{"id":"https://openalex.org/W4400977318","doi":"https://doi.org/10.1109/tgrs.2024.3426359","title":"Multi-View Feature Fusion and Visual Prompt for Remote Sensing Image Captioning","display_name":"Multi-View Feature Fusion and Visual Prompt for Remote Sensing Image Captioning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400977318","doi":"https://doi.org/10.1109/tgrs.2024.3426359"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2024.3426359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3426359","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/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":true,"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&#x2019;an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091764131","display_name":"Qiaoling Lin","orcid":"https://orcid.org/0000-0003-1633-0293"},"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":"Qiaoling Lin","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi&#x2019;an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi&#x2019;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&#x2019;an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087012500","display_name":"Yu Liao","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":"Yu Liao","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi&#x2019;an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085893076","display_name":"Dou Quan","orcid":"https://orcid.org/0000-0001-6943-4657"},"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":"Dou Quan","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi&#x2019;an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111268514","display_name":"Zhongqian Jin","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":"Zhongqian Jin","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi&#x2019;an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi&#x2019;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 of Ministry of Education of China, Xidian University, Xi&#x2019;an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050630882","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 of Ministry of Education of China, Xidian University, Xi&#x2019;an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5065660222"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":2.9914,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.92429913,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"62","issue":null,"first_page":"1","last_page":"17"},"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":0.9993000030517578,"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":0.9993000030517578,"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":0.9930999875068665,"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":0.9905999898910522,"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":0.8717807531356812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7272237539291382},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6042933464050293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5770066380500793},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.5765445232391357},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.5704920887947083},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5469184517860413},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4622262716293335},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.455181360244751},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42954644560813904},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.411579430103302},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.21071064472198486}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8717807531356812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7272237539291382},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6042933464050293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5770066380500793},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.5765445232391357},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.5704920887947083},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5469184517860413},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4622262716293335},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.455181360244751},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42954644560813904},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.411579430103302},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.21071064472198486},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2024.3426359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3426359","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/G1741041753","display_name":null,"funder_award_id":"U22B2054","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G631455688","display_name":null,"funder_award_id":"2022M722496","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W1980038761","https://openalex.org/W2086866337","https://openalex.org/W2101105183","https://openalex.org/W2194775991","https://openalex.org/W2506483933","https://openalex.org/W2510520237","https://openalex.org/W2575842049","https://openalex.org/W2603566245","https://openalex.org/W2745461083","https://openalex.org/W2779054585","https://openalex.org/W2810454813","https://openalex.org/W2896348597","https://openalex.org/W2911584214","https://openalex.org/W2920981979","https://openalex.org/W2963446712","https://openalex.org/W2979924880","https://openalex.org/W3006487741","https://openalex.org/W3011916860","https://openalex.org/W3015625772","https://openalex.org/W3017628311","https://openalex.org/W3091588028","https://openalex.org/W3100245404","https://openalex.org/W3119438769","https://openalex.org/W3154766321","https://openalex.org/W3173220247","https://openalex.org/W3185341429","https://openalex.org/W3194015448","https://openalex.org/W3198377975","https://openalex.org/W4206028074","https://openalex.org/W4206111836","https://openalex.org/W4211112734","https://openalex.org/W4283216168","https://openalex.org/W4310459386","https://openalex.org/W4312310776","https://openalex.org/W4312389717","https://openalex.org/W4317433994","https://openalex.org/W4361009677","https://openalex.org/W4387350510","https://openalex.org/W6637373629","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6755207826","https://openalex.org/W6767164110","https://openalex.org/W6789753369","https://openalex.org/W6791353385","https://openalex.org/W6803567076"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Remote":[0],"sensing":[1],"image":[2,13,38],"(RSI)":[3],"captioning":[4,42],"is":[5,67,119,140,184],"a":[6,46,58,113,136],"vision-language":[7,102],"multimodal":[8],"task":[9],"concentrating":[10],"on":[11,147,168],"both":[12,158],"comprehension":[14],"and":[15,43,63,74,106,152],"sentence":[16,53,133],"generation.":[17,54,134],"Several":[18],"studies":[19],"suggest":[20],"that":[21,174],"encoder\u2013decoder-based":[22,32],"methods":[23,33],"have":[24],"achieved":[25],"success":[26],"in":[27,79],"RSI":[28,41,72,80],"captioning.":[29,81],"However,":[30],"existing":[31],"may":[34],"not":[35],"fully":[36],"explore":[37],"representations":[39,73],"for":[40,52,130],"suffer":[44],"from":[45,99,160],"lack":[47],"of":[48],"additional":[49],"prompt":[50,64],"information":[51,129],"In":[55],"this":[56],"article,":[57],"novel":[59],"multi-view":[60,93],"feature":[61,87],"fusion":[62,88],"(MVP)-based":[65],"model":[66,77,105],"proposed":[68,120],"to":[69,90,121,142],"obtain":[70],"better":[71],"enhance":[75],"language":[76],"performance":[78],"Specifically,":[82],"we":[83],"design":[84],"an":[85],"attention-based":[86],"module":[89,118],"dynamically":[91],"fuse":[92],"visual":[94,115,125,150,154],"features,":[95],"which":[96,156],"are":[97,157,166],"extracted":[98],"the":[100,107,131,148,153],"fine-tuned":[101],"pretraining":[103,109],"(VLP)":[104],"vision-task":[108],"(VP)":[110],"model.":[111],"Then,":[112],"flexible":[114],"prefix":[116],"mapping":[117],"transform":[122],"images":[123],"into":[124],"prefixes,":[126,155],"providing":[127],"semantic":[128],"subsequent":[132],"Finally,":[135],"BERT-based":[137],"caption":[138],"generator":[139],"applied":[141],"generate":[143],"accurate":[144],"descriptions":[145],"based":[146],"fused":[149],"features":[151],"outputs":[159],"our":[161,175],"designed":[162],"modules.":[163],"Extensive":[164],"experiments":[165],"conducted":[167],"three":[169],"well-known":[170],"benchmark":[171],"datasets,":[172],"demonstrating":[173],"method":[176],"achieves":[177],"state-of-the-art":[178],"(SOTA)":[179],"performance.":[180],"The":[181],"relevant":[182],"code":[183],"available":[185],"at":[186],"<uri":[187],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[188],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/QiaoLing-Lin/MVP</uri>.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}