{"id":"https://openalex.org/W4402263514","doi":"https://doi.org/10.1109/igarss53475.2024.10642424","title":"FUS-MAE: A Cross-Attention-Based Data Fusion Approach for Masked Autoencoders in Remote Sensing","display_name":"FUS-MAE: A Cross-Attention-Based Data Fusion Approach for Masked Autoencoders in Remote Sensing","publication_year":2024,"publication_date":"2024-07-07","ids":{"openalex":"https://openalex.org/W4402263514","doi":"https://doi.org/10.1109/igarss53475.2024.10642424"},"language":"en","primary_location":{"id":"doi:10.1109/igarss53475.2024.10642424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss53475.2024.10642424","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":"conference-paper","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/A5093701022","display_name":"Hugo Chan-To-Hing","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hugo Chan-To-Hing","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070594442","display_name":"Bharadwaj Veeravalli","orcid":"https://orcid.org/0000-0001-9000-1813"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bharadwaj Veeravalli","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":6.3735,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.97857611,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6953","last_page":"6958"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9988999962806702,"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":0.9988999962806702,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9909999966621399,"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":0.984499990940094,"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/sensor-fusion","display_name":"Sensor fusion","score":0.6995351314544678},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6547086834907532},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5787572264671326},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5647132396697998},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3554193377494812},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33008772134780884}],"concepts":[{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.6995351314544678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6547086834907532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5787572264671326},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5647132396697998},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3554193377494812},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33008772134780884},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/igarss53475.2024.10642424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss53475.2024.10642424","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1923184257","https://openalex.org/W2599837529","https://openalex.org/W2896457183","https://openalex.org/W2949493371","https://openalex.org/W2973660294","https://openalex.org/W3035524453","https://openalex.org/W3094502228","https://openalex.org/W3101647767","https://openalex.org/W3104899156","https://openalex.org/W3159481202","https://openalex.org/W3165730205","https://openalex.org/W3176420170","https://openalex.org/W3214127792","https://openalex.org/W4206909333","https://openalex.org/W4286233797","https://openalex.org/W4288391486","https://openalex.org/W4289821912","https://openalex.org/W4292970091","https://openalex.org/W4312552594","https://openalex.org/W4312685069","https://openalex.org/W4313156423","https://openalex.org/W4376851287","https://openalex.org/W4387026640","https://openalex.org/W4387092314","https://openalex.org/W4387323951","https://openalex.org/W6755207826","https://openalex.org/W6774314701","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6796149595","https://openalex.org/W6840202747","https://openalex.org/W6857134890"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2772917594","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398","https://openalex.org/W2775347418"],"abstract_inverted_index":{"Self-supervised":[0],"frameworks":[1,153],"for":[2,65,145],"representation":[3],"learning":[4,40,99,142],"have":[5],"recently":[6],"stirred":[7],"up":[8],"interest":[9],"among":[10],"the":[11,20,32,45],"remote":[12,67],"sensing":[13,68],"community,":[14],"given":[15],"their":[16],"potential":[17],"to":[18,77,82,108],"mitigate":[19],"high":[21],"labeling":[22],"costs":[23],"associated":[24],"with":[25,126,140],"curating":[26],"large":[27],"satellite":[28],"image":[29,86],"datasets.":[30],"In":[31,91],"realm":[33],"of":[34],"multimodal":[35],"data":[36,55,113,122,147],"fusion,":[37],"while":[38],"contrastive":[39,141],"methods":[41],"can":[42,137],"help":[43],"bridge":[44],"domain":[46,129],"gap":[47],"between":[48,115],"different":[49],"sensor":[50],"types,":[51],"they":[52],"rely":[53],"on":[54,102,155],"augmentation":[56],"techniques":[57],"that":[58,105,135],"require":[59],"expertise":[60],"and":[61,111,119,149,162],"careful":[62],"design,":[63],"especially":[64],"multispectral":[66,120],"data.":[69],"A":[70],"possible":[71],"but":[72],"rather":[73],"scarcely":[74],"studied":[75],"way":[76],"circumvent":[78],"these":[79],"limitations":[80],"is":[81],"use":[83],"a":[84,97,127,156],"masked":[85,103],"modelling":[87],"based":[88,101],"pretraining":[89],"strategy.":[90],"this":[92,167],"paper,":[93],"we":[94],"introduce":[95],"Fus-MAE,":[96],"self-supervised":[98],"framework":[100],"autoencoders":[104],"uses":[106],"cross-attention":[107],"perform":[109],"early":[110],"feature-level":[112],"fusion":[114,148],"synthetic":[116],"aperture":[117],"radar":[118],"optical":[121],"-":[123],"two":[124],"modalities":[125],"significant":[128],"gap.":[130],"Our":[131],"empirical":[132],"findings":[133],"demonstrate":[134],"Fus-MAE":[136],"effectively":[138],"compete":[139],"strategies":[143],"tailored":[144],"SAR-optical":[146],"outperforms":[150],"other":[151],"masked-autoencoders":[152],"trained":[154],"larger":[157],"corpus.":[158],"For":[159],"replicability,":[160],"code":[161],"weights":[163],"are":[164],"provided":[165],"in":[166],"github":[168],"repository.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}