{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T09:01:01Z","timestamp":1764061261098,"version":"3.37.3"},"reference-count":36,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T00:00:00Z","timestamp":1727308800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000065","name":"National Institute of Neurological Disorders and Stroke","doi-asserted-by":"publisher","award":["R01NS110421"],"award-info":[{"award-number":["R01NS110421"]}],"id":[{"id":"10.13039\/100000065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1016\/j.neucom.2024.128628","type":"journal-article","created":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T20:26:59Z","timestamp":1726777619000},"page":"128628","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["ShaderNN: A lightweight and efficient inference engine for real-time applications on mobile GPUs"],"prefix":"10.1016","volume":"611","author":[{"given":"Jing","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhong","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhishek","family":"Saxena","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1890-5110","authenticated-orcid":false,"given":"Jiangong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyu","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1298-9381","authenticated-orcid":false,"given":"Rong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7719-1106","authenticated-orcid":false,"given":"Shuvra S.","family":"Bhattacharyya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"doi-asserted-by":"crossref","unstructured":"M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L.-C. Chen, MobileNetV2: Inverted Residuals and Linear Bottlenecks, in: The IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2018.","key":"10.1016\/j.neucom.2024.128628_b1","DOI":"10.1109\/CVPR.2018.00474"},{"year":"2016","author":"Iandola","series-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size","key":"10.1016\/j.neucom.2024.128628_b2"},{"issue":"3","key":"10.1016\/j.neucom.2024.128628_b3","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1109\/JPROC.2022.3153408","article-title":"A survey of deep learning on mobile devices: Applications, optimizations, challenges, and research opportunities","volume":"110","author":"Zhao","year":"2022","journal-title":"Proc. IEEE"},{"year":"2020","series-title":"Fragment shader \u2014 OpenGL wiki","key":"10.1016\/j.neucom.2024.128628_b4"},{"year":"2019","author":"Lee","series-title":"On-device neural net inference with mobile GPUs","key":"10.1016\/j.neucom.2024.128628_b5"},{"year":"2019","author":"Bai","series-title":"ONNX: Open neural network exchange","key":"10.1016\/j.neucom.2024.128628_b6"},{"year":"2019","author":"Paszke","series-title":"PyTorch: An imperative style, high-performance deep learning library","key":"10.1016\/j.neucom.2024.128628_b7"},{"year":"2020","series-title":"PyTorch mobile","key":"10.1016\/j.neucom.2024.128628_b8"},{"year":"2022","series-title":"Metal: Render advanced 3D graphics and compute data in parallel with graphics processors","key":"10.1016\/j.neucom.2024.128628_b9"},{"key":"10.1016\/j.neucom.2024.128628_b10","series-title":"MLSys","article-title":"MNN: A universal and efficient inference engine","author":"Jiang","year":"2020"},{"year":"2022","series-title":"NCNN: a high-performance neural network inference computing framework optimized for mobile platforms","key":"10.1016\/j.neucom.2024.128628_b11"},{"year":"2022","series-title":"TNN: A high-performance, lightweight neural network inference framework","key":"10.1016\/j.neucom.2024.128628_b12"},{"year":"2022","series-title":"Bolt: A light-weight library for deep learning","key":"10.1016\/j.neucom.2024.128628_b13"},{"year":"2022","series-title":"Mobile AI compute engine","key":"10.1016\/j.neucom.2024.128628_b14"},{"year":"2020","series-title":"Anakin","key":"10.1016\/j.neucom.2024.128628_b15"},{"year":"2018","author":"Cronin","series-title":"Deep Neural Network Algorithms on Graphics Processors for Embedded Systems","key":"10.1016\/j.neucom.2024.128628_b16"},{"year":"2022","author":"Lin","series-title":"Efficient heterogeneous video segmentation at the edge","key":"10.1016\/j.neucom.2024.128628_b17"},{"year":"2022","author":"The Khronos Group","series-title":"Vulkan tutorials","key":"10.1016\/j.neucom.2024.128628_b18"},{"year":"2015","author":"Khronos OpenCL Working Group","series-title":"The OpenCL C Specification, Version 2.0","key":"10.1016\/j.neucom.2024.128628_b19"},{"key":"10.1016\/j.neucom.2024.128628_b20","series-title":"Operating Systems Design and Implementation","article-title":"TensorFlow: A system for large-scale machine learning","author":"Abadi","year":"2016"},{"unstructured":"T. Chen, T. Moreau, Z. Jiang, L. Zheng, E. Yan, H. Shen, M. Cowan, L. Wang, Y. Hu, L. Ceze, et al., {TVM}: An automated {End-to-End} optimizing compiler for deep learning, in: 13th USENIX Symposium on Operating Systems Design and Implementation, OSDI 18, 2018, pp. 578\u2013594.","key":"10.1016\/j.neucom.2024.128628_b21"},{"year":"2021","author":"Tornai","series-title":"Compute shader in image processing development","key":"10.1016\/j.neucom.2024.128628_b22"},{"doi-asserted-by":"crossref","unstructured":"W. Shi, J. Caballero, F. Husz\u00e1r, J. Totz, A.P. Aitken, R. Bishop, D. Rueckert, Z. Wang, Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 1874\u20131883.","key":"10.1016\/j.neucom.2024.128628_b23","DOI":"10.1109\/CVPR.2016.207"},{"issue":"7","key":"10.1016\/j.neucom.2024.128628_b24","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1038\/s42256-021-00342-x","article-title":"Segmentation of neurons from fluorescence calcium recordings beyond real time","volume":"3","author":"Bao","year":"2021","journal-title":"Nat. Mach. Intell."},{"year":"2015","author":"He","series-title":"Deep residual learning for image recognition","key":"10.1016\/j.neucom.2024.128628_b25"},{"year":"2018","author":"Redmon","series-title":"YOLOv3: An incremental improvement","key":"10.1016\/j.neucom.2024.128628_b26"},{"year":"2015","author":"Ronneberger","series-title":"U-Net: Convolutional networks for biomedical image segmentation","key":"10.1016\/j.neucom.2024.128628_b27"},{"year":"2016","author":"Molchanov","series-title":"Pruning convolutional neural networks for resource efficient inference","key":"10.1016\/j.neucom.2024.128628_b28"},{"doi-asserted-by":"crossref","unstructured":"R. Rombach, A. Blattmann, D. Lorenz, P. Esser, B. Ommer, High-resolution image synthesis with latent diffusion models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10684\u201310695.","key":"10.1016\/j.neucom.2024.128628_b29","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10.1016\/j.neucom.2024.128628_b30","series-title":"European Conference on Computer Vision","first-page":"694","article-title":"Perceptual losses for real-time style transfer and super-resolution","author":"Johnson","year":"2016"},{"year":"2022","series-title":"ONNX model zoo","key":"10.1016\/j.neucom.2024.128628_b31"},{"year":"2023","series-title":"Qualcommai","key":"10.1016\/j.neucom.2024.128628_b32"},{"year":"2019","author":"Lugaresi","series-title":"Mediapipe: A framework for building perception pipelines","key":"10.1016\/j.neucom.2024.128628_b33"},{"doi-asserted-by":"crossref","unstructured":"W. Niu, J. Guan, Y. Wang, G. Agrawal, B. Ren, DNNFusion: accelerating deep neural networks execution with advanced operator fusion, in: Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation, 2021, pp. 883\u2013898.","key":"10.1016\/j.neucom.2024.128628_b34","DOI":"10.1145\/3453483.3454083"},{"year":"2024","series-title":"XLA: Optimizing compiler for machine learning","key":"10.1016\/j.neucom.2024.128628_b35"},{"doi-asserted-by":"crossref","unstructured":"P. Tillet, H.T. Kung, D. Cox, Triton: an intermediate language and compiler for tiled neural network computations, in: Proceedings of the ACM SIGPLAN International Workshop on Machine Learning and Programming Languages, 2019, pp. 10\u201319.","key":"10.1016\/j.neucom.2024.128628_b36","DOI":"10.1145\/3315508.3329973"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231224013997?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231224013997?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T21:05:32Z","timestamp":1731272732000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231224013997"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":36,"alternative-id":["S0925231224013997"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2024.128628","relation":{},"ISSN":["0925-2312"],"issn-type":[{"type":"print","value":"0925-2312"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ShaderNN: A lightweight and efficient inference engine for real-time applications on mobile GPUs","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2024.128628","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"128628"}}