{"id":"https://openalex.org/W4402260632","doi":"https://doi.org/10.1109/igarss53475.2024.10641565","title":"DP-RSCAP: Dual Prompt-Based Scene and Entity Network for Remote Sensing Image Captioning","display_name":"DP-RSCAP: Dual Prompt-Based Scene and Entity Network for Remote Sensing Image Captioning","publication_year":2024,"publication_date":"2024-07-07","ids":{"openalex":"https://openalex.org/W4402260632","doi":"https://doi.org/10.1109/igarss53475.2024.10641565"},"language":"en","primary_location":{"id":"doi:10.1109/igarss53475.2024.10641565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss53475.2024.10641565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium","raw_type":"proceedings-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/A5067691968","display_name":"Lanxiao Wang","orcid":"https://orcid.org/0000-0002-3745-0262"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lanxiao Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066434602","display_name":"Heqian Qiu","orcid":"https://orcid.org/0000-0002-0963-0311"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heqian Qiu","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013715827","display_name":"Minjian Zhang","orcid":"https://orcid.org/0000-0002-5012-148X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minjian Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100617043","display_name":"Fanman Meng","orcid":"https://orcid.org/0000-0002-3016-2567"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fanman Meng","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075737786","display_name":"Qingbo Wu","orcid":"https://orcid.org/0000-0003-2936-6340"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingbo Wu","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114378292","display_name":"Hongliang Li","orcid":"https://orcid.org/0000-0002-7481-095X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongliang Li","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5067691968"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":1.3748,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81948747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7129","last_page":"7132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9882000088691711,"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/closed-captioning","display_name":"Closed captioning","score":0.9262161254882812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7482472062110901},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.7244929671287537},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5645170211791992},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.501533031463623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4811016917228699},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.32157379388809204},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09365451335906982}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9262161254882812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7482472062110901},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.7244929671287537},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5645170211791992},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.501533031463623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4811016917228699},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.32157379388809204},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09365451335906982},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/igarss53475.2024.10641565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss53475.2024.10641565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":11,"referenced_works":["https://openalex.org/W2779054585","https://openalex.org/W2986534680","https://openalex.org/W3100245404","https://openalex.org/W3130184989","https://openalex.org/W3154766321","https://openalex.org/W3206063331","https://openalex.org/W4312389717","https://openalex.org/W4312915946","https://openalex.org/W4391305855","https://openalex.org/W4391341588","https://openalex.org/W4394938913"],"related_works":["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/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W2352553236"],"abstract_inverted_index":{"As":[0],"a":[1,61,121,141],"challenging":[2,173],"task":[3],"towards":[4],"remote":[5,13],"sensing":[6,14],"image":[7,15],"analysis,":[8],"the":[9,22,35,46,75,92,99,150,172,176],"core":[10],"problem":[11],"of":[12,48,77,101,179],"captioning":[16],"is":[17],"how":[18],"to":[19,72,90,111,146],"accurately":[20],"transform":[21],"vision":[23],"information":[24,51,86,157],"into":[25],"text":[26,84],"information.":[27],"Existing":[28],"methods":[29],"usually":[30],"achieve":[31],"it":[32],"based":[33],"on":[34,171],"simple":[36],"multi-task":[37],"learning":[38],"strategy":[39],"or":[40],"visual":[41,134,151],"attention":[42],"mechanism,":[43],"which":[44,70,126,162],"ignores":[45],"importance":[47],"intermediate":[49,88,160],"connection":[50,89],"for":[52],"cross-modal":[53,78],"transformation.":[54],"To":[55],"solve":[56],"above":[57],"problem,":[58],"we":[59,104,119,138],"propose":[60],"novel":[62],"dual":[63,142,155],"prompt-based":[64,143],"scene":[65,122,129],"and":[66,97,131,148,154],"entity":[67,114],"network":[68],"(DP-RSCap)":[69],"aims":[71],"fully":[73],"utilize":[74],"ability":[76,178],"alignment":[79],"in":[80,116,165],"vision-language":[81],"model":[82],"build":[83],"prior":[85],"as":[87,158],"narrow":[91],"gap":[93],"between":[94],"different":[95],"modalities":[96],"improve":[98],"quality":[100],"caption.":[102,168],"Specifically,":[103],"first":[105],"introduce":[106],"an":[107],"entity-concept":[108],"prompt":[109,124],"exporter":[110],"obtain":[112,132],"explicit":[113,159],"concepts":[115],"images.":[117],"Then,":[118],"design":[120,140],"class":[123,130],"generator":[125],"can":[127,163],"predict":[128],"fine-grained":[133],"semantic":[135,152],"features.":[136],"Finally,":[137],"further":[139],"caption":[144],"decoder":[145],"align":[147],"merge":[149],"feature":[153],"prompts":[156],"connections,":[161],"assist":[164],"generating":[166],"precise":[167],"Extensive":[169],"experiments":[170],"RSICD":[174],"demonstrate":[175],"superior":[177],"our":[180],"model.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}