{"id":"https://openalex.org/W4413754737","doi":"https://doi.org/10.1109/jstars.2025.3603036","title":"Multimodal Large Models Driven SAR Image Captioning: A Benchmark Dataset and Baselines","display_name":"Multimodal Large Models Driven SAR Image Captioning: A Benchmark Dataset and Baselines","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413754737","doi":"https://doi.org/10.1109/jstars.2025.3603036"},"language":"en","primary_location":{"id":"doi:10.1109/jstars.2025.3603036","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2025.3603036","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.2025.3603036","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114246406","display_name":"Ziyi Gao","orcid":"https://orcid.org/0009-0009-9262-8332"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi Gao","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, China","College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0009-9262-8332","affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077549875","display_name":"Shuzhou Sun","orcid":"https://orcid.org/0000-0001-8453-3346"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuzhou Sun","raw_affiliation_strings":["Department of Computer Science and Technology, Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint Center for ML, Tsinghua University, Beijing, China","Department of Computer Science & Technology, Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint Center for ML, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8453-3346","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint Center for ML, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science & Technology, Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint Center for ML, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037131575","display_name":"Ming\u2010Ming Cheng","orcid":"https://orcid.org/0000-0001-5550-8758"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming-Ming Cheng","raw_affiliation_strings":["TKLNDST, College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-5550-8758","affiliations":[{"raw_affiliation_string":"TKLNDST, College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054002392","display_name":"Yongxiang Liu","orcid":"https://orcid.org/0000-0002-0682-8365"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxiang Liu","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, China","College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418783","display_name":"Li Liu","orcid":"https://orcid.org/0000-0002-2011-2873"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, China","College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0002-2011-2873","affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1250,"currency":"USD","value_usd":1250},"apc_paid":{"value":1250,"currency":"USD","value_usd":1250},"fwci":1.5311,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.84521271,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"18","issue":null,"first_page":"24011","last_page":"24026"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9739000201225281,"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/T10862","display_name":"AI in cancer detection","score":0.9659000039100647,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.7951562404632568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7669718265533447},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6565260291099548},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6431806683540344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5505151152610779},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5501927137374878},{"id":"https://openalex.org/keywords/synthetic-aperture-radar","display_name":"Synthetic aperture radar","score":0.536686897277832},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.39760762453079224},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35892561078071594},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35592007637023926},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.09254837036132812},{"id":"https://openalex.org/keywords/geodesy","display_name":"Geodesy","score":0.05964621901512146}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7951562404632568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7669718265533447},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6565260291099548},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6431806683540344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5505151152610779},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5501927137374878},{"id":"https://openalex.org/C87360688","wikidata":"https://www.wikidata.org/wiki/Q740686","display_name":"Synthetic aperture radar","level":2,"score":0.536686897277832},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.39760762453079224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35892561078071594},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35592007637023926},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.09254837036132812},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.05964621901512146},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstars.2025.3603036","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2025.3603036","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:10d58ec56ff2423393af8a23d3971ca4","is_oa":true,"landing_page_url":"https://doaj.org/article/10d58ec56ff2423393af8a23d3971ca4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","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 24011-24026 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/jstars.2025.3603036","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2025.3603036","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":[{"id":"https://openalex.org/G5747617250","display_name":null,"funder_award_id":"62531026","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7774348999","display_name":null,"funder_award_id":"62376283","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W62621907","https://openalex.org/W825973156","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2194775991","https://openalex.org/W2506483933","https://openalex.org/W2510520237","https://openalex.org/W2745461083","https://openalex.org/W2779054585","https://openalex.org/W2920981979","https://openalex.org/W3034655362","https://openalex.org/W3104050923","https://openalex.org/W4206111836","https://openalex.org/W4211112734","https://openalex.org/W4283776488","https://openalex.org/W4293370702","https://openalex.org/W4320004340","https://openalex.org/W4324129116","https://openalex.org/W4378697422","https://openalex.org/W4380303580","https://openalex.org/W4385245566","https://openalex.org/W4386071707","https://openalex.org/W4389067838","https://openalex.org/W4389765680","https://openalex.org/W4390873136","https://openalex.org/W4391100112","https://openalex.org/W4393307085","https://openalex.org/W4393944506","https://openalex.org/W4394007658","https://openalex.org/W4394585954","https://openalex.org/W4394762705","https://openalex.org/W4396941249","https://openalex.org/W4399728165","https://openalex.org/W4401988131","https://openalex.org/W4402817372","https://openalex.org/W4403277141","https://openalex.org/W4404479756","https://openalex.org/W4406921704","https://openalex.org/W4406982839","https://openalex.org/W4408182599","https://openalex.org/W4408355476","https://openalex.org/W4409383105","https://openalex.org/W4409462227","https://openalex.org/W4410050224","https://openalex.org/W4410226950","https://openalex.org/W4410808562"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Despite":[0],"the":[1,38,53,60,78,81,115,136,181],"remarkable":[2],"progress":[3],"achieved":[4],"by":[5,114],"synthetic":[6],"aperture":[7],"radar":[8],"(SAR)":[9],"imagery":[10,87],"in":[11,20,180],"tasks":[12],"such":[13],"as":[14],"scene":[15],"classification":[16],"and":[17,26,42,88,106,132,145,149,177,191],"object":[18],"detection":[19],"recent":[21],"years,":[22],"automatically":[23],"generating":[24],"accurate":[25],"structurally":[27],"coherent":[28],"natural":[29,89],"language":[30,90,196],"descriptions":[31],"remains":[32],"a":[33,70,109,187],"significant":[34],"challenge":[35],"due":[36],"to":[37],"inherent":[39],"structural":[40],"complexity":[41],"semantic":[43,72,103,175],"ambiguity":[44],"of":[45,85,198],"SAR":[46,61,86,182],"data.":[47],"In":[48],"this":[49,93,130],"paper,":[50],"we":[51,95,134],"propose":[52],"first":[54],"large-scale":[55],"benchmark":[56],"dataset":[57,172],"tailored":[58],"for":[59,164,194],"image":[62,183],"captioning":[63,184],"task.":[64],"Our":[65],"central":[66],"insight":[67],"is":[68],"that":[69,100,170],"hierarchical":[71],"modeling":[73],"strategy":[74,131],"can":[75],"effectively":[76],"bridge":[77],"gap":[79],"between":[80],"unique":[82],"visual":[83],"characteristics":[84],"expression.":[91],"To":[92],"end,":[94],"design":[96],"an":[97],"annotation":[98,111,122,126],"protocol":[99],"spans":[101],"three":[102],"layers\u2014object,":[104],"relation,":[105],"scene\u2014and":[107],"develop":[108],"semi-automated":[110],"framework":[112],"assisted":[113],"large":[116],"model":[117],"GPT-4V,":[118],"significantly":[119],"reducing":[120],"human":[121],"cost":[123],"while":[124],"ensuring":[125],"quality.":[127],"Based":[128],"on":[129,142],"framework,":[133],"construct":[135],"ATRNet-SARCap":[137],"1.0":[138],"dataset,":[139],"which":[140],"focuses":[141],"aircraft":[143],"targets":[144],"covers":[146],"5,251":[147],"images":[148],"47,259":[150],"structured":[151],"caption":[152],"sentences.":[153],"We":[154],"further":[155],"conduct":[156],"systematic":[157],"experiments":[158],"using":[159],"various":[160],"mainstream":[161],"encoder-decoder":[162],"frameworks":[163],"visionlanguage":[165],"modeling.":[166],"The":[167],"results":[168],"demonstrate":[169],"our":[171],"substantially":[173],"enhances":[174],"completeness":[176],"expression":[178],"accuracy":[179],"task,":[185],"providing":[186],"highquality":[188],"data":[189],"foundation":[190],"research":[192],"paradigm":[193],"advancing":[195],"understanding":[197],"remote":[199],"sensing":[200],"imagery.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}