{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T08:37:00Z","timestamp":1777106220559,"version":"3.51.4"},"reference-count":24,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T00:00:00Z","timestamp":1621814400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Commun. ACM"],"published-print":{"date-parts":[[2021,6]]},"abstract":"<jats:p>A new framework allows intelligence on mainstream end devices without special hardware.<\/jats:p>","DOI":"10.1145\/3418297","type":"journal-article","created":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T17:58:51Z","timestamp":1621879131000},"page":"62-68","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["CoCoPIE"],"prefix":"10.1145","volume":"64","author":[{"given":"Hui","family":"Guan","sequence":"first","affiliation":[{"name":"University of Massachusetts at Amherst, MA"}]},{"given":"Shaoshan","family":"Liu","sequence":"additional","affiliation":[{"name":"Perceptin Inc. Mountain View, CA"}]},{"given":"Xiaolong","family":"Ma","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA"}]},{"given":"Wei","family":"Niu","sequence":"additional","affiliation":[{"name":"College of William &amp; Mary, Williamsburg, VA"}]},{"given":"Bin","family":"Ren","sequence":"additional","affiliation":[{"name":"College of William &amp; Mary, Williamsburg, VA"}]},{"given":"Xipeng","family":"Shen","sequence":"additional","affiliation":[{"name":"North Carolina State University, Raleigh, NC"}]},{"given":"Yanzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}]},{"given":"Pu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA"}]}],"member":"320","published-online":{"date-parts":[[2021,5,24]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Alibaba. 2019.  Alibaba. 2019."},{"key":"e_1_2_1_2_1","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation","author":"Chen T.","year":"2018","unstructured":"Chen , T. et al. TVM: An automated end-toend optimizing compiler for deep learning . In 13th USENIX Symposium on Operating Systems Design and Implementation , 2018 , 578--594. Chen, T. et al. TVM: An automated end-toend optimizing compiler for deep learning. In 13th USENIX Symposium on Operating Systems Design and Implementation, 2018, 578--594."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2016.7418007"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_13"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_2_1_6_1","volume-title":"Tensorflow lite","author":"Google","year":"2019","unstructured":"Google . Tensorflow lite , 2019 . Google. Tensorflow lite, 2019."},{"key":"e_1_2_1_7_1","volume-title":"Google cloud TPU","author":"Google Cloud TPU","year":"2017","unstructured":"Google Cloud TPU . Google cloud TPU , 2017 ; https:\/\/cloud.google.com\/tpu\/ Google Cloud TPU. Google cloud TPU, 2017; https:\/\/cloud.google.com\/tpu\/"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314652"},{"key":"e_1_2_1_9_1","first-page":"84","article-title":"Ese: Efficient speech recognition engine with sparse LSTM on FPGA","volume":"75","author":"Han S.","year":"2017","unstructured":"Han , S. . Ese: Efficient speech recognition engine with sparse LSTM on FPGA . FPGA , 2017 , 75 -- 84 . Han, S. et al. Ese: Efficient speech recognition engine with sparse LSTM on FPGA. FPGA, 2017, 75--84.","journal-title":"FPGA"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"e_1_2_1_11_1","first-page":"4","article-title":"Let there be color! joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification","volume":"3","author":"Iizuka S.","year":"2016","unstructured":"Iizuka , S. , Simo-Serra , E. , and Ishikawa , H . Let there be color! joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification . ACM Trans. Graphics 3 , 4 ( July 2016 ). Iizuka, S., Simo-Serra, E., and Ishikawa, H. Let there be color! joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification. ACM Trans. Graphics 3, 4 (July 2016).","journal-title":"ACM Trans. Graphics"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.280"},{"key":"e_1_2_1_13_1","volume-title":"Proceedings of the Intern. Conf. on Learning Representations","author":"Li H.","year":"2017","unstructured":"Li , H. , Kadav , A. , Durdanovic , I. , Samet , H. , and Graf , H . Pruning filters for efficient convnets . In Proceedings of the Intern. Conf. on Learning Representations , 2017 . Li, H., Kadav, A., Durdanovic, I., Samet, H., and Graf, H. Pruning filters for efficient convnets. In Proceedings of the Intern. Conf. on Learning Representations, 2017."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_2_1_15_1","volume-title":"AAAI","author":"Ma X.","year":"2020","unstructured":"Ma , X. et al. PCONV: The missing but desirable sparsity in DNN weight pruning for real-time execution on mobile devices . AAAI , 2020 . Ma, X. et al. PCONV: The missing but desirable sparsity in DNN weight pruning for real-time execution on mobile devices. AAAI, 2020."},{"key":"e_1_2_1_16_1","volume-title":"Exploring the regularity of sparse structure in convolutional neural networks. 2017","author":"Mao H.","year":"2017","unstructured":"Mao , H. , Han , S. , Pool , J. , Li , W. , Liu , X. , Wang , Y. , and Dally , W . Exploring the regularity of sparse structure in convolutional neural networks. 2017 ; arXiv:1705.08922, 2017 . Mao, H., Han, S., Pool, J., Li, W., Liu, X., Wang, Y., and Dally, W. Exploring the regularity of sparse structure in convolutional neural networks. 2017; arXiv:1705.08922, 2017."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622776.1622780"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378534"},{"key":"e_1_2_1_19_1","volume-title":"Proceedings of the IEEE Conf. Computer Vision and Pattern Recognition Workshops","author":"Timofte R.","year":"2017","unstructured":"Timofte , R. , Agustsson , E. , Gool , L. , Yang , M. , and Zhang , L . Ntire challenge on single image super-resolution: Methods and results . In Proceedings of the IEEE Conf. Computer Vision and Pattern Recognition Workshops , 2017 , 114--125. Timofte, R., Agustsson, E., Gool, L., Yang, M., and Zhang, L. Ntire challenge on single image super-resolution: Methods and results. In Proceedings of the IEEE Conf. Computer Vision and Pattern Recognition Workshops, 2017, 114--125."},{"key":"e_1_2_1_20_1","first-page":"2082","article-title":"Learning structured sparsity in deep neural networks","volume":"2074","author":"Wen W.","year":"2016","unstructured":"Wen , W. , Wu , C. , Wang , Y. , Chen , Y. , and Li , H . Learning structured sparsity in deep neural networks . In Advances in Neural Information Processing Systems , 2016 , 2074 -- 2082 . Wen, W., Wu, C., Wang, Y., Chen, Y., and Li, H. Learning structured sparsity in deep neural networks. In Advances in Neural Information Processing Systems, 2016, 2074--2082.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_21_1","volume-title":"Wide activation for efficient and accurate image super-resolution. 2018","author":"Yu J.","year":"1808","unstructured":"Yu , J. , Fan , Y. , Yang , J. , Xu , N. , Wang , Z. , Wang , X. , and Huang , T . Wide activation for efficient and accurate image super-resolution. 2018 ; arXiv: 1808 .08718. Yu, J., Fan, Y., Yang, J., Xu, N., Wang, Z., Wang, X., and Huang, T. Wide activation for efficient and accurate image super-resolution. 2018; arXiv:1808.08718."},{"key":"e_1_2_1_22_1","volume-title":"et al. Priv: A privacy-preserving deep neural network model compression framework. arXiv preprint","author":"Zhan Z.","year":"2020","unstructured":"Zhan , Z. et al. Priv: A privacy-preserving deep neural network model compression framework. arXiv preprint , 2020 . Zhan, Z. et al. Priv: A privacy-preserving deep neural network model compression framework. arXiv preprint, 2020."},{"key":"e_1_2_1_23_1","unstructured":"Zhang H. and Dana K. Multi-style generative network for real-time transfer. 2017; arXiv:1703.06953.  Zhang H. and Dana K. Multi-style generative network for real-time transfer. 2017; arXiv:1703.06953."},{"key":"e_1_2_1_24_1","first-page":"495","article-title":"Learning deep features for scene recognition using places database","volume":"487","author":"Zhou B.","year":"2014","unstructured":"Zhou , B. , Lapedriza , A. , Xiao , J. , Torralba , A. , and Oliva , A . Learning deep features for scene recognition using places database . In Advances in Neural Information Processing Systems , 2014 , 487 -- 495 . Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., and Oliva, A. Learning deep features for scene recognition using places database. In Advances in Neural Information Processing Systems, 2014, 487--495.","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["Communications of the ACM"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3418297","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3418297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:02:27Z","timestamp":1750197747000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3418297"}},"subtitle":["enabling real-time AI on off-the-shelf mobile devices via compression-compilation co-design"],"short-title":[],"issued":{"date-parts":[[2021,5,24]]},"references-count":24,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["10.1145\/3418297"],"URL":"https:\/\/doi.org\/10.1145\/3418297","relation":{},"ISSN":["0001-0782","1557-7317"],"issn-type":[{"value":"0001-0782","type":"print"},{"value":"1557-7317","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,24]]},"assertion":[{"value":"2021-05-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}