{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:58:21Z","timestamp":1782835101337,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T00:00:00Z","timestamp":1688947200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"CCDC Army Research Laboratory","award":["W911NF-17-2-0196"],"award-info":[{"award-number":["W911NF-17-2-0196"]}]},{"name":"National Science Foundation","award":["1719386 & 1815347"],"award-info":[{"award-number":["1719386 & 1815347"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,10]]},"DOI":"10.1145\/3570361.3592514","type":"proceedings-article","created":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T16:50:12Z","timestamp":1689007812000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Re-thinking computation offload for efficient inference on IoT devices with duty-cycled radios"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2118-2834","authenticated-orcid":false,"given":"Jin","family":"Huang","sequence":"first","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9128-2231","authenticated-orcid":false,"given":"Hui","family":"Guan","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, Massachusetts, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2762-9194","authenticated-orcid":false,"given":"Deepak","family":"Ganesan","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, Massachusetts, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,10]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Arm cortex-a77. https:\/\/www.arm.com\/products\/silicon-ip-cpu\/cortex-a\/cortex-a77.  Arm cortex-a77. https:\/\/www.arm.com\/products\/silicon-ip-cpu\/cortex-a\/cortex-a77."},{"key":"e_1_3_2_1_2_1","volume-title":"https:\/\/developer.arm.com\/Processors\/Cortex-M33","author":"Arm","unstructured":"Arm cortex-m33. https:\/\/developer.arm.com\/Processors\/Cortex-M33 . Arm cortex-m33. https:\/\/developer.arm.com\/Processors\/Cortex-M33."},{"key":"e_1_3_2_1_3_1","unstructured":"Maximize ble throughput. https:\/\/punchthrough.com\/maximizing-ble-throughput-on-ios-and-android\/.  Maximize ble throughput. https:\/\/punchthrough.com\/maximizing-ble-throughput-on-ios-and-android\/."},{"key":"e_1_3_2_1_4_1","unstructured":"nrf online power profiler. https:\/\/devzone.nordicsemi.com\/power\/w\/opp.  nrf online power profiler. https:\/\/devzone.nordicsemi.com\/power\/w\/opp."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451100"},{"key":"e_1_3_2_1_6_1","volume-title":"A downsampled variant of imagenet as an alternative to the cifar datasets. arXiv preprint arXiv:1707.08819","author":"Chrabaszcz Patryk","year":"2017","unstructured":"Patryk Chrabaszcz , Ilya Loshchilov , and Frank Hutter . A downsampled variant of imagenet as an alternative to the cifar datasets. arXiv preprint arXiv:1707.08819 , 2017 . Patryk Chrabaszcz, Ilya Loshchilov, and Frank Hutter. A downsampled variant of imagenet as an alternative to the cifar datasets. arXiv preprint arXiv:1707.08819, 2017."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102797"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-019-8208-z"},{"key":"e_1_3_2_1_10_1","article-title":"An efficient training and inference engine for intelligent mobile cloud computing services","author":"Eshratifar Amir Erfan","year":"2019","unstructured":"Amir Erfan Eshratifar , Mohammad Saeed Abrishami , and Massoud Pedram . Jointdnn : An efficient training and inference engine for intelligent mobile cloud computing services . IEEE Transactions on Mobile Computing , 2019 . Amir Erfan Eshratifar, Mohammad Saeed Abrishami, and Massoud Pedram. Jointdnn: An efficient training and inference engine for intelligent mobile cloud computing services. IEEE Transactions on Mobile Computing, 2019.","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"e_1_3_2_1_11_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149","author":"Han Song","year":"2015","unstructured":"Song Han , Huizi Mao , and William J Dally . Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 , 2015 . Song Han, Huizi Mao, and William J Dally. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149, 2015."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_13_1","unstructured":"Himax WE-I Plus EVB Endpoint AI Development Board. https:\/\/www.sparkfun.com\/products\/17256.  Himax WE-I Plus EVB Endpoint AI Development Board. https:\/\/www.sparkfun.com\/products\/17256."},{"key":"e_1_3_2_1_14_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton , Oriol Vinyals , and Jeff Dean . Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 , 2015 . Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2015."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_3_2_1_16_1","first-page":"613","volume-title":"2015 USENIX Annual Technical Conference (USENIX ATC 15)","author":"Huang Jian","year":"2015","unstructured":"Jian Huang , Anirudh Badam , Ranveer Chandra , and Edmund B. Nightingale . Weardrive: Fast and energy-efficient storage for wearables . In 2015 USENIX Annual Technical Conference (USENIX ATC 15) , pages 613 -- 625 , Santa Clara, CA , July 2015 . USENIX Association. Jian Huang, Anirudh Badam, Ranveer Chandra, and Edmund B. Nightingale. Weardrive: Fast and energy-efficient storage for wearables. In 2015 USENIX Annual Technical Conference (USENIX ATC 15), pages 613--625, Santa Clara, CA, July 2015. USENIX Association."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419215"},{"key":"e_1_3_2_1_18_1","volume-title":"Packet-loss-tolerant split inference for delay-sensitive deep learning in lossy wireless networks. arXiv preprint arXiv:2104.13629","author":"Itahara Sohei","year":"2021","unstructured":"Sohei Itahara , Takayuki Nishio , and Koji Yamamoto . Packet-loss-tolerant split inference for delay-sensitive deep learning in lossy wireless networks. arXiv preprint arXiv:2104.13629 , 2021 . Sohei Itahara, Takayuki Nishio, and Koji Yamamoto. Packet-loss-tolerant split inference for delay-sensitive deep learning in lossy wireless networks. arXiv preprint arXiv:2104.13629, 2021."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"e_1_3_2_1_21_1","first-page":"3301","volume-title":"International Conference on Machine Learning","author":"Kaya Yigitcan","year":"2019","unstructured":"Yigitcan Kaya , Sanghyun Hong , and Tudor Dumitras . Shallow-deep networks : Understanding and mitigating network overthinking . In International Conference on Machine Learning , pages 3301 -- 3310 . PMLR, 2019 . Yigitcan Kaya, Sanghyun Hong, and Tudor Dumitras. Shallow-deep networks: Understanding and mitigating network overthinking. In International Conference on Machine Learning, pages 3301--3310. PMLR, 2019."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2018.8639121"},{"key":"e_1_3_2_1_23_1","unstructured":"Alex Krizhevsky Vinod Nair and Geoffrey Hinton. Cifar-100 (canadian institute for advanced research).  Alex Krizhevsky Vinod Nair and Geoffrey Hinton. Cifar-100 (canadian institute for advanced research)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3243473"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419194"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3446382.3448359"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01418-6_40"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-432"},{"key":"e_1_3_2_1_29_1","first-page":"5958","volume-title":"International Conference on Machine Learning","author":"Li Zhuohan","year":"2020","unstructured":"Zhuohan Li , Eric Wallace , Sheng Shen , Kevin Lin , Kurt Keutzer , Dan Klein , and Joey Gonzalez . Train big, then compress: Rethinking model size for efficient training and inference of transformers . In International Conference on Machine Learning , pages 5958 -- 5968 . PMLR, 2020 . Zhuohan Li, Eric Wallace, Sheng Shen, Kevin Lin, Kurt Keutzer, Dan Klein, and Joey Gonzalez. Train big, then compress: Rethinking model size for efficient training and inference of transformers. In International Conference on Machine Learning, pages 5958--5968. PMLR, 2020."},{"key":"e_1_3_2_1_30_1","first-page":"34","article-title":"Memory-efficient patch-based inference for tiny deep learning","author":"Lin Ji","year":"2021","unstructured":"Ji Lin , Wei-Ming Chen , Han Cai , Chuang Gan , and Song Han . Memory-efficient patch-based inference for tiny deep learning . Advances in Neural Information Processing Systems , 34 , 2021 . Ji Lin, Wei-Ming Chen, Han Cai, Chuang Gan, and Song Han. Memory-efficient patch-based inference for tiny deep learning. Advances in Neural Information Processing Systems, 34, 2021.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"e_1_3_2_1_31_1","first-page":"1","article-title":"Context-adaptive and runtime-evolutionary deep model compression for mobile applications. Proceedings of the ACM on Interactive, Mobile","volume":"5","author":"Liu Sicong","year":"2021","unstructured":"Sicong Liu , Bin Guo , Ke Ma , Zhiwen Yu , and Junzhao Du. Adaspring : Context-adaptive and runtime-evolutionary deep model compression for mobile applications. Proceedings of the ACM on Interactive, Mobile , Wearable and Ubiquitous Technologies , 5 ( 1 ): 1 -- 22 , 2021 . Sicong Liu, Bin Guo, Ke Ma, Zhiwen Yu, and Junzhao Du. Adaspring: Context-adaptive and runtime-evolutionary deep model compression for mobile applications. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 5(1):1--22, 2021.","journal-title":"Wearable and Ubiquitous Technologies"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196022"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2021.3129415"},{"key":"e_1_3_2_1_34_1","unstructured":"microTVM: TVM on bare-metal. https:\/\/tvm.apache.org\/docs\/topic\/microtvm\/index.html.  microTVM: TVM on bare-metal. https:\/\/tvm.apache.org\/docs\/topic\/microtvm\/index.html."},{"key":"e_1_3_2_1_35_1","volume-title":"Raspberry pi 4 model b. online].(https:\/\/www.raspberrypi.org","author":"Pi Raspberry","year":"2015","unstructured":"Raspberry Pi . Raspberry pi 4 model b. online].(https:\/\/www.raspberrypi.org , 2015 . Raspberry Pi. Raspberry pi 4 model b. online].(https:\/\/www.raspberrypi.org, 2015."},{"key":"e_1_3_2_1_36_1","unstructured":"S32R2X: Microcontrollers for High-Performance Radar. https:\/\/www.nxp.com\/products\/processors-and-microcontrollers\/power-architecture\/s32r-radar-mcus\/s32r26-and-s32r27-microcontrollers-for-high-performance-radar:S32R2X.  S32R2X: Microcontrollers for High-Performance Radar. https:\/\/www.nxp.com\/products\/processors-and-microcontrollers\/power-architecture\/s32r-radar-mcus\/s32r26-and-s32r27-microcontrollers-for-high-performance-radar:S32R2X."},{"key":"e_1_3_2_1_37_1","volume-title":"Improving device-edge cooperative inference of deep learning via 2-step pruning. arXiv preprint arXiv:1903.03472","author":"Shi Wenqi","year":"2019","unstructured":"Wenqi Shi , Yunzhong Hou , Sheng Zhou , Zhisheng Niu , Yang Zhang , and Lu Geng . Improving device-edge cooperative inference of deep learning via 2-step pruning. arXiv preprint arXiv:1903.03472 , 2019 . Wenqi Shi, Yunzhong Hou, Sheng Zhou, Zhisheng Niu, Yang Zhang, and Lu Geng. Improving device-edge cooperative inference of deep learning via 2-step pruning. arXiv preprint arXiv:1903.03472, 2019."},{"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":"10.1109\/ICPR.2016.7900006"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.226"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.3390\/bios11100350"},{"key":"e_1_3_2_1_42_1","unstructured":"https:\/\/greenwaves-technologies.com\/gap8-product\/. GAP8: Ultra-low power always-on processor for embedded artificial intelligence.  https:\/\/greenwaves-technologies.com\/gap8-product\/. GAP8: Ultra-low power always-on processor for embedded artificial intelligence."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2979669"},{"key":"e_1_3_2_1_44_1","volume-title":"Tinyml: Machine learning with tensorflow lite on arduino and ultra-low-power microcontrollers","author":"Warden Pete","year":"2019","unstructured":"Pete Warden and Daniel Situnayake . Tinyml: Machine learning with tensorflow lite on arduino and ultra-low-power microcontrollers . O'Reilly Media , 2019 . Pete Warden and Daniel Situnayake. Tinyml: Machine learning with tensorflow lite on arduino and ultra-low-power microcontrollers. O'Reilly Media, 2019."}],"event":{"name":"MobiCom '23: 29th Annual International Conference on Mobile Computing and Networking","location":"Madrid Spain","acronym":"MobiCom '23","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the 29th Annual International Conference on Mobile Computing and Networking"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3570361.3592514","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3570361.3592514","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:27Z","timestamp":1750182567000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3570361.3592514"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,10]]},"references-count":44,"alternative-id":["10.1145\/3570361.3592514","10.1145\/3570361"],"URL":"https:\/\/doi.org\/10.1145\/3570361.3592514","relation":{},"subject":[],"published":{"date-parts":[[2023,7,10]]},"assertion":[{"value":"2023-07-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}