{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T12:42:20Z","timestamp":1774010540544,"version":"3.50.1"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002553","name":"Seoul National University of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002553","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.neucom.2026.132958","type":"journal-article","created":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T07:39:46Z","timestamp":1770449986000},"page":"132958","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["SPEED: Structured kernel block pruning with filter groups for efficient and elastic SW-HW co-design in FPGA-based CNN accelerators"],"prefix":"10.1016","volume":"675","author":[{"given":"Kwanghyun","family":"Koo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1471-0228","authenticated-orcid":false,"given":"Sunwoong","family":"Kim","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7962-657X","authenticated-orcid":false,"given":"Hyun","family":"Kim","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.132958_bib0005","series-title":"2022 23rd International Symposium on Quality Electronic Design (ISQED)","first-page":"1","article-title":"A high-speed CNN hardware accelerator with regular pruning","author":"Song","year":"2022"},{"key":"10.1016\/j.neucom.2026.132958_bib0010","doi-asserted-by":"crossref","first-page":"159611","DOI":"10.1109\/ACCESS.2024.3488093","article-title":"Hlq: hardware-friendly logarithmic quantization aware training for power-efficient low-precision CNN models","volume":"12","author":"Choi","year":"2024","journal-title":"IEEE Access"},{"issue":"11","key":"10.1016\/j.neucom.2026.132958_bib0015","first-page":"4668","article-title":"Mobile-x: dedicated FPGA implementation of the mobilenet accelerator optimizing depthwise separable convolution","volume":"71","author":"Hong","year":"2024","journal-title":"IEEE Trans. Circuits Syst. II Express Briefs"},{"issue":"10","key":"10.1016\/j.neucom.2026.132958_bib0020","first-page":"3882","article-title":"Dedicated FPGA implementation of the Gaussian tinyyolov3 accelerator","volume":"70","author":"Ki","year":"2023","journal-title":"IEEE Trans. Circuits Syst. II Express Briefs"},{"key":"10.1016\/j.neucom.2026.132958_bib0025","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12124","article-title":"Cswin transformer: a general vision transformer backbone with cross-shaped windows","author":"Dong","year":"2022"},{"key":"10.1016\/j.neucom.2026.132958_bib0030","series-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24","first-page":"4291","article-title":"Hyq: hardware-friendly post-training quantization for cnn-transformer hybrid networks","author":"Kim","year":"2024"},{"issue":"5","key":"10.1016\/j.neucom.2026.132958_bib0035","doi-asserted-by":"crossref","first-page":"2280","DOI":"10.1109\/TCSI.2024.3369230","article-title":"Ace-cnn: approximate carry disregard multipliers for energy-efficient cnn-based image classification","volume":"71","author":"Shakibhamedan","year":"2024","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"issue":"2","key":"10.1016\/j.neucom.2026.132958_bib0040","first-page":"816","article-title":"A high-throughput and flexible CNN accelerator based on mixed-radix FFT method","volume":"72","author":"Meng","year":"2025","journal-title":"IEEE Trans. Circuits Syst. I: Regul. Pap."},{"issue":"3","key":"10.1016\/j.neucom.2026.132958_bib0045","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1007\/s11554-024-01442-8","article-title":"Survey of convolutional neural network accelerators on field-programmable gate array platforms: architectures and optimization techniques","volume":"21","author":"Hong","year":"2024","journal-title":"J. Real-Time Image Process."},{"key":"10.1016\/j.neucom.2026.132958_bib0050","doi-asserted-by":"crossref","first-page":"5588","DOI":"10.1109\/TMM.2023.3338052","article-title":"Trunk pruning: highly compatible channel pruning for convolutional neural networks without fine-tuning","volume":"26","author":"Kim","year":"2024","journal-title":"IEEE Trans. Multimedia"},{"issue":"1","key":"10.1016\/j.neucom.2026.132958_bib0055","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1109\/TCSI.2020.3030663","article-title":"High performance CNN accelerators based on hardware and algorithm co-optimization","volume":"68","author":"Yuan","year":"2021","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"10.1016\/j.neucom.2026.132958_bib0060","author":"Choi"},{"key":"10.1016\/j.neucom.2026.132958_bib0065","author":"Esser"},{"key":"10.1016\/j.neucom.2026.132958_bib0070","author":"Peccia"},{"key":"10.1016\/j.neucom.2026.132958_bib0075","article-title":"Learning both weights and connections for efficient neural network","volume":"28","author":"Han","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.132958_bib0080","series-title":"Proceedings of the 59th ACM\/IEEE Design Automation Conference","first-page":"145","article-title":"Accelerating and pruning CNNS for semantic segmentation on FPGA","author":"Mor\u00ec","year":"2022"},{"key":"10.1016\/j.neucom.2026.132958_bib0085","series-title":"2020 25th International Conference on Pattern Recognition (ICPR)","first-page":"255","article-title":"HFP: hardware-aware filter pruning for deep convolutional neural networks acceleration","author":"Yu","year":"2021"},{"key":"10.1016\/j.neucom.2026.132958_bib0090","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neucom.2026.132958_bib0095","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4943","article-title":"Centripetal SGD for pruning very deep convolutional networks with complicated structure","author":"Ding","year":"2019"},{"key":"10.1016\/j.neucom.2026.132958_bib0100","doi-asserted-by":"crossref","first-page":"217033","DOI":"10.1109\/ACCESS.2020.3041464","article-title":"An energy-efficient implementation of group pruned CNNS on FPGA","volume":"8","author":"Pang","year":"2020","journal-title":"Ieee Access"},{"key":"10.1016\/j.neucom.2026.132958_bib0105","series-title":"Revisit Kernel Pruning with Lottery Regulated Grouped Convolutions","author":"Zhong","year":"2022"},{"key":"10.1016\/j.neucom.2026.132958_bib0110","doi-asserted-by":"crossref","first-page":"118547","DOI":"10.1109\/ACCESS.2023.3326534","article-title":"V-skp: vectorized kernel-based structured kernel pruning for accelerating deep convolutional neural networks","volume":"11","author":"Koo","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.neucom.2026.132958_bib0115","series-title":"2024 ACM\/IEEE 51st Annual International Symposium on Computer Architecture (ISCA)","first-page":"890","article-title":"Tcp: a tensor contraction processor for AI workloads industrial product*","author":"Kim","year":"2024"},{"key":"10.1016\/j.neucom.2026.132958_bib0120","series-title":"2017 IEEE International Symposium on High Performance Computer Architecture (HPCA)","first-page":"553","article-title":"Flexflow: a flexible dataflow accelerator architecture for convolutional neural networks","author":"Lu","year":"2017"},{"key":"10.1016\/j.neucom.2026.132958_bib0125","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9157","article-title":"Yolact: real-time instance segmentation","author":"Bolya","year":"2019"},{"issue":"1","key":"10.1016\/j.neucom.2026.132958_bib0130","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","article-title":"The PASCAL visual object classes challenge: a retrospective","volume":"111","author":"Everingham","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.132958_bib0135","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.132958_bib0140","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1492","article-title":"Aggregated residual transformations for deep neural networks","author":"Xie","year":"2017"},{"key":"10.1016\/j.neucom.2026.132958_bib0145","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4510","article-title":"Mobilenetv2: inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"key":"10.1016\/j.neucom.2026.132958_bib0150","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1016\/j.neucom.2021.10.009","article-title":"Progressive kernel pruning with saliency mapping of input-output channels","volume":"467","author":"Zhu","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.132958_bib0155","author":"Frankle"},{"key":"10.1016\/j.neucom.2026.132958_bib0160","series-title":"IJCAI","first-page":"8","article-title":"Accelerating convolutional networks via global & dynamic filter pruning","volume":"vol. 2","author":"Lin","year":"2018"},{"key":"10.1016\/j.neucom.2026.132958_bib0165","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"1389","article-title":"Channel pruning for accelerating very deep neural networks","author":"He","year":"2017"},{"key":"10.1016\/j.neucom.2026.132958_bib0170","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neucom.2026.132958_bib0175","author":"Lin"},{"issue":"6","key":"10.1016\/j.neucom.2026.132958_bib0180","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1080\/03772063.2020.1821797","article-title":"Efficient CNN accelerator on FPGA","volume":"66","author":"Kala","year":"2020","journal-title":"IETE J. Res."},{"issue":"4","key":"10.1016\/j.neucom.2026.132958_bib0185","doi-asserted-by":"crossref","first-page":"1634","DOI":"10.1109\/TCSI.2024.3483308","article-title":"Eyelet: a cross-mesh noc-based fine-grained sparse CNN accelerator for spatio-temporal parallel computing optimization","volume":"72","author":"Yao","year":"2024","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"10.1016\/j.neucom.2026.132958_bib0190","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4340","article-title":"Filter pruning via geometric median for deep convolutional neural networks acceleration","author":"He","year":"2019"},{"key":"10.1016\/j.neucom.2026.132958_bib0195","series-title":"International Conference on Neural Information Processing","first-page":"88","article-title":"Filter pruning via similarity clustering for deep convolutional neural networks","author":"Song","year":"2022"},{"key":"10.1016\/j.neucom.2026.132958_bib0200","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2024.121418","article-title":"Sfp: similarity-based filter pruning for deep neural networks","volume":"689","author":"Li","year":"2025","journal-title":"Inf. Sci."},{"issue":"1","key":"10.1016\/j.neucom.2026.132958_bib0205","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1007\/s10489-023-05207-x","article-title":"Automatic filter pruning algorithm for image classification","volume":"54","author":"Xue","year":"2024","journal-title":"Appl. Intell."},{"key":"10.1016\/j.neucom.2026.132958_bib0210","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1529","article-title":"Hrank: filter pruning using high-rank feature map","author":"Lin","year":"2020"},{"key":"10.1016\/j.neucom.2026.132958_bib0215","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6438","article-title":"Towards compact CNNS via collaborative compression","author":"Li","year":"2021"},{"key":"10.1016\/j.neucom.2026.132958_bib0220","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16091","article-title":"Depgraph: towards any structural pruning","author":"Fang","year":"2023"},{"key":"10.1016\/j.neucom.2026.132958_bib0225","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.127124","article-title":"A novel and efficient model pruning method for deep convolutional neural networks by evaluating the direct and indirect effects of filters","volume":"569","author":"Zheng","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.132958_bib0230","series-title":"2020 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)","first-page":"73","article-title":"Prune it yourself: automated pruning by multiple level sensitivity","author":"Yan","year":"2020"},{"key":"10.1016\/j.neucom.2026.132958_bib0235","series-title":"2020 International Conference on Omni-Layer Intelligent Systems (COINS)","first-page":"1","article-title":"Chapr: efficient inference of CNNS via channel pruning","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neucom.2026.132958_bib0240","series-title":"2022 23rd International Symposium on Quality Electronic Design (ISQED)","first-page":"1","article-title":"A high-speed CNN hardware accelerator with regular pruning","author":"Song","year":"2022"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226003553?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226003553?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T10:38:51Z","timestamp":1774003131000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226003553"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":48,"alternative-id":["S0925231226003553"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.132958","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SPEED: Structured kernel block pruning with filter groups for efficient and elastic SW-HW co-design in FPGA-based CNN accelerators","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.132958","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132958"}}