{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:20:45Z","timestamp":1757622045227,"version":"3.44.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1109\/socc46988.2019.1570558495","type":"proceedings-article","created":{"date-parts":[[2020,5,7]],"date-time":"2020-05-07T21:27:28Z","timestamp":1588886848000},"page":"50-55","source":"Crossref","is-referenced-by-count":3,"title":["An Operation-Minimized FPGA Accelerator Design by Dynamically Exploiting Sparsity in CNN Winograd Transform"],"prefix":"10.1109","author":[{"given":"Xinkai","family":"Di","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China,100049"}]},{"given":"Haigang","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China,100049"}]},{"given":"Zhihong","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China,100049"}]},{"given":"Ning","family":"Mao","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China,100049"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2705069"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.25"},{"key":"ref31","first-page":"6517","article-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)-YOLO9000: Better, Faster","author":"redmon","year":"2017","journal-title":"Stronger[J]"},{"year":"2019","key":"ref30"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847276"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2966986.2967011"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref11","article-title":"maxDNN: An Efficient Convolution Kernel for Deep Learning with Maxwell GPUs[J]","author":"lavin","year":"2015","journal-title":"Computer Science"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2016.7418007"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"journal-title":"2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO) IEEE Computer Society","article-title":"From high-level deep neural models to FPGAs [C]","year":"2016","key":"ref15"},{"key":"ref16","article-title":"Frequency Domain Acceleration of Convolutional","author":"zhang","year":"2017","journal-title":"Neural Networks on CPU-FPGA Shared Memory System in FPGA"},{"key":"ref17","article-title":"Fast algorithms for convolutional neural networks","author":"lavin","year":"2015","journal-title":"arXiv preprint arXiv 1509 09308"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.64"},{"key":"ref19","first-page":"55","author":"aydonat","year":"2017","journal-title":"An Open CLTM Deep Learning Accelerator on Arria 10[J]"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2554688.2554785"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2015.30"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref6","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks[C]","author":"krizhevsky","year":"2012","journal-title":"International Conference on Neural Information Processing Systems Curran Associates Inc"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2014.23"},{"key":"ref5","article-title":"Towards end-to-end speech recognition with deep convolutional neural networks","author":"zhang","year":"2017","journal-title":"arXiv preprint arXiv 1701"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref7","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition[J]","author":"simonyan","year":"2014","journal-title":"Computer Science"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"journal-title":"You only look once Unified real-time object detection","year":"2015","author":"redmon","key":"ref9"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"journal-title":"Enabling Sparse Winograd Convolution by Native Pruning","year":"2017","author":"li","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"journal-title":"Efficient sparse-winograd convolutional neural networks","year":"2018","author":"liu","key":"ref21"},{"key":"ref24","article-title":"Sparse Winograd Convolutional neural networks on small-scale systolic arrays","author":"shi","year":"2018","journal-title":"arXiv preprint arXiv 1810 06008"},{"key":"ref23","first-page":"1","article-title":"2018 55th ACM\/ESDA\/IEEE Design Automation Conference (DAC) SpWA","author":"lu","year":"2018","journal-title":"An Efficient Sparse Winograd Convolutional Neural Networks Accelerator on FPGAs [C]"},{"key":"ref26","first-page":"3","article-title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding[J]","volume":"56","author":"han","year":"2015","journal-title":"FIBER"},{"key":"ref25","article-title":"Faster CNNs with Direct Sparse Convolutions and Guided Pruning","author":"park","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"}],"event":{"name":"2019 32nd IEEE International System-on-Chip Conference (SOCC)","start":{"date-parts":[[2019,9,3]]},"location":"Singapore","end":{"date-parts":[[2019,9,6]]}},"container-title":["2019 32nd IEEE International System-on-Chip Conference (SOCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9083732\/9087941\/09088036.pdf?arnumber=9088036","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T17:40:43Z","timestamp":1757353243000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9088036\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/socc46988.2019.1570558495","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}