{"id":"https://openalex.org/W3214363026","doi":"https://doi.org/10.1145/3474717.3483631","title":"Remote Sensing Image Captioning with Continuous Output Neural Models","display_name":"Remote Sensing Image Captioning with Continuous Output Neural Models","publication_year":2021,"publication_date":"2021-11-02","ids":{"openalex":"https://openalex.org/W3214363026","doi":"https://doi.org/10.1145/3474717.3483631","mag":"3214363026"},"language":"en","primary_location":{"id":"doi:10.1145/3474717.3483631","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474717.3483631","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474717.3483631","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3474717.3483631","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073069587","display_name":"Rita Ramos","orcid":"https://orcid.org/0000-0002-8741-8164"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Rita Ramos","raw_affiliation_strings":["INESC-ID, Instituto Superior T\u00e9cnico, University of Lisbon, Lisbon, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INESC-ID, Instituto Superior T\u00e9cnico, University of Lisbon, Lisbon, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I141596103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055101594","display_name":"Bruno Martins","orcid":"https://orcid.org/0000-0002-3856-2936"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Bruno Martins","raw_affiliation_strings":["INESC-ID & LUMLIS (Lisbon ELLIS Unit), Instituto Superior T\u00e9cnico, University of Lisbon, Lisbon, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INESC-ID & LUMLIS (Lisbon ELLIS Unit), Instituto Superior T\u00e9cnico, University of Lisbon, Lisbon, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I141596103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2911,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57369991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"32"},"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":0.9976000189781189,"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":0.9918000102043152,"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":0.8974089622497559},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7911485433578491},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7272367477416992},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6805535554885864},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5970901846885681},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5278793573379517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5191354155540466},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5149782299995422},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4778006672859192},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.4595022201538086},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.43906328082084656},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4250994026660919},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3934102952480316},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11431661248207092}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8974089622497559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7911485433578491},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7272367477416992},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6805535554885864},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5970901846885681},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5278793573379517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5191354155540466},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5149782299995422},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4778006672859192},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.4595022201538086},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43906328082084656},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4250994026660919},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3934102952480316},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11431661248207092},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474717.3483631","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474717.3483631","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474717.3483631","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3474717.3483631","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474717.3483631","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474717.3483631","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2441341484","display_name":"Instituto de Engenharia de Sistemas e Computadores, Investiga\u00e7\u00e3o e Desenvolvimento em Lisboa","funder_award_id":"UIDB/50021/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G5008780491","display_name":"Prospec\u00e7\u00e3o de informa\u00e7\u00e3o geo-referenciada de m\u00faltiplas fontes e modalidades","funder_award_id":"PTDC/CCI-CIF/32607/2017","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G5454278309","display_name":null,"funder_award_id":"/2017","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G6788841209","display_name":"Deep Learning Methods Bridging Language and Vision","funder_award_id":"2020.06106.BD","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3214363026.pdf"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1603598191","https://openalex.org/W2064675550","https://openalex.org/W2250539671","https://openalex.org/W2626778328","https://openalex.org/W2946948417","https://openalex.org/W2962743139","https://openalex.org/W2972884859","https://openalex.org/W3011916860","https://openalex.org/W3102877762"],"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/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4286432911"],"abstract_inverted_index":{"Remote":[0],"sensing":[1],"image":[2,111],"captioning":[3],"involves":[4],"generating":[5,48],"a":[6,27],"concise":[7],"textual":[8],"description":[9],"for":[10,97,101],"an":[11,41],"input":[12],"aerial":[13],"image.":[14],"Most":[15],"previous":[16],"methods":[17,120],"are":[18],"based":[19,44],"on":[20,45],"neural":[21],"encoder-decoder":[22],"models":[23],"trained":[24],"to":[25,74,138],"generate":[26],"sequence":[28],"of":[29,50,54,69,83,90],"discrete":[30,57,116],"outputs":[31,64,134],"with":[32,146],"the":[33,67,81,91,102,122,128,147,151],"standard":[34],"cross-entropy":[35],"token-level":[36],"loss.":[37],"This":[38,93],"paper":[39],"explores":[40],"alternative":[42],"method":[43],"continuous":[46,63,118,133],"outputs,":[47],"sequences":[49],"embedding":[51],"vectors":[52],"instead":[53],"directly":[55],"predicting":[56],"word":[58],"tokens.":[59],"We":[60,113],"argue":[61],"that":[62,86,132],"can":[65,135],"facilitate":[66],"optimization":[68],"semantic":[70],"similarity,":[71],"as":[72],"opposed":[73],"exact":[75],"word-by-word":[76],"matches.":[77],"It":[78],"also":[79,106],"facilitates":[80],"use":[82],"loss":[84],"functions":[85],"compare":[87],"different":[88],"views":[89],"data.":[92],"includes":[94],"comparing":[95,107],"representations":[96],"individual":[98],"tokens":[99],"and":[100,105,141],"entire":[103],"captions,":[104],"captions":[108],"against":[109],"intermediate":[110],"representations.":[112],"experimentally":[114],"compared":[115],"versus":[117],"output":[119],"over":[121],"RSICD":[123],"dataset,":[124],"extensively":[125],"used":[126],"in":[127,150],"area.":[129,152],"Results":[130],"show":[131],"indeed":[136],"lead":[137],"better":[139],"results,":[140],"our":[142],"approach":[143],"performs":[144],"competitively":[145],"state-of-the-art":[148],"model":[149]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}