{"id":"https://openalex.org/W4399571349","doi":"https://doi.org/10.1109/jstars.2024.3413323","title":"NLP-Based Fusion Approach to Robust Image Captioning","display_name":"NLP-Based Fusion Approach to Robust Image Captioning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399571349","doi":"https://doi.org/10.1109/jstars.2024.3413323"},"language":"en","primary_location":{"id":"doi:10.1109/jstars.2024.3413323","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2024.3413323","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":null,"license_id":null,"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.2024.3413323","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004777179","display_name":"Riccardo Ricci","orcid":"https://orcid.org/0000-0002-2128-7456"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Riccardo Ricci","raw_affiliation_strings":["Department of Information Engineering and Computer Science, University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2128-7456","affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021389231","display_name":"Farid Melgani","orcid":"https://orcid.org/0000-0001-9745-3732"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Farid Melgani","raw_affiliation_strings":["Department of Information Engineering and Computer Science, University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0001-9745-3732","affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071340024","display_name":"Jos\u00e9 Marcato","orcid":"https://orcid.org/0000-0002-9096-6866"},"institutions":[{"id":"https://openalex.org/I122558511","display_name":"Universidade Federal de Mato Grosso do Sul","ror":"https://ror.org/0366d2847","country_code":"BR","type":"education","lineage":["https://openalex.org/I122558511"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Marcato Junior","raw_affiliation_strings":["Federal University of Mato Grosso do Sul, Cidade Universitária, Campo Grande, MS, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-9096-6866","affiliations":[{"raw_affiliation_string":"Federal University of Mato Grosso do Sul, Cidade Universitária, Campo Grande, MS, Brazil","institution_ids":["https://openalex.org/I122558511"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017880637","display_name":"Wesley Nunes Gon\u00e7alves","orcid":"https://orcid.org/0000-0002-8815-6653"},"institutions":[{"id":"https://openalex.org/I122558511","display_name":"Universidade Federal de Mato Grosso do Sul","ror":"https://ror.org/0366d2847","country_code":"BR","type":"education","lineage":["https://openalex.org/I122558511"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Wesley Nunes Gon\u00e7alves","raw_affiliation_strings":["Federal University of Mato Grosso do Sul, Cidade Universitária, Campo Grande, MS, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-8815-6653","affiliations":[{"raw_affiliation_string":"Federal University of Mato Grosso do Sul, Cidade Universitária, Campo Grande, MS, Brazil","institution_ids":["https://openalex.org/I122558511"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004777179"],"corresponding_institution_ids":["https://openalex.org/I193223587"],"apc_list":{"value":1250,"currency":"USD","value_usd":1250},"apc_paid":{"value":1250,"currency":"USD","value_usd":1250},"fwci":0.6621,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68381753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"17","issue":null,"first_page":"11809","last_page":"11822"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991000294685364,"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":0.9932000041007996,"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":0.9148101806640625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7929107546806335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6097928881645203},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.5297238230705261},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4980509281158447},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.49039244651794434},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.43819794058799744},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3469024896621704},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32758888602256775},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11517930030822754}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9148101806640625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929107546806335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6097928881645203},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.5297238230705261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4980509281158447},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.49039244651794434},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.43819794058799744},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3469024896621704},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32758888602256775},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11517930030822754},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/jstars.2024.3413323","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2024.3413323","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":null,"license_id":null,"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:iris.unitn.it:11572/437937","is_oa":true,"landing_page_url":"https://hdl.handle.net/11572/437937","pdf_url":"https://iris.unitn.it/bitstream/11572/437937/1/2024_JSTARS-Robust_Image_Captioning.pdf","source":{"id":"https://openalex.org/S4377196320","display_name":"Iris (University of Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:b9ade1c915ec4d50ae42b5c3d70a4d74","is_oa":true,"landing_page_url":"https://doaj.org/article/b9ade1c915ec4d50ae42b5c3d70a4d74","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 11809-11822 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/jstars.2024.3413323","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2024.3413323","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":null,"license_id":null,"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/G116629194","display_name":null,"funder_award_id":"88881","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G4049964222","display_name":null,"funder_award_id":"311850/2018-01","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G5456659865","display_name":null,"funder_award_id":"2018-01","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G7649365024","display_name":null,"funder_award_id":"88881.311850/2018-01","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"}],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2102265725","https://openalex.org/W2103699041","https://openalex.org/W2105482032","https://openalex.org/W2133512280","https://openalex.org/W2158275940","https://openalex.org/W2185175083","https://openalex.org/W2510520237","https://openalex.org/W2779054585","https://openalex.org/W2896457183","https://openalex.org/W2915585235","https://openalex.org/W2919929126","https://openalex.org/W2963223306","https://openalex.org/W2994928934","https://openalex.org/W2997056851","https://openalex.org/W3008374555","https://openalex.org/W3010857614","https://openalex.org/W3047058320","https://openalex.org/W3094502228","https://openalex.org/W3098708719","https://openalex.org/W3100245404","https://openalex.org/W3107492437","https://openalex.org/W3107503524","https://openalex.org/W3147394685","https://openalex.org/W3168972675","https://openalex.org/W3196922338","https://openalex.org/W3209274285","https://openalex.org/W3213119051","https://openalex.org/W4206759674","https://openalex.org/W4211112734","https://openalex.org/W4214587440","https://openalex.org/W4224911357","https://openalex.org/W4293661094","https://openalex.org/W4307079201","https://openalex.org/W4312915946","https://openalex.org/W4385245566","https://openalex.org/W4385567053","https://openalex.org/W4388157208","https://openalex.org/W4391136447","https://openalex.org/W4394938913","https://openalex.org/W6639432524","https://openalex.org/W6682631176","https://openalex.org/W6773815586","https://openalex.org/W6791353385","https://openalex.org/W6847076894","https://openalex.org/W6849177959"],"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/W2788731446"],"abstract_inverted_index":{"Robustness":[0],"in":[1,43],"remote":[2],"sensing":[3],"image":[4],"captioning":[5,23,38,101,119],"is":[6],"crucial":[7],"for":[8,77,116],"real-world":[9],"applications.":[10],"However,":[11],"most":[12,90],"of":[13,21,52,67,75,96,109],"the":[14,19,37,50,64,68,73,106],"research":[15],"focuses":[16],"on":[17,49,72,131],"improving":[18,78],"performance":[20],"single":[22,54,89],"algorithms,":[24,120],"either":[25],"by":[26,99],"introducing":[27],"novel":[28],"feature":[29],"processing":[30,135],"units":[31],"or":[32,86],"metatasks":[33],"that":[34,47,147],"indirectly":[35],"improve":[36],"performance.":[39],"Despite":[40],"indisputable":[41],"improvements":[42],"performance,":[44],"we":[45,80],"argue":[46],"relying":[48],"output":[51],"a":[53,88,94,152],"model":[55],"can":[56,139],"be":[57,140],"critical,":[58],"especially":[59],"when":[60],"data":[61],"scarcity":[62],"limits":[63],"generalization":[65],"capability":[66],"trained":[69],"algorithms.":[70,102],"Focusing":[71],"advantages":[74],"ensembles":[76],"robustness,":[79],"propose":[81],"different":[82,100,118],"ways":[83],"to":[84],"select":[85],"generate":[87],"coherent":[91],"caption":[92],"from":[93],"set":[95],"predictions":[97],"made":[98],"The":[103],"disjunction":[104],"between":[105],"two":[107],"phases":[108],"prediction":[110],"and":[111,125],"selection/generation":[112],"provides":[113],"high":[114],"flexibility":[115],"inserting":[117],"each":[121],"with":[122,151],"its":[123],"peculiarities":[124],"strengths.":[126],"In":[127],"this":[128],"context,":[129],"based":[130],"neural":[132],"natural":[133],"language":[134],"tools,":[136],"our":[137],"approach":[138],"considered":[141],"as":[142],"an":[143],"additional":[144],"fusion":[145],"block":[146],"enables":[148],"higher":[149],"robustness":[150],"contained":[153],"complexity":[154],"burden.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-05T09:01:59.212387","created_date":"2025-10-10T00:00:00"}