{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:16:25Z","timestamp":1766268985762,"version":"3.37.3"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972396"],"award-info":[{"award-number":["61972396"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0103402"],"award-info":[{"award-number":["2020AAA0103402"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Strategic Priority Research Program of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XDA27040300"],"award-info":[{"award-number":["XDA27040300"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1109\/tnnls.2021.3095276","type":"journal-article","created":{"date-parts":[[2021,8,10]],"date-time":"2021-08-10T23:11:46Z","timestamp":1628637106000},"page":"433-445","source":"Crossref","is-referenced-by-count":8,"title":["ECBC: Efficient Convolution via Blocked Columnizing"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4231-7607","authenticated-orcid":false,"given":"Tianli","family":"Zhao","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences, Institute of Automation, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinghao","family":"Hu","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"He","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Institute of Automation, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3083-794X","authenticated-orcid":false,"given":"Weixiang","family":"Xu","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxing","family":"Wang","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Leng","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1289-2758","authenticated-orcid":false,"given":"Jian","family":"Cheng","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Institute of Automation, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref2","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR)","author":"Simonyan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref5","article-title":"YOLOv3: An incremental improvement","volume-title":"arXiv:1804.02767","author":"Redmon","year":"2018"},{"key":"ref6","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"1","author":"Ren"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5244\/c.29.160"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref11","first-page":"1","article-title":"High performance convolutional neural networks for document processing","volume-title":"Proc. 10th Int. Workshop Frontiers Handwriting Recognit.","author":"Chellapilla"},{"key":"ref12","first-page":"815","article-title":"MEC: Memory-efficient convolution for deep neural network","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","author":"Cho"},{"key":"ref13","first-page":"5776","article-title":"High performance zero-memory overhead direct convolutions","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Zhang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00069"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00032"},{"key":"ref16","first-page":"1025","article-title":"Optimizing CNN model inference on CPUs","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Liu"},{"key":"ref17","first-page":"1","article-title":"The indirect convolution algorithm","volume":"arXiv:1907.02129","author":"Dukhan","year":"2019","journal-title":"CoRR"},{"key":"ref18","first-page":"1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Han"},{"key":"ref19","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00161"},{"key":"ref21","first-page":"1","article-title":"Slimmable neural networks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Yu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00189"},{"key":"ref23","first-page":"1","article-title":"Searching for low-bit weights in quantized neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Yang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.422"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11713"},{"key":"ref28","first-page":"1269","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","volume-title":"Proc. 38th Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Denton"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.88"},{"key":"ref30","first-page":"1","article-title":"Speeding up convolutional neural networks using fine-tuned CP-decomposition","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR)","author":"Lebedev"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970364"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178496"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/DAC.2018.8465825"},{"key":"ref34","first-page":"1","article-title":"Towards optimal Winograd convolution on manycores","volume-title":"Proc. SysML","author":"Jia"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/77626.79170"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2012.97"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503219"},{"volume-title":"MKL: Intel Math Kernel Library","year":"2020","key":"ref39"},{"volume-title":"Eigen V3","year":"2010","author":"Guennebaud","key":"ref40"},{"key":"ref41","first-page":"2515","article-title":"Memory-optimal direct convolutions for maximizing classification accuracy in embedded applications","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Gural"},{"key":"ref42","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 12th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Chen"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"},{"key":"ref44","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Zheng"},{"key":"ref45","first-page":"1","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","volume-title":"Proc. Neural Inf. Process. Syst. Workshop Mach. Learn. Syst.","author":"Chen"},{"key":"ref46","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Abadi"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.110"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2535371"},{"volume-title":"NNPACK","year":"2020","author":"Dukhan","key":"ref50"},{"volume-title":"TFLITE","year":"2020","key":"ref51"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10007736\/09490341.pdf?arnumber=9490341","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T22:53:57Z","timestamp":1705013637000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9490341\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":53,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3095276","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2023,1]]}}}