{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T15:51:28Z","timestamp":1762876288409,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,6,24]],"date-time":"2021-06-24T00:00:00Z","timestamp":1624492800000},"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":[],"published-print":{"date-parts":[[2021,6,25]]},"DOI":"10.1145\/3469116.3470011","type":"proceedings-article","created":{"date-parts":[[2021,6,24]],"date-time":"2021-06-24T10:10:05Z","timestamp":1624529405000},"page":"7-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Are Mobile DNN Accelerators Accelerating DNNs?"],"prefix":"10.1145","author":[{"given":"Qingqing","family":"Cao","sequence":"first","affiliation":[{"name":"Stony Brook University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandru E.","family":"Irimiea","sequence":"additional","affiliation":[{"name":"University of Oxford"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Abdelfattah","sequence":"additional","affiliation":[{"name":"Samsung AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aruna","family":"Balasubramanian","sequence":"additional","affiliation":[{"name":"Stony Brook University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas D.","family":"Lane","sequence":"additional","affiliation":[{"name":"University of Cambridge and Samsung AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,6,24]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2013. Sentiment analysis and artificial intelligence: Siri should I open this email? https:\/\/venturebeat.com\/2013\/04\/01\/sentiment-analysis-and-artificial-intelligence-siri-should-i-open-this-email\/  2013. Sentiment analysis and artificial intelligence: Siri should I open this email? https:\/\/venturebeat.com\/2013\/04\/01\/sentiment-analysis-and-artificial-intelligence-siri-should-i-open-this-email\/"},{"key":"e_1_3_2_1_2_1","unstructured":"2018. Google APIs for Android. https:\/\/developers.google.com\/android\/reference\/com\/google\/android\/gms\/location\/DetectedActivity.  2018. Google APIs for Android. https:\/\/developers.google.com\/android\/reference\/com\/google\/android\/gms\/location\/DetectedActivity."},{"key":"e_1_3_2_1_3_1","unstructured":"2018. Hey Siri: An On-device DNN-powered Voice Trigger for Apple's Personal Assistant. https:\/\/machinelearning.apple.com\/2017\/10\/01\/hey-siri.html.  2018. Hey Siri: An On-device DNN-powered Voice Trigger for Apple's Personal Assistant. https:\/\/machinelearning.apple.com\/2017\/10\/01\/hey-siri.html."},{"key":"e_1_3_2_1_4_1","unstructured":"2019. Beyond Siri Google Assistant and Alexa - what you need to know about AI Conversational Applications. https:\/\/www.kdnuggets.com\/beyond-siri-googleassistant-and-alexa-what-you-need-to-know-about-ai-conversational-applications.html\/  2019. Beyond Siri Google Assistant and Alexa - what you need to know about AI Conversational Applications. https:\/\/www.kdnuggets.com\/beyond-siri-googleassistant-and-alexa-what-you-need-to-know-about-ai-conversational-applications.html\/"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2016.7581275"},{"key":"e_1_3_2_1_6_1","unstructured":"Amazon. 2019. MakerHawk UM34C. https:\/\/www.amazon.com\/MakerHawk-Bluetooth-Voltmeter-Multimeter-Resistance\/dp\/B07DK4GDSP. accessed 22-October-2019.  Amazon. 2019. MakerHawk UM34C. https:\/\/www.amazon.com\/MakerHawk-Bluetooth-Voltmeter-Multimeter-Resistance\/dp\/B07DK4GDSP. accessed 22-October-2019."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_8_1","unstructured":"TensorFlow Authors. 2018. TensorFlow Lite. https:\/\/www.tensorflow.org\/. accessed 8-April-2017.  TensorFlow Authors. 2018. TensorFlow Lite. https:\/\/www.tensorflow.org\/. accessed 8-April-2017."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2015.10"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"e_1_3_2_1_12_1","volume-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1. arXiv:1602.02830","author":"Courbariaux Matthieu","year":"2016","unstructured":"Matthieu Courbariaux , Itay Hubara , Daniel Soudry , Ran El-Yaniv , and Yoshua Bengio . 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1. arXiv:1602.02830 ( 2016 ). Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1. arXiv:1602.02830 (2016)."},{"key":"e_1_3_2_1_13_1","first-page":"19","volume-title":"Proc of the 2019 Conf. of the NAACL-HLT. Association for Computational Linguistics","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2019 . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding . In Proc of the 2019 Conf. of the NAACL-HLT. Association for Computational Linguistics , Minneapolis, Minnesota, 4171--4186. https:\/\/doi.org\/10. 18653\/v1\/N 19 - 1423 10.18653\/v1 Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proc of the 2019 Conf. of the NAACL-HLT. Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186. https:\/\/doi.org\/10.18653\/v1\/N19-1423"},{"key":"e_1_3_2_1_14_1","volume-title":"Compressing deep convolutional networks using vector quantization. arXiv:1412.6115","author":"Gong Yunchao","year":"2014","unstructured":"Yunchao Gong , Liu Liu , Ming Yang , and Lubomir Bourdev . 2014. Compressing deep convolutional networks using vector quantization. arXiv:1412.6115 ( 2014 ). Yunchao Gong, Liu Liu, Ming Yang, and Lubomir Bourdev. 2014. Compressing deep convolutional networks using vector quantization. arXiv:1412.6115 (2014)."},{"key":"e_1_3_2_1_15_1","unstructured":"Google. 2018. TensorFlow. https:\/\/www.tensorflow.org\/. accessed 8-May-2018.  Google. 2018. TensorFlow. https:\/\/www.tensorflow.org\/. accessed 8-May-2018."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3204949.3204975"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_19_1","unstructured":"Huawei. 2018. Kirin 970. http:\/\/www.hisilicon.com\/en\/Media-Center\/News\/Key-Information-About-the-Huawei-Kirin970.  Huawei. 2018. Kirin 970. http:\/\/www.hisilicon.com\/en\/Media-Center\/News\/Key-Information-About-the-Huawei-Kirin970."},{"key":"e_1_3_2_1_20_1","volume-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and &lt","author":"Iandola Forrest N","year":"2016","unstructured":"Forrest N Iandola , Song Han , Matthew W Moskewicz , Khalid Ashraf , William J Dally , and Kurt Keutzer . 2016 . Squeezenet: Alexnet-level accuracy with 50x fewer parameters and &lt ; 0.5 mb model size. arXiv:1602.07360 (2016). Forrest N Iandola, Song Han, Matthew W Moskewicz, Khalid Ashraf, William J Dally, and Kurt Keutzer. 2016. Squeezenet: Alexnet-level accuracy with 50x fewer parameters and < 0.5 mb model size. arXiv:1602.07360 (2016)."},{"key":"e_1_3_2_1_21_1","volume-title":"AI Benchmark: Running Deep Neural Networks on Android Smartphones. ArXiv e-prints (Oct","author":"Ignatov A.","year":"2018","unstructured":"A. Ignatov , R. Timofte , W. Chou , K. Wang , M. Wu , T. Hartley , and L. Van Gool . 2018. AI Benchmark: Running Deep Neural Networks on Android Smartphones. ArXiv e-prints (Oct . 2018 ). arXiv:1810.01109 [cs.AI] A. Ignatov, R. Timofte, W. Chou, K. Wang, M. Wu, T. Hartley, and L. Van Gool. 2018. AI Benchmark: Running Deep Neural Networks on Android Smartphones. ArXiv e-prints (Oct. 2018). arXiv:1810.01109 [cs.AI]"},{"key":"e_1_3_2_1_22_1","unstructured":"Intel. 2019. Intel Neural Compute Stick 2. https:\/\/software.intel.com\/en-us\/neural-compute-stick. accessed 22-October-2019.  Intel. 2019. Intel Neural Compute Stick 2. https:\/\/software.intel.com\/en-us\/neural-compute-stick. accessed 22-October-2019."},{"key":"e_1_3_2_1_23_1","unstructured":"Intel. 2019. OpenVINO Toolkit. https:\/\/software.intel.com\/en-us\/openvino-toolkit. accessed 21-October-2019.  Intel. 2019. OpenVINO Toolkit. https:\/\/software.intel.com\/en-us\/openvino-toolkit. accessed 21-October-2019."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/2959355.2959378"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454289"},{"key":"e_1_3_2_1_27_1","unstructured":"Jiasen Lu Vedanuj Goswami Marcus Rohrbach Devi Parikh and Stefan Lee. 2020. 12-in-1: Multi-Task Vision and Language Representation Learning. 10437--10446.  Jiasen Lu Vedanuj Goswami Marcus Rohrbach Devi Parikh and Stefan Lee. 2020. 12-in-1: Multi-Task Vision and Language Representation Learning. 10437--10446."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2014.7478823"},{"key":"e_1_3_2_1_29_1","unstructured":"Movidius. 2018. Movidius Neural Compute Stick. https:\/\/developer.movidius.com\/. accessed 23-March-2018.  Movidius. 2018. Movidius Neural Compute Stick. https:\/\/developer.movidius.com\/. accessed 23-March-2018."},{"key":"e_1_3_2_1_30_1","unstructured":"Movidius. 2018. SDK for the Neural Compute Stick. https:\/\/github.com\/movidius\/ncsdk. accessed 21-April-2018.  Movidius. 2018. SDK for the Neural Compute Stick. https:\/\/github.com\/movidius\/ncsdk. accessed 21-April-2018."},{"key":"e_1_3_2_1_31_1","unstructured":"OnePlus. 2018. OnePlus 3. https:\/\/www.oneplus.com\/3.  OnePlus. 2018. OnePlus 3. https:\/\/www.oneplus.com\/3."},{"key":"e_1_3_2_1_32_1","unstructured":"Qualcomm. 2018. Snapdragon Neural Processing Engine. https:\/\/developer.qualcomm.com\/software\/snapdragon-neural-processing-engine. accessed 13-May-2018.  Qualcomm. 2018. Snapdragon Neural Processing Engine. https:\/\/developer.qualcomm.com\/software\/snapdragon-neural-processing-engine. accessed 13-May-2018."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001165"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_36_1","volume-title":"Proc. of the 2013 conf. on empirical methods in natural language processing. 1631--1642","author":"Socher Richard","year":"2013","unstructured":"Richard Socher , Alex Perelygin , Jean Wu , Jason Chuang , Christopher D Manning , Andrew Y Ng , and Christopher Potts . 2013 . Recursive deep models for semantic compositionality over a sentiment treebank . In Proc. of the 2013 conf. on empirical methods in natural language processing. 1631--1642 . Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D Manning, Andrew Y Ng, and Christopher Potts. 2013. Recursive deep models for semantic compositionality over a sentiment treebank. In Proc. of the 2013 conf. on empirical methods in natural language processing. 1631--1642."},{"key":"e_1_3_2_1_37_1","unstructured":"Monsoon Solutions. 2018. Monsoon Power Monitor. https:\/\/www.msoon.com\/LabEquipment\/PowerMonitor\/.  Monsoon Solutions. 2018. Monsoon Power Monitor. https:\/\/www.msoon.com\/LabEquipment\/PowerMonitor\/."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_1_40_1","volume-title":"Well-read students learn better: On the importance of pre-training compact models. arXiv:1908.08962","author":"Turc Iulia","year":"2019","unstructured":"Iulia Turc , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2019. Well-read students learn better: On the importance of pre-training compact models. arXiv:1908.08962 ( 2019 ). Iulia Turc, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Well-read students learn better: On the importance of pre-training compact models. arXiv:1908.08962 (2019)."},{"key":"e_1_3_2_1_41_1","unstructured":"Nvidia TX2. 2018. Nvidia TX2. https:\/\/devblogs.nvidia.com\/jetson-tx2-delivers-twice-intelligence-edge\/.  Nvidia TX2. 2018. Nvidia TX2. https:\/\/devblogs.nvidia.com\/jetson-tx2-delivers-twice-intelligence-edge\/."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"}],"event":{"name":"MobiSys '21: The 19th Annual International Conference on Mobile Systems, Applications, and Services","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGOPS ACM Special Interest Group on Operating Systems"],"location":"Virtual WI USA","acronym":"MobiSys '21"},"container-title":["Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3469116.3470011","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3469116.3470011","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:29Z","timestamp":1750191509000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3469116.3470011"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,24]]},"references-count":43,"alternative-id":["10.1145\/3469116.3470011","10.1145\/3469116"],"URL":"https:\/\/doi.org\/10.1145\/3469116.3470011","relation":{},"subject":[],"published":{"date-parts":[[2021,6,24]]},"assertion":[{"value":"2021-06-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}