288","https://openalex.org/W4360605441","https://openalex.org/W4361009677","https://openalex.org/W4383748367","https://openalex.org/W4385245566","https://openalex.org/W4385864244","https://openalex.org/W4387986561","https://openalex.org/W4391226826","https://openalex.org/W4391305855","https://openalex.org/W4391341588","https://openalex.org/W4394585954","https://openalex.org/W4396941249","https://openalex.org/W4403864103","https://openalex.org/W4404563351","https://openalex.org/W4407152340","https://openalex.org/W4408145414","https://openalex.org/W6635446068","https://openalex.org/W6637306801","https://openalex.org/W6678262379","https://openalex.org/W6678914141","https://openalex.org/W6679436768","https://openalex.org/W6682086108","https://openalex.org/W6682631176","https://openalex.org/W6683512859","https://openalex.org/W6849177959"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757"],"abstract_inverted_index":{"Remote":[0],"sensing":[1,15,173],"image":[2],"captioning(RSIC)":[3],"aims":[4],"to":[5,19,61,121],"generate":[6],"semantically":[7],"rich":[8],"and":[9,25,57,81,85,95,127,140,158],"syntactically":[10],"accurate":[11],"descriptions":[12],"for":[13,171],"remote":[14,172],"images.":[16,174],"However,":[17],"due":[18],"the":[20,116,119,143],"complex":[21],"spatial":[22,59,63,90,113],"layouts,":[23],"occlusions,":[24],"overlapping":[26],"objects":[27],"in":[28,167],"such":[29],"images,":[30],"caption":[31],"generation":[32],"is":[33],"often":[34],"challenged":[35],"by":[36],"semantic":[37],"ambiguity.":[38],"To":[39],"address":[40],"these":[41,161],"issues,":[42],"we":[43,101],"propose":[44],"a":[45,68,96,103],"novel":[46],"<bold":[47,69,104],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[48,70,105],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Dual-Stream":[49,71],"Spatially-Aware":[50],"Transformer":[51],"(DSAT)</b>,which":[52],"explicitly":[53],"models":[54],"both":[55],"global":[56,79],"local":[58],"relationships":[60,114],"enhance":[62],"understanding.":[64],"Specifically,":[65],"DSAT":[66],"introduces":[67],"Feature":[72],"Interaction":[73],"(DFI)</b>":[74],"module":[75],"that":[76,110],"extracts":[77],"grid-level":[78],"features":[80],"region-level":[82],"object":[83,124],"features,":[84],"further":[86],"enhances":[87],"their":[88],"respective":[89],"dependencies":[91],"through":[92],"multi-branch":[93],"convolution":[94],"graph":[97],"attention":[98],"network.":[99],"Additionally,":[100],"design":[102],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Spatially-Aware":[106],"Attention":[107],"(SAA)</b>":[108],"mechanism":[109],"encodes":[111],"relative":[112],"into":[115],"Transformer,":[117],"allowing":[118],"model":[120],"better":[122],"capture":[123],"distribution":[125],"patterns":[126],"geometric":[128],"relationships.":[129],"Extensive":[130],"experiments":[131],"conducted":[132],"on":[133,160],"three":[134],"benchmark":[135],"datasets,":[136,162],"namely":[137],"Sydney-Captions,":[138],"UCM-Captions,":[139],"RSICD,":[141],"highlight":[142],"superior":[144],"performance":[145],"of":[146,155],"DSAT.":[147],"The":[148],"proposed":[149],"method":[150],"achieves":[151],"impressive":[152],"CIDEr":[153],"scores":[154],"338.59%,":[156],"450.93%,":[157],"275.36%":[159],"respectively,":[163],"demonstrating":[164],"its":[165],"effectiveness":[166],"generating":[168],"high-quality":[169],"captions":[170]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}