{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T08:01:25Z","timestamp":1777104085473,"version":"3.51.4"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T00:00:00Z","timestamp":1675900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T00:00:00Z","timestamp":1675900800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1007\/s11042-023-14537-4","type":"journal-article","created":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T18:43:44Z","timestamp":1675968224000},"page":"21019-21030","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Performance-oriented FPGA-based convolution neural network designs"],"prefix":"10.1007","volume":"82","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3174-9367","authenticated-orcid":false,"given":"Chi-Chou","family":"Kao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,9]]},"reference":[{"key":"14537_CR1","doi-asserted-by":"crossref","unstructured":"Akira J, Fujii T, Sato S, Nakahara H (2018) An FPGA realization of OpenPose based on a sparse weight convolutional neural network. In: 2018 international conference on field- programmable technology (FPT). IEEE, pp 310-313","DOI":"10.1109\/FPT.2018.00061"},{"key":"14537_CR2","doi-asserted-by":"crossref","unstructured":"Aydonat U, O\u2019Connell S, Capalija D, Ling AC, Chiu GR (2017) An OpenCLTM deep learning accelerator on Arria 10. In: 2017 international symposium on field-programmable gate array (FPGA). ACM, pp 55\u201364","DOI":"10.1145\/3020078.3021738"},{"key":"14537_CR3","doi-asserted-by":"crossref","unstructured":"Chakradhar S, Sankaradas M, Jakkula V, Cadambi S (2010) A dynamically configurable coprocessor for convolutional neural networks. In: 2010 37th international symposium oncomputer architecture (ISCA). ACM 247-257","DOI":"10.1145\/1815961.1815993"},{"issue":"1","key":"14537_CR4","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1145\/2654822.2541967","volume":"42","author":"T Chen","year":"2014","unstructured":"Chen T, Du Z, Sun N, Wang J, Wu C, Chn Y (2014) Diannao: a small-footprint high-throughput accelerator for ubiquitous machine-learning. ACM Sigarch Comput Architect News 42(1):269\u2013284. https:\/\/doi.org\/10.1145\/2654822.2541967","journal-title":"ACM Sigarch Comput Architect News"},{"key":"14537_CR5","doi-asserted-by":"crossref","unstructured":"Chen YT, Cong J, Fang Z, Lei J, Wei P (2016) When spark meets FPGAs: a case study for next-generation DNA sequencing acceleration. In: 2016 8th Usenix workshop on hot topic in cloud computing (HotCloud). https:\/\/www.usenix.org\/conference\/hotcloud16\/workshop-program\/presentation\/chen. Accessed 11 June 2022","DOI":"10.1109\/FCCM.2016.18"},{"issue":"1","key":"14537_CR6","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1109\/JSSC.2016.2616357","volume":"52","author":"YH Chen","year":"2017","unstructured":"Chen YH, Krishna T, Emer JS, Sze V (2017) Eyeriss: an energy efficient reconfigurable accelerator for deep convolutional neural networks. IEEE J Solid State Circuits 52(1):127\u2013138. https:\/\/doi.org\/10.1109\/JSSC.2016.2616357","journal-title":"IEEE J Solid State Circuits"},{"key":"14537_CR7","doi-asserted-by":"crossref","unstructured":"Cong J, Xiao B (2014) Minimizing computation in convolutional neural networks. In: 2014 24th international conference on artificial neural networks (ICANN). Springer, pp 281-290","DOI":"10.1007\/978-3-319-11179-7_36"},{"key":"14537_CR8","doi-asserted-by":"crossref","unstructured":"Farabet C, Poulet C, Han JY, LeCun Y (2009) Cnp: an FPGA-based processor for convolutional networks. In: 2009 international conference on field programmable logic and applications (FPL). IEEE, pp 32-37","DOI":"10.1109\/FPL.2009.5272559"},{"key":"14537_CR9","unstructured":"Github repository (2022) https:\/\/github.com\/tensorflow\/tensorflow. Accessed 11 June 2022"},{"key":"14537_CR10","doi-asserted-by":"crossref","unstructured":"Guan Y, Liang H, Xu N, Wang W, Shi S, Chen X, Sun G, Zhang W, Cong J (2017) FP-DNN: an automated framework for mapping deep neural networks onto FPGAs with RTL-HLS hybrid templates. In: IEEE 25th international symposium on field-programmable custom computing machines (FCCM). IEEE, pp 152\u2013159","DOI":"10.1109\/FCCM.2017.25"},{"key":"14537_CR11","unstructured":"Gupta S, Agrawal A, Gopalakrishnan K, Narayanan P (2015) Deep learning with limited numerical precision. In: 2015 international conference on machine learning (ICML). ACM, pp 1737-1746"},{"key":"14537_CR12","unstructured":"Han S, Mao H, Dally WJ (2016) Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding. https:\/\/arxiv.org\/abs\/1510.00149. Accessed 11 June 2022"},{"key":"14537_CR13","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andeetto M, Adam H (2017) MobileNets: efficient convolutional neural networks for Mobile vision applications. arXiv. https:\/\/arxiv.org\/abs\/1704.04861. Accessed 11 June 2022."},{"issue":"1","key":"14537_CR14","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji S, Xu W, Yang M, Yu K (2013) 3D convolutional neural networks for human action recognition. IEEE Trans Pattern Anal Mach Intell 35(1):221\u2013231. https:\/\/doi.org\/10.1109\/TPAMI.2012.59","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"14537_CR15","doi-asserted-by":"crossref","unstructured":"Jouppi N, Young C, Patil N, Patterson D, Agrawal G, et al (2017) In-datacenter performance analysis of a tensor processing unit. In: 2017 44th international symposium on computer architecture (ISCA). ACM, pp 1\u201312","DOI":"10.1145\/3079856.3080246"},{"issue":"6","key":"14537_CR16","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) Image net classification with deep convolutional neural networks. ACM Commun 60(6):84\u201390. https:\/\/doi.org\/10.1145\/3065386","journal-title":"ACM Commun"},{"issue":"11","key":"14537_CR17","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324. https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc IEEE"},{"key":"14537_CR18","unstructured":"Li H, Fan X, Li J, Cao W, Zhou X, Wang L (2016) A High-Performance FPGA-based Accelerator for Large-scale Convolutional Neural Networks. In: 2016 International conference on field programmable logic and applications (FPL). IEEE, pp 1\u20139"},{"key":"14537_CR19","unstructured":"Li H, Fan X, Jiao L, Cao W, Zhou X, Wang L (2016) A high performance FPGA-based accelerator for large-scale convolutional neural networks. In: 2016 international conference on field programmable logic and applications (FPL). IEEE, pp 1-9"},{"issue":"8","key":"14537_CR20","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.1109\/TVLSI.2019.2913958","volume":"27","author":"X Lian","year":"2019","unstructured":"Lian X, Liu Z, Song Z, Dai J, Zhou W, Ji X (2019) High-performance FPGA-based CNN accelerator with block-floating-point arithmetic. IEEE Trans Very Large-Scale Integr (VLSI) Syst 27(8):1874\u20131885. https:\/\/doi.org\/10.1109\/TVLSI.2019.2913958","journal-title":"IEEE Trans Very Large-Scale Integr (VLSI) Syst"},{"key":"14537_CR21","unstructured":"Noronha D, Salehpour B, Wilton SJE (2018) LeFlow: enabling flexible FPGA high-level synthesis of TensorFlow deep neural networks. In: 5th international workshop on FPGA for software programmer (FSP). VDE-Verlag, pp 1\u20138"},{"key":"14537_CR22","unstructured":"Rosenberg C (2013) Improving photo search: a step across the semantic gap. Google AI blog. http:\/\/googleresearch.blogspot.com\/2013\/06\/improving-photo-search-step-across.html. Accessed 11 June 2022"},{"key":"14537_CR23","doi-asserted-by":"crossref","unstructured":"Shen Y, Ferdman M, Milder P (2017) Maximizing CNN accelerator efficiency through resource partitioning. In: 2017 44th international symposium on computer architecture (ISCA). ACM, 535\u2013547","DOI":"10.1145\/3079856.3080221"},{"key":"14537_CR24","unstructured":"Simonyan, K., Zisserman (2015) Very Deep Convolutional Networks for Large-Scale Image Recognition. https:\/\/arxiv.org\/abs\/1409.1556. Accessed 11 June 2022."},{"key":"14537_CR25","doi-asserted-by":"crossref","unstructured":"Suda N, Chandra V, Dasika G, Mohanty A, Ma Y, Vrudhula S, Seo JS, Cao Y (2016) Throughput-optimized OpenCL-based FPGA accelerator for large-scale convolutional neural networks. In: 2016 international symposium on field-programmable gate array (FPGA). ACM, pp 16\u201325","DOI":"10.1145\/2847263.2847276"},{"key":"14537_CR26","doi-asserted-by":"crossref","unstructured":"Umuroglu Y, Fraser N, Gambardella G, Blott M, Leong P, Jahre M, Vissers K (2017) FINN: a framework for fast, scalable Binarized neural network inference. In: 2017 international symposium on field-programmable gate array (FPGA). ACM, pp 65\u201374","DOI":"10.1145\/3020078.3021744"},{"key":"14537_CR27","doi-asserted-by":"crossref","unstructured":"Wei X, Liang Y, Li X, Yu CH, Zhang P, Cong J (2018) \u201cTGPA: Tile-Grained Pipeline Architecture for Low latency CNN Inference,\u201d in 2018 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD), pp. 1\u20138","DOI":"10.1145\/3240765.3240856"},{"key":"14537_CR28","unstructured":"Wikipedia (2022) https:\/\/en.wikipedia.org\/wiki\/TensorFlow. Accessed 11 June 2022"},{"key":"14537_CR29","unstructured":"Xilinx (2012) Large FPGA methodology guide. Xilinx web. https:\/\/www.xilinx.com\/support\/documentation\/sw_manuals\/xilinx13_4\/ug872_largefpga.pdf. Accessed 11 June 2022"},{"key":"14537_CR30","doi-asserted-by":"crossref","unstructured":"Zhang C, Li P, Sun G, Guan Y, Xiao B, Cong J (2015) Optimizing FPGA-based accelerator Design for Deep Convolutional Neural Networks. In: 2015 international symposium on field-programmable gate array (FPGA). ACM, pp 161-170","DOI":"10.1145\/2684746.2689060"},{"key":"14537_CR31","doi-asserted-by":"crossref","unstructured":"Zhang C, Wu D, Sun J, Sun G, Luo G, Cong J (2016) Energy-Efficient CNN Implementation on a Deeply Pipelined FPGA Cluster. In: 2016 International symposium on low power electronics and design (ISLPED). ACM, pp 326\u2013331","DOI":"10.1145\/2934583.2934644"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14537-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-14537-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14537-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,25]],"date-time":"2023-05-25T09:22:48Z","timestamp":1685006568000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-14537-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,9]]},"references-count":31,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["14537"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-14537-4","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,9]]},"assertion":[{"value":"11 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"To the best of our knowledge, the named authors have no conflict of interest, financial or otherwise.Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}