{"id":"https://openalex.org/W4391924192","doi":"https://doi.org/10.1109/whispers61460.2023.10430788","title":"Multimodal Fusion Methods with Vision Transformers for Remote Sensing Semantic Segmentation","display_name":"Multimodal Fusion Methods with Vision Transformers for Remote Sensing Semantic Segmentation","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4391924192","doi":"https://doi.org/10.1109/whispers61460.2023.10430788"},"language":"en","primary_location":{"id":"doi:10.1109/whispers61460.2023.10430788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/whispers61460.2023.10430788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 13th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://boa.unimib.it/bitstream/10281/446101/1/Morelli-2023-Whispers-AMM.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093952916","display_name":"Veronica Grazia Morelli","orcid":null},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Veronica Grazia Morelli","raw_affiliation_strings":["University of Milano-Bicocca,Systems and Communications (DISCo),Department of Informatics,Milan,Italy,20126"],"affiliations":[{"raw_affiliation_string":"University of Milano-Bicocca,Systems and Communications (DISCo),Department of Informatics,Milan,Italy,20126","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062273130","display_name":"Mirko Paolo Barbato","orcid":"https://orcid.org/0000-0002-3967-8957"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mirko Paolo Barbato","raw_affiliation_strings":["University of Milano-Bicocca,Systems and Communications (DISCo),Department of Informatics,Milan,Italy,20126"],"affiliations":[{"raw_affiliation_string":"University of Milano-Bicocca,Systems and Communications (DISCo),Department of Informatics,Milan,Italy,20126","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066752349","display_name":"Flavio Piccoli","orcid":"https://orcid.org/0000-0001-7432-4284"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Flavio Piccoli","raw_affiliation_strings":["University of Milano-Bicocca,Systems and Communications (DISCo),Department of Informatics,Milan,Italy,20126"],"affiliations":[{"raw_affiliation_string":"University of Milano-Bicocca,Systems and Communications (DISCo),Department of Informatics,Milan,Italy,20126","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053344554","display_name":"Paolo Napoletano","orcid":"https://orcid.org/0000-0001-9112-0574"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Napoletano","raw_affiliation_strings":["University of Milano-Bicocca,Systems and Communications (DISCo),Department of Informatics,Milan,Italy,20126"],"affiliations":[{"raw_affiliation_string":"University of Milano-Bicocca,Systems and Communications (DISCo),Department of Informatics,Milan,Italy,20126","institution_ids":["https://openalex.org/I66752286"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5093952916"],"corresponding_institution_ids":["https://openalex.org/I66752286"],"apc_list":null,"apc_paid":null,"fwci":0.4864,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70519337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996399998664856,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9904999732971191,"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":0.6848536133766174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6176608204841614},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6173378229141235},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5551453232765198},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5390114188194275},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.48100098967552185},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4468268156051636},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4134059250354767},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.3388362526893616},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.13356313109397888},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1313515603542328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6848536133766174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6176608204841614},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6173378229141235},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5551453232765198},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5390114188194275},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48100098967552185},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4468268156051636},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4134059250354767},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3388362526893616},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.13356313109397888},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1313515603542328},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/whispers61460.2023.10430788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/whispers61460.2023.10430788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 13th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS)","raw_type":"proceedings-article"},{"id":"pmh:oai:boa.unimib.it:10281/446101","is_oa":true,"landing_page_url":"https://hdl.handle.net/10281/446101","pdf_url":"https://boa.unimib.it/bitstream/10281/446101/1/Morelli-2023-Whispers-AMM.pdf","source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:boa.unimib.it:10281/446101","is_oa":true,"landing_page_url":"https://hdl.handle.net/10281/446101","pdf_url":"https://boa.unimib.it/bitstream/10281/446101/1/Morelli-2023-Whispers-AMM.pdf","source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391924192.pdf","grobid_xml":"https://content.openalex.org/works/W4391924192.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2767290858","https://openalex.org/W2884822772","https://openalex.org/W2889985731","https://openalex.org/W2966715458","https://openalex.org/W3007268491","https://openalex.org/W3048631361","https://openalex.org/W3099319035","https://openalex.org/W3102692100","https://openalex.org/W3110908156","https://openalex.org/W3132607382","https://openalex.org/W3138516171","https://openalex.org/W4321483963","https://openalex.org/W4362519158","https://openalex.org/W4376226279","https://openalex.org/W4385697395","https://openalex.org/W4387828735","https://openalex.org/W6766904570","https://openalex.org/W6788135285"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2099421762","https://openalex.org/W2530546662","https://openalex.org/W2967030268","https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W1522196789","https://openalex.org/W2152662039"],"abstract_inverted_index":{"This":[0,21,125],"paper":[1],"presents":[2],"a":[3,12,70],"comparative":[4],"analysis":[5],"of":[6,26,33,72,79,114,141,144],"transformerbased":[7],"fusion":[8,28,133],"methods":[9,29,83,134],"applied":[10],"to":[11,89,130],"novel":[13],"multimodal":[14],"dataset":[15,102],"for":[16,38],"remote":[17],"sensing":[18],"semantic":[19],"segmentation.":[20],"investigation":[22],"evaluates":[23],"the":[24,31,34,43,54,77,100,108,142],"impact":[25],"several":[27],"on":[30,99,120],"accuracy":[32],"results.":[35],"In":[36],"particular,":[37],"early":[39],"fusion,":[40,48,74],"we":[41,49,75],"investigate":[42,50,76],"Early":[44],"Concatenation.":[45,81],"For":[46],"middle":[47],"four":[51],"methods,":[52],"namely":[53],"Token":[55,61],"Patch":[56,59],"Embedding,":[57,60],"Channel":[58],"Fusion":[62],"at":[63],"Attention":[64],"Level,":[65],"and":[66,117,123],"Cross-Attention.":[67],"Finally,":[68],"as":[69],"representative":[71],"late":[73],"use":[78],"Late":[80,105],"The":[82],"presented":[84],"here":[85],"are":[86],"specifically":[87],"designed":[88],"operate":[90],"effectively":[91],"with":[92],"all":[93],"modalities":[94],"under":[95],"investigation.":[96],"Experiments":[97],"conducted":[98],"Ticino":[101],"show":[103],"that":[104],"Concatenation":[106],"outperforms":[107],"best":[109],"single":[110],"modality":[111],"RGB":[112],"method":[113],"4.04%,":[115],"2.24%":[116],"3.47%":[118],"respectively":[119],"accuracy,":[121],"precision":[122],"mIoU.":[124],"study":[126],"provides":[127],"an":[128],"opportunity":[129],"further":[131],"explore":[132],"utilizing":[135],"transformers,":[136],"thereby":[137],"enhancing":[138],"our":[139],"understanding":[140],"potential":[143],"data":[145],"fusion.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}