{"id":"https://openalex.org/W4310608692","doi":"https://doi.org/10.1109/icta56932.2022.9963033","title":"3D-NWA: A Nested-Winograd Accelerator for 3D CNNs","display_name":"3D-NWA: A Nested-Winograd Accelerator for 3D CNNs","publication_year":2022,"publication_date":"2022-10-28","ids":{"openalex":"https://openalex.org/W4310608692","doi":"https://doi.org/10.1109/icta56932.2022.9963033"},"language":"en","primary_location":{"id":"doi:10.1109/icta56932.2022.9963033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icta56932.2022.9963033","pdf_url":null,"source":{"id":"https://openalex.org/S4363608577","display_name":"2022 IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA)","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/A5019014231","display_name":"Huafeng Ye","orcid":null},"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":true,"raw_author_name":"Huafeng Ye","raw_affiliation_strings":["School of Microelectronics Science and Technology, Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics Science and Technology, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077743110","display_name":"Huipeng Deng","orcid":null},"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":"Huipeng Deng","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370396","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0002-0579-3041"},"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":"Jian Wang","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350102","display_name":"Mingyu Wang","orcid":"https://orcid.org/0000-0001-5722-9752"},"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":"Mingyu Wang","raw_affiliation_strings":["School of Microelectronics Science and Technology, Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics Science and Technology, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017560036","display_name":"Zhiyi Yu","orcid":"https://orcid.org/0000-0002-8802-0457"},"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":"Zhiyi Yu","raw_affiliation_strings":["School of Microelectronics Science and Technology, Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics Science and Technology, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5019014231"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.06,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.29773278,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"143","last_page":"144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9988999962806702,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9986000061035156,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9980000257492065,"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":0.79295414686203},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7576905488967896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.72100830078125},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7010413408279419},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6941494345664978},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5215263962745667},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5067442059516907},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.45407119393348694},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44642189145088196},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4273395538330078},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.42595380544662476},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.26291579008102417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24825239181518555},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.24095648527145386},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19630539417266846},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.08144325017929077}],"concepts":[{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.79295414686203},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7576905488967896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72100830078125},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7010413408279419},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6941494345664978},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5215263962745667},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5067442059516907},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.45407119393348694},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44642189145088196},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4273395538330078},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42595380544662476},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.26291579008102417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24825239181518555},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.24095648527145386},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19630539417266846},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.08144325017929077},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icta56932.2022.9963033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icta56932.2022.9963033","pdf_url":null,"source":{"id":"https://openalex.org/S4363608577","display_name":"2022 IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2904795057","https://openalex.org/W2963673357","https://openalex.org/W3018618942","https://openalex.org/W3134700402","https://openalex.org/W3215712654","https://openalex.org/W6757703747"],"related_works":["https://openalex.org/W4225949190","https://openalex.org/W2017990332","https://openalex.org/W2080337923","https://openalex.org/W2964954556","https://openalex.org/W1488776355","https://openalex.org/W2093251826","https://openalex.org/W4221155546","https://openalex.org/W4244262766","https://openalex.org/W3034421924","https://openalex.org/W2982536526"],"abstract_inverted_index":{"3D":[0,16,69],"Convolutional":[1],"neural":[2],"networks":[3],"(3D":[4],"CNNs)":[5],"perform":[6],"better":[7],"in":[8,23,49],"some":[9],"scenarios,":[10],"such":[11],"as":[12],"video":[13],"understanding":[14],"and":[15,26,35,120],"medical":[17],"image":[18],"diagnosis.":[19],"With":[20],"the":[21,24,29,45,75,79,83,87,110,115,130],"increase":[22,38],"dimension":[25],"size":[27],"of":[28,47,112],"convolution":[30,50,54],"kernel,":[31],"CNN's":[32],"computational":[33],"complexity":[34],"implementation":[36],"difficulty":[37],"severely.":[39],"Winograd":[40,71],"transformation":[41],"can":[42],"significantly":[43],"reduce":[44],"number":[46],"multiplications":[48,88],"operations.":[51],"However,":[52],"large":[53],"filters":[55],"will":[56],"bring":[57],"numerical":[58],"instability.":[59],"In":[60],"this":[61],"article,":[62],"we":[63,108],"presented":[64],"a":[65],"novel":[66],"method":[67],"called":[68],"nested":[70],"algorithm":[72,85],"to":[73,91,100,126],"address":[74],"problem.":[76],"Compared":[77],"with":[78,129],"state-of-art":[80,131],"OLA-Winograd":[81],"algorithm,":[82],"proposed":[84],"reduces":[86],"by":[89],"1.72":[90],"5.83\u00d7":[92],"for":[93],"computing":[94],"5":[95,97,99],"\u00d7":[96,98,102,104],"9":[101,103,105],"convolutions.":[106],"Finally,":[107],"demonstrate":[109],"efficiency":[111,124],"3D-NWA":[113],"on":[114],"FPGA":[116],"platform":[117],"(Xilinx":[118],"VCU118)":[119],"achieve":[121],"highest":[122],"DSP":[123],"up":[125],"4.67\u00d7":[127],"compared":[128],"accelerators.":[132]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}