{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T15:46:51Z","timestamp":1775749611020,"version":"3.50.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T00:00:00Z","timestamp":1775692800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T00:00:00Z","timestamp":1775692800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100005405","name":"Ritsumeikan University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005405","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-026-08450-4","type":"journal-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:52:17Z","timestamp":1775746337000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An embedded vision transformer with quantization-friendly simple attention, optimized buffers, and SIMD acceleration"],"prefix":"10.1007","volume":"82","author":[{"given":"Hayata","family":"Kaneko","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,9]]},"reference":[{"key":"8450_CR1","doi-asserted-by":"crossref","unstructured":"Ahn H, Chen T, Alnaasan N, Shafi A, Abduljabbar M, Subramoni H et al (2023) Performance characterization of using quantization for DNN inference on edge devices: extended version. arXiv:2303.05016","DOI":"10.1109\/ICFEC57925.2023.00009"},{"key":"8450_CR2","doi-asserted-by":"crossref","unstructured":"Lin Y, Zhang T, Sun P, Li Z, Zhou S (2021) Fq-vit: post-training quantization for fully quantized vision transformer. arXiv:2111.13824","DOI":"10.24963\/ijcai.2022\/164"},{"key":"8450_CR3","doi-asserted-by":"crossref","unstructured":"Li Z, Gu Q (2023) I-vit: Integer-only quantization for efficient vision transformer inference. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17065\u201317075","DOI":"10.1109\/ICCV51070.2023.01565"},{"key":"8450_CR4","doi-asserted-by":"publisher","first-page":"1592","DOI":"10.1109\/TMM.2023.3265159","volume":"25","author":"J Mao","year":"2023","unstructured":"Mao J, Yao Y, Sun Z, Huang X, Shen F, Shen HT (2023) Attention map guided transformer pruning for occluded person re-identification on edge device. IEEE Trans Multim 25:1592\u20131599","journal-title":"IEEE Trans Multim"},{"key":"8450_CR5","doi-asserted-by":"crossref","unstructured":"Koohpayegani SA, Pirsiavash H (2024) Sima: Simple softmax-free attention for vision transformers. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2607\u20132617","DOI":"10.1109\/WACV57701.2024.00259"},{"key":"8450_CR6","doi-asserted-by":"crossref","unstructured":"Flamand E, Rossi D, Conti F, Loi I, Pullini A, Rotenberg F, Benini L (2018) Gap-8: A risc-v soc for ai at the edge of the iot. In: 2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP). IEEE, pp. 1\u20134","DOI":"10.1109\/ASAP.2018.8445101"},{"key":"8450_CR7","doi-asserted-by":"crossref","unstructured":"M\u00fcller H, Kartsch V, Benini L (2024) Gap9shield: a 150gops AI-capable ultra-low power module for vision and ranging applications on nano-drones. In: European Robotics Forum. Springer, pp. 292\u2013297","DOI":"10.1007\/978-3-031-76424-0_52"},{"issue":"7","key":"8450_CR8","doi-asserted-by":"publisher","first-page":"2055","DOI":"10.1109\/JSSC.2024.3385987","volume":"59","author":"AS Prasad","year":"2024","unstructured":"Prasad AS, Scherer M, Conti F, Rossi D, Di Mauro A, Eggimann M, G\u00f3mez JT, Li Z, Sarwar SS, Wang Z et al (2024) Siracusa: a 16 nm heterogenous risc-v soc for extended reality with at-mram neural engine. IEEE J Solid-State Circuits 59(7):2055\u20132069","journal-title":"IEEE J Solid-State Circuits"},{"issue":"20","key":"8450_CR9","doi-asserted-by":"publisher","first-page":"33269","DOI":"10.1109\/JIOT.2024.3431913","volume":"11","author":"L Lamberti","year":"2024","unstructured":"Lamberti L, Bellone L, Macan L, Natalizio E, Conti F, Palossi D, Benini L (2024) Distilling tiny and ultra-fast deep neural networks for autonomous navigation on nano-uavs. IEEE Internet Things J 11(20):33269\u201333281","journal-title":"IEEE Internet Things J"},{"issue":"10","key":"8450_CR10","doi-asserted-by":"publisher","first-page":"2700","DOI":"10.1109\/TVLSI.2017.2654506","volume":"25","author":"M Gautschi","year":"2017","unstructured":"Gautschi M, Schiavone PD, Traber A, Loi I, Pullini A, Rossi D, Flamand E, G\u00fcrkaynak FK, Benini L (2017) Near-threshold risc-v core with DSP extensions for scalable IoT endpoint devices. IEEE Trans Very Large Scale Integr VLSI Syst 25(10):2700\u20132713","journal-title":"IEEE Trans Very Large Scale Integr VLSI Syst"},{"key":"8450_CR11","doi-asserted-by":"publisher","first-page":"115647","DOI":"10.1016\/j.oceaneng.2023.115647","volume":"286","author":"H Rajani","year":"2023","unstructured":"Rajani H, Gracias N, Garcia R (2023) A convolutional vision transformer for semantic segmentation of side-scan sonar data. Ocean Eng 286:115647","journal-title":"Ocean Eng"},{"key":"8450_CR12","doi-asserted-by":"crossref","unstructured":"Guo J, Han K, Wu H, Tang Y, Chen X, Wang Y, Xu C (2022) Cmt: cnvolutional neural networks meet vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12175\u201312185","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"8450_CR13","unstructured":"Touvron H, Cord M, Douze M, Massa F, Sablayrolles A, J\u00e9gou H (2021) Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning. PMLR, pp. 10347\u201310357"},{"key":"8450_CR14","unstructured":"Mehta S, Rastegari M (2021) Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv:2110.02178"},{"key":"8450_CR15","doi-asserted-by":"crossref","unstructured":"Kulkarni U, Hosamani AS, Masur AS, Hegde S, Vernekar GR, Chandana KS (2022) A survey on quantization methods for optimization of deep neural networks. In: 2022 international conference on automation, computing and renewable systems (ICACRS). IEEE, pp. 827\u2013834","DOI":"10.1109\/ICACRS55517.2022.10028742"},{"key":"8450_CR16","doi-asserted-by":"crossref","unstructured":"Oh S, Kwon Y, Lee J (2025) Work-in-progress: I-flashattention: fully integer fused attention for efficient vision transformers. In: 2025 International Conference on Compilers, Architecture, and Synthesis for Embedded Systems (CASES)","DOI":"10.1145\/3742872.3757072"},{"key":"8450_CR17","unstructured":"Nagel M, Fournarakis M, Amjad RA, Bondarenko Y, Van\u00a0Baalen M, Blankevoort T (2021) A white paper on neural network quantization. arXiv:2106.08295"},{"key":"8450_CR18","doi-asserted-by":"publisher","first-page":"16344","DOI":"10.52202\/068431-1189","volume":"35","author":"T Dao","year":"2022","unstructured":"Dao T, Fu D, Ermon S, Rudra A, R\u00e9 C (2022) Flashattention: fast and memory-efficient exact attention with io-awareness. Adv Neural Inf Process Syst 35:16344\u201316359","journal-title":"Adv Neural Inf Process Syst"},{"key":"8450_CR19","doi-asserted-by":"crossref","unstructured":"Kaneko H, Meng L (2024) Analysis towards deployment and acceleration for vit on a lightweight risc-v processor. In: 2024 6th International Conference on Industrial Artificial Intelligence (IAI). IEEE, pp. 1\u20136","DOI":"10.1109\/IAI63275.2024.10730301"},{"key":"8450_CR20","doi-asserted-by":"crossref","unstructured":"Jacob B, Kligys S, Chen B, Zhu M, Tang M, Howard A, Adam H, Kalenichenko D (2018) Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2704\u20132713","DOI":"10.1109\/CVPR.2018.00286"},{"key":"8450_CR21","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.aiopen.2022.10.001","volume":"3","author":"T Lin","year":"2022","unstructured":"Lin T, Wang Y, Liu X, Qiu X (2022) A survey of transformers. AI Open 3:111\u2013132","journal-title":"AI Open"},{"issue":"1","key":"8450_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3771939","volume":"25","author":"H Kaneko","year":"2026","unstructured":"Kaneko H, Ishibashi R, Meng L (2026) Simd-cp: Simd with redundant bits compression and mixed-precision packing for quantized DNNs. ACM Trans Embedd Comput Syst 25(1):1\u201320","journal-title":"ACM Trans Embedd Comput Syst"},{"key":"8450_CR23","unstructured":"Or A, Jain A, Vega-Myhre D, Cai J, Hernandez CD, Zheng Z, Guessous D, Kuznetsov V, Puhrsch C, Saroufim M et\u00a0al (2025)Torchao: pytorch-native training-to-serving model optimization. arXiv:2507.16099"},{"key":"8450_CR24","unstructured":"Lai L, Suda N, Chandra V (2018) Cmsis-nn: efficient neural network kernels for arm cortex-m cpus. arXiv:1801.06601"},{"key":"8450_CR25","unstructured":"Openhw group cv32e40p user manual. https:\/\/docs.openhwgroup.org\/projects\/cv32e40p-user-manual\/en\/cv32e40p_v1.8.3\/. Accessed: 2025-011-27"},{"key":"8450_CR26","unstructured":"Obstacle detection. https:\/\/www.kaggle.com\/datasets\/vrushankanand\/obstacle-detection. Accessed: 2025-011-27"},{"key":"8450_CR27","unstructured":"Hand gesture recognition database. https:\/\/www.kaggle.com\/datasets\/gti-upm\/leapgestrecog. Accessed: 2025-011-27"},{"key":"8450_CR28","doi-asserted-by":"crossref","unstructured":"Zhang Y, Su Z, Meng L (2025) Hand gesture recognition for real-time nano drone control on risc-v. In: 2025 IEEE International Conference on Real-time Computing and Robotics (RCAR). IEEE, pp. 95\u2013100","DOI":"10.1109\/RCAR65431.2025.11139603"},{"key":"8450_CR29","unstructured":"Banbury C, Reddi VJ, Torelli P, Holleman J, Jeffries N, Kiraly C, Montino P, Kanter D, Ahmed S, Pau D et al (2021) Mlperf tiny benchmark. arXiv:2106.07597"},{"key":"8450_CR30","unstructured":"Chowdhery A, Warden P, Shlens J, Howard A, Rhodes R (2019) Visual wake words dataset. arXiv:1906.05721"},{"key":"8450_CR31","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: common objects in context. In: European Conference on Computer Vision. Springer, pp. 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"8450_CR32","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861"},{"key":"8450_CR33","doi-asserted-by":"crossref","unstructured":"Zhang H, Duan J, Xue M, Song J, Sun L, Song M (2022) ootstrapping vits: towards liberating vision transformers from pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8944\u20138953","DOI":"10.1109\/CVPR52688.2022.00874"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-026-08450-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-026-08450-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-026-08450-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:52:26Z","timestamp":1775746346000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-026-08450-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,9]]},"references-count":33,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["8450"],"URL":"https:\/\/doi.org\/10.1007\/s11227-026-08450-4","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,9]]},"assertion":[{"value":"11 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"337"}}