{"id":"https://openalex.org/W3000063004","doi":"https://doi.org/10.1145/3338533.3366575","title":"Shifted Spatial-Spectral Convolution for Deep Neural Networks","display_name":"Shifted Spatial-Spectral Convolution for Deep Neural Networks","publication_year":2019,"publication_date":"2019-12-15","ids":{"openalex":"https://openalex.org/W3000063004","doi":"https://doi.org/10.1145/3338533.3366575","mag":"3000063004"},"language":"en","primary_location":{"id":"doi:10.1145/3338533.3366575","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3338533.3366575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Multimedia Asia","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/A5029688192","display_name":"Yuhao Xu","orcid":"https://orcid.org/0000-0003-0334-2260"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuhao Xu","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050229964","display_name":"Hideki Nakayama","orcid":"https://orcid.org/0000-0001-8726-2780"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideki Nakayama","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9990000128746033,"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":0.9990000128746033,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.998199999332428,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9972000122070312,"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/convolution","display_name":"Convolution (computer science)","score":0.8223074674606323},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7487959861755371},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.7211567163467407},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6901081204414368},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6840587854385376},{"id":"https://openalex.org/keywords/discrete-fourier-transform","display_name":"Discrete Fourier transform (general)","score":0.6421859860420227},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5969853401184082},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.5649504661560059},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.5316776633262634},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.49779582023620605},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.49130406975746155},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4874892234802246},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48145025968551636},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41469258069992065},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3590579628944397},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.29034537076950073},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24035051465034485},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20338302850723267},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.1532725691795349},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.13972756266593933},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11864331364631653},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.07914456725120544},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07608065009117126}],"concepts":[{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.8223074674606323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7487959861755371},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.7211567163467407},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6901081204414368},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6840587854385376},{"id":"https://openalex.org/C57733114","wikidata":"https://www.wikidata.org/wiki/Q1006032","display_name":"Discrete Fourier transform (general)","level":5,"score":0.6421859860420227},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5969853401184082},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5649504661560059},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.5316776633262634},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49779582023620605},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.49130406975746155},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4874892234802246},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48145025968551636},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41469258069992065},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3590579628944397},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29034537076950073},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24035051465034485},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20338302850723267},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.1532725691795349},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.13972756266593933},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11864331364631653},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.07914456725120544},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07608065009117126},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3338533.3366575","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3338533.3366575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Multimedia Asia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5912977134","display_name":"Building World Knowledge by Grounding Language and Multimedia","funder_award_id":"19H04166","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1789336918","https://openalex.org/W1922123711","https://openalex.org/W1977993134","https://openalex.org/W2031614119","https://openalex.org/W2061171222","https://openalex.org/W2097117768","https://openalex.org/W2144872957","https://openalex.org/W2163605009","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2335728318","https://openalex.org/W2549139847","https://openalex.org/W2609675817","https://openalex.org/W2896786907","https://openalex.org/W2943827948","https://openalex.org/W2951845198","https://openalex.org/W2963446712","https://openalex.org/W2964166828","https://openalex.org/W2988396473","https://openalex.org/W3217577904"],"related_works":["https://openalex.org/W2150576912","https://openalex.org/W2108727544","https://openalex.org/W2112053570","https://openalex.org/W2086323236","https://openalex.org/W2145506072","https://openalex.org/W2963134360","https://openalex.org/W4229011731","https://openalex.org/W3013474837","https://openalex.org/W2162611351","https://openalex.org/W2053055950"],"abstract_inverted_index":{"Deep":[0],"convolutional":[1],"neural":[2],"networks":[3,154],"(CNNs)":[4],"extract":[5,83],"local":[6],"features":[7,84],"and":[8,44,79,82,88,101,105,121,129,165],"learn":[9],"spatial":[10,16,20,78,87,100,120],"representations":[11,103],"via":[12],"convolutions":[13],"in":[14,31,85,145],"the":[15,19,28,32,133],"domain.":[17],"Beyond":[18],"information,":[21],"some":[22],"works":[23,51],"also":[24],"manage":[25],"to":[26,55,62,76,117],"capture":[27],"spectral":[29,80,102,122],"information":[30,123],"frequency":[33,89],"domain":[34,36],"by":[35],"switching":[37],"methods":[38],"like":[39],"discrete":[40,45],"Fourier":[41],"transform":[42,47],"(DFT)":[43],"cosine":[46],"(DCT).":[48],"However,":[49],"most":[50],"only":[52],"pay":[53],"attention":[54],"a":[56,72,114,146],"single":[57,147],"domain,":[58,148],"which":[59],"is":[60],"prone":[61],"ignoring":[63],"other":[64],"important":[65],"features.":[66],"In":[67],"this":[68],"work,":[69],"we":[70,112],"propose":[71],"novel":[73],"network":[74],"structure":[75],"combine":[77],"convolutions,":[81],"both":[86,119],"domains.":[90],"The":[91],"input":[92],"channels":[93],"are":[94,127],"divided":[95],"into":[96],"two":[97],"groups":[98],"for":[99,108],"respectively,":[104],"then":[106],"integrated":[107],"feature":[109],"fusion.":[110],"Meanwhile,":[111],"design":[113],"channel-shifting":[115],"mechanism":[116],"ensure":[118],"of":[124],"every":[125],"channel":[126],"equally":[128],"adequately":[130],"obtained":[131],"throughout":[132],"deep":[134],"networks.":[135],"Experimental":[136],"results":[137],"demonstrate":[138],"that":[139],"compared":[140],"with":[141,167],"state-of-the-art":[142],"CNN":[143],"models":[144],"our":[149],"shifted":[150],"spatial-spectral":[151],"convolution":[152],"based":[153],"achieve":[155],"better":[156],"performance":[157],"on":[158],"image":[159],"classification":[160],"datasets":[161],"including":[162],"CIFAR10,":[163],"CIFAR100":[164],"SVHN,":[166],"considerably":[168],"fewer":[169],"parameters.":[170]},"counts_by_year":[{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}