{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T05:12:46Z","timestamp":1699679566719},"reference-count":34,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"21","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Electron. Express"],"published-print":{"date-parts":[[2023,11,10]]},"DOI":"10.1587\/elex.20.20230379","type":"journal-article","created":{"date-parts":[[2023,10,5]],"date-time":"2023-10-05T22:52:28Z","timestamp":1696546348000},"page":"20230379-20230379","source":"Crossref","is-referenced-by-count":0,"title":["Accelerating event-based deep neural networks via flexible data encoding"],"prefix":"10.1587","volume":"20","author":[{"given":"Yuanli","family":"Zhong","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongqi","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bosheng","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yibing","family":"Tang","sequence":"additional","affiliation":[{"name":"Wuhan Digital Engineering Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jigang","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] Y. Zhou, <i>et al.<\/i>: \u201cEvent-based stereo visual odometry,\u201d IEEE Trans. Robot. <b>37<\/b> (2021) 1433 (DOI: 10.1109\/TRO.2021.3062252).","DOI":"10.1109\/TRO.2021.3062252"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] V. Mohan, <i>et al.<\/i>: \u201cEbbinnot: a hardware-efficient hybrid event-frame tracker for stationary dynamic vision sensors,\u201d IEEE Internet Things J. <b>9<\/b> (2022) 20902 (DOI: 10.1109\/JIOT.2022.3178120).","DOI":"10.1109\/JIOT.2022.3178120"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] F. Munir, <i>et al.<\/i>: \u201cLdnet: End-to-end lane marking detection approach using a dynamic vision sensor,\u201d IEEE Trans. Intell. Transp. Syst. <b>23<\/b> (2021) 9318 (DOI: 10.1109\/TITS.2021.3102479).","DOI":"10.1109\/TITS.2021.3102479"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] A. Bisulco, <i>et al.<\/i>: \u201cFast motion understanding with spatiotemporal neural networks and dynamic vision sensors,\u201d IEEE International Conference on Robotics and Automation (2021) 14098 (DOI: 10.1109\/ICRA48506.2021.9561290).","DOI":"10.1109\/ICRA48506.2021.9561290"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] H. Kumawat and S. Mukhopadhyay: \u201cRadar guided dynamic visual attention for resource-efficient rgb object detection,\u201d Proc. Int. Joint Conf. Neural Netw. (2022) 1 (DOI: 10.1109\/IJCNN55064.2022.9892184).","DOI":"10.1109\/IJCNN55064.2022.9892184"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] M. Liu and T. Delbruck: \u201cEDFLOW: Event driven optical flow camera with keypoint detection and adaptive block matching,\u201d IEEE Trans. Circuits Syst. Video Technol. <b>32<\/b> (2022) 5776 (DOI: 10.1109\/TCSVT.2022.3156653).","DOI":"10.1109\/TCSVT.2022.3156653"},{"key":"7","unstructured":"[7] A. Vaswani, <i>et al.<\/i>: \u201cAttention is all you need,\u201d Advances in Neural Information Processing Systems <b>30<\/b> (2017) (DOI: 10.48550\/arXiv.1706.03762)."},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] K. Zhang, <i>et al.<\/i>: \u201cFFDNet: Toward a fast and flexible solution for CNN-based image denoising,\u201d IEEE Trans. Image Process. <b>27<\/b> (2018) 4608 (DOI: 10.1109\/TIP.2018.2839891).","DOI":"10.1109\/TIP.2018.2839891"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] A.S. Lele, <i>et al.<\/i>: \u201cBiomimetic high-speed target localization with fused frame and event vision for edge application,\u201d Frontiers in Neuroscience <b>16<\/b> (2022) (DOI: 10.3389\/fnins.2022.1010302).","DOI":"10.3389\/fnins.2022.1010302"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] J. Kim, <i>et al.<\/i>: \u201cEfficient GPU multitasking with latency minimization and cache boosting,\u201d IEICE Electron. Express <b>14<\/b> (2017) 20161158 (DOI: 10.1587\/elex.14.20161158).","DOI":"10.1587\/elex.14.20161158"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] Y. Wang, <i>et al.<\/i>: \u201cEV-gait: Event-based robust gait recognition using dynamic vision sensors,\u201d IEEE Conf. Comput. Vis. Pattern Recognit. (2019) 6358 (DOI: 10.1109\/CVPR.2019.00652).","DOI":"10.1109\/CVPR.2019.00652"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] H. Deng, <i>et al.<\/i>: \u201cDimension fusion: Dimension-level dynamically composable accelerator for convolutional neural networks,\u201d IEICE Electron. Express <b>18<\/b> (2021) 20210491 (DOI: 10.1587\/elex.18.20210491).","DOI":"10.1587\/elex.18.20210491"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] F. Liu, <i>et al.<\/i>: \u201cCASSANN-v2: A high-performance cnn accelerator architecture with on-chip memory self-adaptive tuning,\u201d IEICE Electron. Express <b>19<\/b> (2022) 20220124 (DOI: 10.1587\/elex.19.20220124).","DOI":"10.1587\/elex.19.20220124"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] M. Arredondo-Vel\u00e1zquez, <i>et al.<\/i>: \u201cA streaming accelerator of convolutional neural networks for resource-limited applications,\u201d IEICE Electron. Express <b>16<\/b> (2019) 20190633 (DOI: 10.1587\/elex.16.20190633).","DOI":"10.1587\/elex.16.20190633"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] Y. Chen, <i>et al.<\/i>: \u201cDaDianNao: A machine-learning supercomputer,\u201d IEEE\/ACM International Symposium on Microarchitecture (2014) 609 (DOI: 10.1109\/MICRO.2014.58).","DOI":"10.1109\/MICRO.2014.58"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] X. Cai, <i>et al.<\/i>: \u201cDeepBurning-SEG: Generating dnn accelerators of segment-grained pipeline architecture,\u201d IEEE\/ACM International Symposium on Microarchitecture (2022) 1396 (DOI: 10.1109\/MICRO56248.2022.00094).","DOI":"10.1109\/MICRO56248.2022.00094"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] W. Sun, <i>et al.<\/i>: \u201cA 112-765GOPS\/W FPGA-based CNN accelerator using importance map guided adaptive activation sparsification for pix2pix applications,\u201d IEEE Asian Solid-State Circuits Conference (2020) 1 (DOI: 10.1109\/A-SSCC48613.2020.9336115).","DOI":"10.1109\/A-SSCC48613.2020.9336115"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] Y. Umuroglu, <i>et al.<\/i>: \u201cLogicNets: Co-designed neural networks and circuits for extreme-throughput applications,\u201d International Conference on Field-Programmable Logic and Applications (2020) 291 (DOI: 10.1109\/FPL50879.2020.00055).","DOI":"10.1109\/FPL50879.2020.00055"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] J. Albericio, <i>et al.<\/i>: \u201cCnvlutin: Ineffectual-neuron-free deep neural network computing,\u201d ACM SIGARCH Comput. Archit. News <b>44<\/b> (2016) 1 (DOI: 10.1145\/3007787.3001138).","DOI":"10.1145\/3007787.3001138"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] N.F.Y. Chen: \u201cPseudo-labels for supervised learning on dynamic vision sensor data, applied to object detection under ego-motion,\u201d IEEE Conference on Computer Vision and Pattern Recognition Workshops (2018) 644 (DOI: 10.1109\/CVPRW.2018.00107).","DOI":"10.1109\/CVPRW.2018.00107"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] M.H. Tayarani-Najaran and M. Schmuker: \u201cEvent-based sensing and signal processing in the visual, auditory, and olfactory domain: a review,\u201d Frontiers in Neural Circuits <b>15<\/b> (2021) 610446 (DOI: 10.3389\/fncir.2021.610446).","DOI":"10.3389\/fncir.2021.610446"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] J. Li, <i>et al.<\/i>: \u201cAsynchronous spatio-temporal memory network for continuous event-based object detection,\u201d IEEE Trans. Image Process. <b>31<\/b> (2022) 2975 (DOI: 10.1109\/TIP.2022.3162962).","DOI":"10.1109\/TIP.2022.3162962"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] Y. Wang, <i>et al.<\/i>: \u201cB-SCT: Improve SpMV processing on SIMD architectures,\u201d IEICE Electron. Express <b>12<\/b> (2015) 20150170 (DOI: 10.1587\/elex.12.20150170).","DOI":"10.1587\/elex.12.20150170"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] L. Pentecost, <i>et al.<\/i>: \u201cMaxNVM: Maximizing DNN storage density and inference efficiency with sparse encoding and error mitigation,\u201d IEEE\/ACM International Symposium on Microarchitecture (2019) 769 (DOI: 10.1145\/3352460.3358258).","DOI":"10.1145\/3352460.3358258"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] T. Chen, <i>et al.<\/i>: \u201cDianNao: A small-footprint high-throughput accelerator for ubiquitous machine-learning,\u201d ACM SIGARCH Comput. Archit. News <b>42<\/b> (2014) 269 (DOI: 10.1145\/2541940.2541967).","DOI":"10.1145\/2654822.2541967"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] S. Han, <i>et al.<\/i>: \u201cEIE: Efficient inference engine on compressed deep neural network,\u201d ACM SIGARCH Comput. Archit. News <b>44<\/b> (2016) 243 (DOI: 10.1145\/3007787.3001163).","DOI":"10.1145\/3007787.3001163"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] H. Rebecq, <i>et al.<\/i>: \u201cHigh speed and high dynamic range video with an event camera,\u201d IEEE Trans. Pattern Anal. Mach. Intell. <b>43<\/b> (2019) 1964 (DOI: 10.1109\/TPAMI.2019.2963386).","DOI":"10.1109\/TPAMI.2019.2963386"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] M. Gehrig, <i>et al.<\/i>: \u201cE-RAFT: Dense optical flow from event cameras,\u201d International Conference on 3D Vision (2021) 197 (DOI: 10.1109\/3DV53792.2021.00030).","DOI":"10.1109\/3DV53792.2021.00030"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] D. Gehrig, <i>et al.<\/i>: \u201cCombining events and frames using recurrent asynchronous multimodal networks for monocular depth prediction,\u201d IEEE Robot. Automat. Lett. <b>6<\/b> (2021) 2822 (DOI: 10.1109\/LRA.2021.3060707).","DOI":"10.1109\/LRA.2021.3060707"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] F. Paredes-Vall\u00e9s and G.C. de Croon: \u201cBack to event basics: Self-supervised learning of image reconstruction for event cameras via photometric constancy,\u201d IEEE Conf. Comput. Vis. Pattern Recognit. (2021) 3446 (DOI: 10.1109\/CVPR46437.2021.00345).","DOI":"10.1109\/CVPR46437.2021.00345"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] N. Muralimanohar, <i>et al.<\/i>: \u201cCacti 6.0: A tool to model large caches,\u201d HP laboratories <b>27<\/b> (2009) 28.","DOI":"10.1109\/MM.2008.2"},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] S. Zhang, <i>et al.<\/i>: \u201cCambricon-X: An accelerator for sparse neural networks,\u201d IEEE\/ACM International Symposium on Microarchitecture (2016) 1 (DOI: 10.1109\/MICRO.2016.7783723).","DOI":"10.1109\/MICRO.2016.7783723"},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] A. Parashar, <i>et al.<\/i>: \u201cSCNN: An accelerator for compressed-sparse convolutional neural networks,\u201d ACM SIGARCH Comput. Archit. News <b>45<\/b> (2017) 27 (DOI: 10.1145\/3140659.3080254).","DOI":"10.1145\/3140659.3080254"},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] A. Gondimalla, <i>et al.<\/i>: \u201cSparTen: A sparse tensor accelerator for convolutional neural networks,\u201d IEEE\/ACM International Symposium on Microarchitecture (2019) 151 (DOI: 10.1145\/3352460.3358291).","DOI":"10.1145\/3352460.3358291"}],"container-title":["IEICE Electronics Express"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/elex\/20\/21\/20_20.20230379\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T03:20:36Z","timestamp":1699672836000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/elex\/20\/21\/20_20.20230379\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,10]]},"references-count":34,"journal-issue":{"issue":"21","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.1587\/elex.20.20230379","relation":{},"ISSN":["1349-2543"],"issn-type":[{"value":"1349-2543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,10]]},"article-number":"20.20230379"}}