{"id":"https://openalex.org/W4376456352","doi":"https://doi.org/10.1109/tcsvt.2023.3274545","title":"Mutually Beneficial Transformer for Multimodal Data Fusion","display_name":"Mutually Beneficial Transformer for Multimodal Data Fusion","publication_year":2023,"publication_date":"2023-05-11","ids":{"openalex":"https://openalex.org/W4376456352","doi":"https://doi.org/10.1109/tcsvt.2023.3274545"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3274545","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3274545","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5100716988","display_name":"Jinping Wang","orcid":"https://orcid.org/0000-0002-4157-8605"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinping Wang","raw_affiliation_strings":["School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4157-8605","affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070935877","display_name":"Xiaojun Tan","orcid":"https://orcid.org/0000-0003-0137-9270"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4210106122","display_name":"Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)","ror":"https://ror.org/00y7mag53","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210106122"]},{"id":"https://openalex.org/I4391012567","display_name":"Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai)","ror":"https://ror.org/03swgqh13","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012567"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Tan","raw_affiliation_strings":["School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China","Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai, China"],"raw_orcid":"https://orcid.org/0000-0003-0137-9270","affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai, China","institution_ids":["https://openalex.org/I4210106122","https://openalex.org/I4391012567"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6075,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.96381264,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"33","issue":"12","first_page":"7466","last_page":"7479"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994000196456909,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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":0.6997084617614746},{"id":"https://openalex.org/keywords/lidar","display_name":"Lidar","score":0.6445600986480713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6185502409934998},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.5667061805725098},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4976558983325958},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4915841519832611},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.4877263009548187},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34823548793792725},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.22163712978363037},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09809136390686035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6997084617614746},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.6445600986480713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6185502409934998},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.5667061805725098},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4976558983325958},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4915841519832611},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.4877263009548187},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34823548793792725},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.22163712978363037},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09809136390686035},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3274545","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3274545","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8379294929","display_name":null,"funder_award_id":"SML2020SP011","funder_id":"https://openalex.org/F4320330495","funder_display_name":"Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)"}],"funders":[{"id":"https://openalex.org/F4320330495","display_name":"Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)","ror":"https://ror.org/00y7mag53"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W1497089125","https://openalex.org/W1965309615","https://openalex.org/W1976416886","https://openalex.org/W2089468765","https://openalex.org/W2187089797","https://openalex.org/W2623518586","https://openalex.org/W2626015899","https://openalex.org/W2744049245","https://openalex.org/W2896457183","https://openalex.org/W2908968031","https://openalex.org/W2942454403","https://openalex.org/W2963091558","https://openalex.org/W2981689412","https://openalex.org/W3004968762","https://openalex.org/W3006111439","https://openalex.org/W3008402854","https://openalex.org/W3016244469","https://openalex.org/W3024215945","https://openalex.org/W3033482004","https://openalex.org/W3034885317","https://openalex.org/W3035356612","https://openalex.org/W3035467948","https://openalex.org/W3038817281","https://openalex.org/W3081753142","https://openalex.org/W3097065222","https://openalex.org/W3104771364","https://openalex.org/W3105997607","https://openalex.org/W3121523901","https://openalex.org/W3122239467","https://openalex.org/W3128776197","https://openalex.org/W3138516171","https://openalex.org/W3159235206","https://openalex.org/W3163179572","https://openalex.org/W3168367808","https://openalex.org/W3171288715","https://openalex.org/W3177828909","https://openalex.org/W3186033197","https://openalex.org/W3203535769","https://openalex.org/W3205965083","https://openalex.org/W3209540366","https://openalex.org/W3214451643","https://openalex.org/W3214821343","https://openalex.org/W4200068923","https://openalex.org/W4210392637","https://openalex.org/W4210794570","https://openalex.org/W4213019189","https://openalex.org/W4223616928","https://openalex.org/W4225931144","https://openalex.org/W4229058281","https://openalex.org/W4285124347","https://openalex.org/W4295916779","https://openalex.org/W4301878994","https://openalex.org/W4312340363","https://openalex.org/W4312396555","https://openalex.org/W4312628331","https://openalex.org/W4312899742","https://openalex.org/W4313007769","https://openalex.org/W4317987737","https://openalex.org/W4321021766","https://openalex.org/W4376226279","https://openalex.org/W4380763457","https://openalex.org/W4386076504","https://openalex.org/W4390872797","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6784094891","https://openalex.org/W6788135285","https://openalex.org/W6790690058","https://openalex.org/W6794345597","https://openalex.org/W6797360341","https://openalex.org/W6810427767","https://openalex.org/W6839710751","https://openalex.org/W6847461194","https://openalex.org/W6851085318"],"related_works":["https://openalex.org/W2594043982","https://openalex.org/W3036493597","https://openalex.org/W4212888438","https://openalex.org/W2601157893","https://openalex.org/W2373006798","https://openalex.org/W2131735617","https://openalex.org/W2056912418","https://openalex.org/W2033213769","https://openalex.org/W4312376745","https://openalex.org/W2136016640"],"abstract_inverted_index":{"Multimodal":[0],"feature":[1,28,44,111],"fusion":[2,19,33,58],"representation,":[3],"e.g.,":[4],"hyperspectral":[5],"image":[6],"and":[7,10,77,85,89,141,149,177,183,190],"light":[8],"detection":[9],"ranging":[11],"(HSI-LiDAR)":[12],"fusion,":[13],"is":[14,100,132],"an":[15,103,128],"essential":[16],"topic":[17],"for":[18,55,109,145,162],"perception.":[20],"However,":[21],"existing":[22],"networks":[23],"tend":[24],"to":[25,83,105],"employ":[26],"mandatory":[27],"stacking":[29],"or":[30],"local":[31,124],"context":[32],"strategies":[34],"between":[35],"multiple":[36],"modalities,":[37],"ignoring":[38],"the":[39,62,121,135,153,163,171,188,193,196],"power":[40],"of":[41,123,139,192],"globally":[42],"mutual-guided":[43],"transmission.":[45],"Therefore,":[46],"this":[47,73],"paper":[48],"develops":[49],"a":[50,66,78,91,114,159],"mutually":[51],"beneficial":[52],"transformer":[53,117],"method":[54],"multimodal":[56],"data":[57,87,144],"(MBFormer),":[59],"which":[60],"contains":[61],"following":[63],"steps.":[64],"First,":[65],"spatial":[67,92,110],"constraint-based":[68],"self-attention":[69],"(SCS)":[70],"module.":[71,119],"In":[72],"module,":[74],"spectralwise":[75],"attention":[76],"spatialwise":[79],"convolution":[80],"are":[81,156],"applied":[82],"HSI":[84,108,140],"LiDAR":[86,97,143],"individually,":[88],"then":[90],"guide":[93],"mask":[94],"generated":[95],"from":[96],"elevation":[98],"information":[99,147],"used":[101],"as":[102],"agent":[104],"bridge":[106],"with":[107],"constraints.":[112],"Second,":[113],"channel":[115],"diversity-based":[116],"(CDT)":[118],"On":[120],"basis":[122],"spectral":[125],"embedding":[126],"explorations,":[127],"adaptive":[129],"token-mixer":[130],"mechanism":[131],"conducted":[133],"on":[134,181],"groupwise":[136],"classification":[137,160,179],"token":[138],"individual":[142],"global":[146],"connectivity":[148],"transitivity.":[150],"At":[151],"last,":[152],"selected":[154],"features":[155],"embedded":[157],"into":[158],"layer":[161],"final":[164],"result":[165],"calculation.":[166],"Experimental":[167],"results":[168],"show":[169],"that":[170],"proposed":[172],"MBFormer":[173,194],"can":[174],"obtain":[175],"97.76%":[176],"98.62%":[178],"accuracies":[180],"Houston":[182],"Trento":[184],"datasets,":[185],"respectively,":[186],"indicating":[187],"advantages":[189],"competitiveness":[191],"over":[195],"compared":[197],"state-of-the-art":[198],"methods.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
