{"id":"https://openalex.org/W4394585954","doi":"https://doi.org/10.1109/tgrs.2024.3385500","title":"A Multiscale Grouping Transformer With CLIP Latents for Remote Sensing Image Captioning","display_name":"A Multiscale Grouping Transformer With CLIP Latents for Remote Sensing Image Captioning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394585954","doi":"https://doi.org/10.1109/tgrs.2024.3385500"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2024.3385500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3385500","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/A5050813726","display_name":"Lingwu Meng","orcid":"https://orcid.org/0000-0001-9762-3738"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingwu Meng","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378733","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0001-9752-6671"},"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":"Jing Wang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066549670","display_name":"Ran Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Meng","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397623","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5245-3584"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-5245-3584","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020302879","display_name":"Liang Xiao","orcid":"https://orcid.org/0000-0003-0178-9384"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Xiao","raw_affiliation_strings":["School of Computer Science and Engineering and the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Nanjing University of Science and Technology, Nanjing, China","School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0178-9384","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering and the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.9268,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.97205443,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"62","issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980999827384949,"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":0.9980999827384949,"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":0.996999979019165,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9884999990463257,"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":0.798437237739563},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6699814796447754},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.6156191825866699},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5205296277999878},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5122386813163757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4386480450630188},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43304887413978577},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3459030091762543},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.2596972584724426},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10645830631256104},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08804130554199219}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.798437237739563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6699814796447754},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.6156191825866699},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5205296277999878},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5122386813163757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4386480450630188},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43304887413978577},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3459030091762543},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.2596972584724426},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10645830631256104},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08804130554199219},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2024.3385500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3385500","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/G2654280866","display_name":null,"funder_award_id":"62302255","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5868074668","display_name":null,"funder_award_id":"2023TQ0181","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G6139295486","display_name":null,"funder_award_id":"JSGP202101","funder_id":"https://openalex.org/F4320327542","funder_display_name":"Jiangsu Key Laboratory of Spectral Imaging and Intelligence Sense"},{"id":"https://openalex.org/G8865264709","display_name":null,"funder_award_id":"JSGP202204","funder_id":"https://openalex.org/F4320327542","funder_display_name":"Jiangsu Key Laboratory of Spectral Imaging and Intelligence Sense"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320327542","display_name":"Jiangsu Key Laboratory of Spectral Imaging and Intelligence Sense","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W62621907","https://openalex.org/W825973156","https://openalex.org/W1889624880","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W1980038761","https://openalex.org/W2086866337","https://openalex.org/W2101105183","https://openalex.org/W2101926813","https://openalex.org/W2108598243","https://openalex.org/W2176263492","https://openalex.org/W2194775991","https://openalex.org/W2506483933","https://openalex.org/W2510520237","https://openalex.org/W2515866431","https://openalex.org/W2745461083","https://openalex.org/W2779054585","https://openalex.org/W2920981979","https://openalex.org/W2963084599","https://openalex.org/W2963091558","https://openalex.org/W2963418739","https://openalex.org/W2979924880","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3035821888","https://openalex.org/W3100245404","https://openalex.org/W3105577662","https://openalex.org/W3117344638","https://openalex.org/W3119804198","https://openalex.org/W3162930275","https://openalex.org/W3170033848","https://openalex.org/W3194015448","https://openalex.org/W3213759681","https://openalex.org/W4205659311","https://openalex.org/W4206111836","https://openalex.org/W4211112734","https://openalex.org/W4213052879","https://openalex.org/W4213449032","https://openalex.org/W4224035735","https://openalex.org/W4285744637","https://openalex.org/W4289537913","https://openalex.org/W4293732058","https://openalex.org/W4313021481","https://openalex.org/W4362598957","https://openalex.org/W4385245566","https://openalex.org/W4387350510","https://openalex.org/W4387802245","https://openalex.org/W4387986561","https://openalex.org/W6620707391","https://openalex.org/W6621543089","https://openalex.org/W6637306801","https://openalex.org/W6678262379","https://openalex.org/W6679436768","https://openalex.org/W6682086108","https://openalex.org/W6682631176","https://openalex.org/W6685322675","https://openalex.org/W6791353385","https://openalex.org/W6809885388"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4323777661","https://openalex.org/W4388184981","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W4298897568"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"has":[2],"shown":[3],"that":[4],"integrating":[5],"multiscale":[6,145],"visual":[7,146,202],"features":[8,89,117,126,203],"with":[9,68,118,139],"advanced":[10],"Transformer":[11,67,131,134,187],"architectures":[12],"is":[13,108],"a":[14,64,80,85,93,100,104,130,163,171],"promising":[15],"approach":[16],"for":[17,75,213],"remote":[18],"sensing":[19],"image":[20,82,102,113,125],"captioning":[21],"(RSIC).":[22],"However,":[23],"the":[24,40,51,112,123,150,155,159,191,209,216,225,228],"lack":[25],"of":[26,42,78,87,154,201,211,227],"local":[27,151],"modeling":[28,152],"ability":[29,153],"in":[30,48,158],"self-attention":[31,156],"may":[32],"potentially":[33],"lead":[34],"to":[35,110,143,180,195],"inaccurate":[36],"contextual":[37,184],"information.":[38,185],"Moreover,":[39],"scarcity":[41],"trainable":[43],"image-caption":[44],"pairs":[45],"poses":[46],"challenges":[47],"effectively":[49],"harnessing":[50],"semantic":[52],"alignment":[53],"between":[54,198],"images":[55,214],"and":[56,84,115,204],"texts.":[57],"To":[58,98,148],"mitigate":[59],"these":[60],"issues,":[61],"we":[62,161],"propose":[63],"Multiscale":[65],"Grouping":[66,165],"Contrastive":[69],"Language-Image":[70],"Pre-training":[71],"(CLIP)":[72],"latents":[73],"(MG-Transformer)":[74],"RSIC.":[76],"First":[77],"all,":[79],"CLIP":[81],"embedding":[83,114],"set":[86],"region":[88,116],"are":[90,127],"extracted":[91],"within":[92],"Multi-level":[94],"Feature":[95],"Extraction":[96],"module.":[97],"achieve":[99],"comprehensive":[101],"representation,":[103],"Semantic":[105],"Correlation":[106],"module":[107],"designed":[109],"integrate":[111],"an":[119],"attention":[120,178],"gate.":[121],"Subsequently,":[122],"integrated":[124],"fed":[128],"into":[129,174],"model.":[132],"The":[133,186,231],"encoder":[135],"utilizes":[136],"dilated":[137],"convolutions":[138],"different":[140,183],"dilation":[141],"rates":[142],"obtain":[144],"features.":[147,206],"enhance":[149],"mechanism":[157,169,194],"encoder,":[160],"introduce":[162],"Global":[164],"Attention":[166],"mechanism.":[167],"This":[168,207],"incorporates":[170],"grouping":[172],"operation":[173],"self-attention,":[175],"allowing":[176],"each":[177],"head":[179],"focus":[181],"on":[182,220],"decoder":[188],"then":[189],"adopts":[190],"Meshed":[192],"Cross-Attention":[193],"establish":[196],"relationships":[197],"various":[199],"scales":[200],"text":[205],"facilitates":[208],"generation":[210],"captions":[212],"by":[215],"decoder.":[217],"Experimental":[218],"results":[219],"three":[221],"RSIC":[222],"datasets":[223],"demonstrate":[224],"superiority":[226],"proposed":[229],"MG-Transformer.":[230],"code":[232],"will":[233],"be":[234],"publicly":[235],"available":[236],"at":[237],"https://github.com/One-paper-luck/MG-Transformer.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}