{"id":"https://openalex.org/W4405521165","doi":"https://doi.org/10.1109/jstars.2024.3510414","title":"CLIP-Based Grid Features and Masking for Remote Sensing Image Captioning","display_name":"CLIP-Based Grid Features and Masking for Remote Sensing Image Captioning","publication_year":2024,"publication_date":"2024-12-18","ids":{"openalex":"https://openalex.org/W4405521165","doi":"https://doi.org/10.1109/jstars.2024.3510414"},"language":"en","primary_location":{"id":"doi:10.1109/jstars.2024.3510414","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2024.3510414","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.2024.3510414","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053391771","display_name":"Qiaoling Lin","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":true,"raw_author_name":"Qiaoling Lin","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065660222","display_name":"Shuang Wang","orcid":"https://orcid.org/0000-0003-4940-1211"},"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":"Shuang Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091541090","display_name":"Xiutiao Ye","orcid":"https://orcid.org/0009-0002-0088-606X"},"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":"Xiutiao Ye","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707149","display_name":"Ruixuan Wang","orcid":"https://orcid.org/0000-0002-8714-0369"},"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":"Ruixuan Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039983188","display_name":"Rui Yang","orcid":"https://orcid.org/0000-0002-3209-0456"},"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":"Rui Yang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050630882","display_name":"Licheng Jiao","orcid":"https://orcid.org/0000-0003-3354-9617"},"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 of Ministry of Education of China, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5053391771"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":{"value":1250,"currency":"USD","value_usd":1250},"apc_paid":{"value":1250,"currency":"USD","value_usd":1250},"fwci":1.8077,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.870721,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"18","issue":null,"first_page":"2631","last_page":"2642"},"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":0.9979000091552734,"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":0.9979000091552734,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9973999857902527,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9858999848365784,"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":0.8933550119400024},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7793029546737671},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.7784618735313416},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5105003118515015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47014883160591125},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4523318111896515},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4107389748096466},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.35265666246414185},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.08208620548248291}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8933550119400024},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7793029546737671},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.7784618735313416},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5105003118515015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47014883160591125},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4523318111896515},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4107389748096466},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.35265666246414185},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.08208620548248291},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstars.2024.3510414","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2024.3510414","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:ef8d52afd8134d9c8bb6a7299163d891","is_oa":true,"landing_page_url":"https://doaj.org/article/ef8d52afd8134d9c8bb6a7299163d891","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 2631-2642 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/jstars.2024.3510414","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2024.3510414","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/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/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/G6983301035","display_name":null,"funder_award_id":"62201407","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W1980038761","https://openalex.org/W2086866337","https://openalex.org/W2194775991","https://openalex.org/W2506483933","https://openalex.org/W2510520237","https://openalex.org/W2603566245","https://openalex.org/W2779054585","https://openalex.org/W2896348597","https://openalex.org/W2911584214","https://openalex.org/W2920981979","https://openalex.org/W2963446712","https://openalex.org/W2979924880","https://openalex.org/W2997591391","https://openalex.org/W3006487741","https://openalex.org/W3011916860","https://openalex.org/W3012111773","https://openalex.org/W3015625772","https://openalex.org/W3017628311","https://openalex.org/W3035497460","https://openalex.org/W3091588028","https://openalex.org/W3154766321","https://openalex.org/W3165084071","https://openalex.org/W3173220247","https://openalex.org/W3194015448","https://openalex.org/W3205021045","https://openalex.org/W4200272616","https://openalex.org/W4206028074","https://openalex.org/W4211112734","https://openalex.org/W4283216168","https://openalex.org/W4285744637","https://openalex.org/W4310459386","https://openalex.org/W4312389717","https://openalex.org/W4313021481","https://openalex.org/W4387802324","https://openalex.org/W4387969378","https://openalex.org/W4393148220","https://openalex.org/W4400489056","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6755207826","https://openalex.org/W6784333009","https://openalex.org/W6789753369","https://openalex.org/W6791353385","https://openalex.org/W6803567076","https://openalex.org/W6811013733","https://openalex.org/W6847076894","https://openalex.org/W6849177959","https://openalex.org/W6851800889","https://openalex.org/W6854866820","https://openalex.org/W6898505805"],"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":{"Remote":[0],"sensing":[1],"image":[2,14],"(RSI)":[3],"captioning":[4,97],"is":[5],"a":[6,81,90,110,129],"vision-language":[7,52,111],"multimodal":[8],"task":[9],"that":[10],"aims":[11],"to":[12,65,68,114,133,138],"describe":[13],"content":[15],"in":[16],"natural":[17],"language,":[18],"facilitating":[19],"accurate":[20],"and":[21,89,152],"convenient":[22],"comprehension":[23],"of":[24,108,159],"RSIs.":[25,121],"Existing":[26],"methods":[27],"primarily":[28],"focus":[29],"on":[30,42,61,148],"extracting":[31],"visual":[32,86,106,117],"features":[33,88,119],"using":[34],"vision-task":[35],"pretraining":[36,112],"models,":[37],"such":[38],"as":[39],"ResNet":[40],"pretrained":[41],"the":[43,51,95,105,139,142,149,156],"ImageNet,":[44],"which":[45],"may":[46],"not":[47],"be":[48],"optimal":[49],"for":[50,94],"task.":[53,98],"In":[54,76],"addition,":[55],"there":[56],"has":[57],"been":[58],"limited":[59],"emphasis":[60],"text":[62],"preprocessing,":[63],"leading":[64],"missed":[66],"opportunities":[67],"explore":[69],"potential":[70],"relationships":[71],"among":[72],"words":[73],"within":[74],"sentences.":[75],"this":[77],"article,":[78],"we":[79,103],"propose":[80],"transformer-based":[82],"model":[83,140],"utilizing":[84],"CLIP":[85],"grid":[87,118],"random":[91,130],"masking":[92,131],"strategy":[93,132],"RSI":[96,101],"To":[99],"enhance":[100],"representations,":[102],"utilize":[104],"encoder":[107],"CLIP,":[109],"model,":[113],"directly":[115],"extract":[116],"from":[120],"Subsequently,":[122],"all":[123],"training":[124,143],"sentences":[125],"undergo":[126],"preprocessing":[127],"via":[128],"impart":[134],"self-supervised":[135],"text-learning":[136],"capabilities":[137],"during":[141],"stage.":[144],"Extensive":[145],"experiments":[146],"conducted":[147],"RSICD,":[150],"UCM-Captions,":[151],"Sydney-Captions":[153],"datasets":[154],"demonstrate":[155],"superior":[157],"performance":[158],"our":[160],"method.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}