{"id":"https://openalex.org/W4402260575","doi":"https://doi.org/10.1109/igarss53475.2024.10641975","title":"Merging Patches and Tokens: A VQA System for Remote Sensing","display_name":"Merging Patches and Tokens: A VQA System for Remote Sensing","publication_year":2024,"publication_date":"2024-07-07","ids":{"openalex":"https://openalex.org/W4402260575","doi":"https://doi.org/10.1109/igarss53475.2024.10641975"},"language":"en","primary_location":{"id":"doi:10.1109/igarss53475.2024.10641975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss53475.2024.10641975","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/A5111316083","display_name":"Damian Falk","orcid":null},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Damian Falk","raw_affiliation_strings":["University of St.Gallen,AIML Lab, School of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of St.Gallen,AIML Lab, School of Computer Science","institution_ids":["https://openalex.org/I202963720"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009801388","display_name":"Kaan Aydin","orcid":null},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Kaan Aydin","raw_affiliation_strings":["University of St.Gallen,AIML Lab, School of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of St.Gallen,AIML Lab, School of Computer Science","institution_ids":["https://openalex.org/I202963720"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006658500","display_name":"Linus Scheibenreif","orcid":"https://orcid.org/0000-0001-5580-8910"},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Linus Scheibenreif","raw_affiliation_strings":["University of St.Gallen,AIML Lab, School of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of St.Gallen,AIML Lab, School of Computer Science","institution_ids":["https://openalex.org/I202963720"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065722787","display_name":"Damian Borth","orcid":"https://orcid.org/0000-0002-4660-2627"},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Damian Borth","raw_affiliation_strings":["University of St.Gallen,AIML Lab, School of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of St.Gallen,AIML Lab, School of Computer Science","institution_ids":["https://openalex.org/I202963720"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I202963720"],"apc_list":null,"apc_paid":null,"fwci":0.242,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55966443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"694","last_page":"698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11588","display_name":"Atmospheric and Environmental Gas Dynamics","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11588","display_name":"Atmospheric and Environmental Gas Dynamics","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.9871000051498413,"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"}},{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.973800003528595,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6548261642456055},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.46231895685195923},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.21554628014564514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6548261642456055},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.46231895685195923},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.21554628014564514}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/igarss53475.2024.10641975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss53475.2024.10641975","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":[{"score":0.4099999964237213,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W1933349210","https://openalex.org/W2108598243","https://openalex.org/W2896457183","https://openalex.org/W2940726923","https://openalex.org/W2963717374","https://openalex.org/W2964072591","https://openalex.org/W2983550634","https://openalex.org/W3007556011","https://openalex.org/W3012111773","https://openalex.org/W3047579407","https://openalex.org/W3094502228","https://openalex.org/W3098351727","https://openalex.org/W3168972675","https://openalex.org/W3207025788","https://openalex.org/W4220845020","https://openalex.org/W4305005880","https://openalex.org/W4312719444","https://openalex.org/W4387828725","https://openalex.org/W6755207826","https://openalex.org/W6784333009","https://openalex.org/W6845668075"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,43],"investigate":[4],"the":[5,26,46,78,92,97],"integration":[6],"of":[7,48,83],"transformer-based":[8],"feature":[9,34,58],"extractors":[10,59],"in":[11,55,70],"a":[12,52,65],"Remote":[13],"Sensing":[14],"Visual":[15],"Question":[16],"Answering":[17],"(RSVQA)":[18],"framework.":[19],"Our":[20,62],"findings":[21],"demonstrate":[22],"an":[23],"improvement":[24],"to":[25,104],"baseline":[27],"achieved":[28],"through":[29],"additional":[30],"attention":[31],"modules":[32],"after":[33],"extraction":[35],"and":[36,100],"using":[37],"MUTAN":[38],"(Multimodal":[39],"Tucker":[40],"Fusion).":[41],"Further,":[42],"delve":[44],"into":[45],"potential":[47],"multi-task":[49],"learning,":[50],"observing":[51],"considerable":[53],"boost":[54],"performance":[56],"when":[57],"are":[60],"trained.":[61],"results":[63],"suggest":[64],"promising":[66],"future":[67],"research":[68],"avenue":[69],"multitask":[71],"learning":[72],"for":[73,80,95],"RSVQA,":[74],"while":[75],"also":[76],"emphasizing":[77],"need":[79],"careful":[81],"selection":[82],"hyperparameters":[84],"per":[85],"question":[86],"type":[87],"as":[88,90],"well":[89],"finding":[91],"proper":[93],"balance":[94],"training":[96],"shared":[98],"backbone":[99],"individual":[101],"classifiers":[102],"simultaneously":[103],"further":[105],"improve":[106],"performance.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}