{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:44:59Z","timestamp":1775745899355,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,11,6]],"date-time":"2022-11-06T00:00:00Z","timestamp":1667692800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Research Grants Council (RGC)-General Research Fund","award":["14209619&14203420"],"award-info":[{"award-number":["14209619&14203420"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,11,6]]},"DOI":"10.1145\/3560905.3568520","type":"proceedings-article","created":{"date-parts":[[2023,1,24]],"date-time":"2023-01-24T23:37:10Z","timestamp":1674603430000},"page":"91-105","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":34,"title":["BlastNet"],"prefix":"10.1145","author":[{"given":"Neiwen","family":"Ling","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}]},{"given":"Xuan","family":"Huang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}]},{"given":"Zhihe","family":"Zhao","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}]},{"given":"Nan","family":"Guan","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, China"}]},{"given":"Zhenyu","family":"Yan","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}]},{"given":"Guoliang","family":"Xing","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}]}],"member":"320","published-online":{"date-parts":[[2023,1,24]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS.2018.00020"},{"key":"e_1_3_2_1_2_1","volume-title":"Proxylessnas: Direct neural architecture search on target task and hardware. arXiv preprint arXiv:1812.00332","author":"Cai Han","year":"2018","unstructured":"Han Cai, Ligeng Zhu, and Song Han. Proxylessnas: Direct neural architecture search on target task and hardware. arXiv preprint arXiv:1812.00332, 2018."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"e_1_3_2_1_4_1","first-page":"578","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis 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), pages 578--594, 2018."},{"key":"e_1_3_2_1_5_1","unstructured":"F1TENTH Community. F1tenth. https:\/\/f1tenth.org\/."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01166"},{"key":"e_1_3_2_1_7_1","first-page":"953","volume-title":"Fused dnn: A deep neural network fusion approach to fast and robust pedestrian detection. In 2017 IEEE winter conference on applications of computer vision (WACV)","author":"Du Xianzhi","year":"2017","unstructured":"Xianzhi Du, Mostafa El-Khamy, Jungwon Lee, and Larry Davis. Fused dnn: A deep neural network fusion approach to fast and robust pedestrian detection. In 2017 IEEE winter conference on applications of computer vision (WACV), pages 953--961. IEEE, 2017."},{"key":"e_1_3_2_1_8_1","volume-title":"Cnn2gate: Toward designing a general framework for implementation of convolutional neural networks on fpga. arXiv preprint arXiv:2004.04641","author":"Ghaffari Alireza","year":"2020","unstructured":"Alireza Ghaffari and Yvon Savaria. Cnn2gate: Toward designing a general framework for implementation of convolutional neural networks on fpga. arXiv preprint arXiv:2004.04641, 2020."},{"key":"e_1_3_2_1_9_1","volume-title":"A survey of quantization methods for efficient neural network inference. arXiv preprint arXiv:2103.13630","author":"Gholami Amir","year":"2021","unstructured":"Amir Gholami, Sehoon Kim, Zhen Dong, Zhewei Yao, Michael W Mahoney, and Kurt Keutzer. A survey of quantization methods for efficient neural network inference. arXiv preprint arXiv:2103.13630, 2021."},{"key":"e_1_3_2_1_10_1","unstructured":"News Google. Google tensor soc titan m2 security chip features detailed. https:\/\/www.fonearena.com\/blog\/350642\/google-tensor-soc-features.html\/."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2019.00021"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483249"},{"key":"e_1_3_2_1_13_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."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/SiPS47522.2019.9020540"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH48897.2020.00029"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_3_2_1_18_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G","year":"2017","unstructured":"Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538948"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538932"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS52674.2021.00038"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC.2019.8666562"},{"key":"e_1_3_2_1_23_1","unstructured":"Sandra Khvoynitskaya. 3 types of autonomous vehicle sensors in self-driving cars. https:\/\/www.itransition.com\/blog\/autonomous-vehicle-sensors."},{"key":"e_1_3_2_1_24_1","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky Alex","year":"2009","unstructured":"Alex Krizhevsky, Geoffrey Hinton, et al. Learning multiple layers of features from tiny images. 2009."},{"key":"e_1_3_2_1_25_1","first-page":"1097","volume-title":"Advances in neural information processing systems","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097--1105, 2012."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419194"},{"key":"e_1_3_2_1_27_1","first-page":"191","volume-title":"Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021","author":"Lee Seulki","year":"2021","unstructured":"Seulki Lee and Shahriar Nirjon. Deep functional network (dfn) functional interpretation of deep neural networks for intelligent sensing systems. In Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021), pages 191--206, 2021."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00783"},{"key":"e_1_3_2_1_29_1","first-page":"222","volume-title":"CVPR Workshops","author":"Li Peilun","year":"2019","unstructured":"Peilun Li, Guozhen Li, Zhangxi Yan, Youzeng Li, Meiqi Lu, Pengfei Xu, Yang Gu, Bing Bai, Yifei Zhang, and DiDi Chuxing. Spatio-temporal consistency and hierarchical matching for multi-target multi-camera vehicle tracking. In CVPR Workshops, pages 222--230, 2019."},{"key":"e_1_3_2_1_30_1","volume-title":"Detnet: A backbone network for object detection. arXiv preprint arXiv:1804.06215","author":"Li Zeming","year":"2018","unstructured":"Zeming Li, Chao Peng, Gang Yu, Xiangyu Zhang, Yangdong Deng, and Jian Sun. Detnet: A backbone network for object detection. arXiv preprint arXiv:1804.06215, 2018."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485938"},{"key":"e_1_3_2_1_34_1","volume-title":"Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055","author":"Liu Hanxiao","year":"2018","unstructured":"Hanxiao Liu, Karen Simonyan, and Yiming Yang. Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055, 2018."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.211.2100302"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11356-020-09950-3"},{"key":"e_1_3_2_1_37_1","volume-title":"A survey of cpu-gpu heterogeneous computing techniques. ACM Computing Surveys (CSUR), 47(4):1--35","author":"Mittal Sparsh","year":"2015","unstructured":"Sparsh Mittal and Jeffrey S Vetter. A survey of cpu-gpu heterogeneous computing techniques. ACM Computing Surveys (CSUR), 47(4):1--35, 2015."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454083"},{"key":"e_1_3_2_1_39_1","unstructured":"NVIDIA. Cuda c\/c++ streams and concurrency. https:\/\/developer.download.nvidia.com\/CUDA\/training\/StreamsAndConcurrencyWebinar.pdf."},{"key":"e_1_3_2_1_40_1","unstructured":"NVIDIA. Jetson agx xavier series modules and developer kit. https:\/\/www.nvidia.com\/en-us\/autonomous-machines\/embedded-systems\/jetson-agx-xavier\/."},{"key":"e_1_3_2_1_41_1","unstructured":"NVIDIA. Tegrastats utility. https:\/\/docs.nvidia.com\/drive\/drive_os_5.1.6.1L\/nvvib_docs\/index.html#page\/DRIVE_OS_Linux_SDK_Development_Guide\/Utilities\/util_tegrastats.html."},{"key":"e_1_3_2_1_42_1","unstructured":"PyTorch. Cpu threading and torchscript inference. https:\/\/pytorch.org\/docs\/stable\/notes\/cpu_threading_torchscript_inference.html."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3380891"},{"key":"e_1_3_2_1_44_1","volume-title":"Yolov3: An incremental improvement. arXiv","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi. Yolov3: An incremental improvement. arXiv, 2018."},{"key":"e_1_3_2_1_45_1","unstructured":"Microsoft Research. Nni (neural network intelligence). https:\/\/nni.readthedocs.io\/en\/stable\/."},{"key":"e_1_3_2_1_46_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.52"},{"key":"e_1_3_2_1_48_1","volume-title":"Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition. Neural Networks, (0):-","author":"Stallkamp J.","year":"2012","unstructured":"J. Stallkamp, M. Schlipsing, J. Salmen, and C. Igel. Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition. Neural Networks, (0):-, 2012."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"e_1_3_2_1_50_1","first-page":"21","article-title":"To bridge neural network design and real-world performance: A behaviour study for neural networks","volume":"3","author":"Tang Xiaohu","year":"2021","unstructured":"Xiaohu Tang, Shihao Han, Li Lyna Zhang, Ting Cao, and Yunxin Liu. To bridge neural network design and real-world performance: A behaviour study for neural networks. Proceedings of Machine Learning and Systems, 3:21--37, 2021.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3448625"},{"key":"e_1_3_2_1_52_1","volume-title":"Generalizing from a few examples: A survey on few-shot learning. ACM computing surveys (csur), 53(3):1--34","author":"Wang Yaqing","year":"2020","unstructured":"Yaqing Wang, Quanming Yao, James T Kwok, and Lionel M Ni. Generalizing from a few examples: A survey on few-shot learning. ACM computing surveys (csur), 53(3):1--34, 2020."},{"key":"e_1_3_2_1_53_1","unstructured":"Wikipedia. Worst-case execution time. https:\/\/en.wikipedia.org\/wiki\/Worst-case_execution_time."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS46320.2019.00042"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2784093"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3345448"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3107424"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419192"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.3390\/fi11040094"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.3042320"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274783.3275199"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450268.3453520"}],"event":{"name":"SenSys '22: The 20th ACM Conference on Embedded Networked Sensor Systems","location":"Boston Massachusetts","acronym":"SenSys '22","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGCOMM ACM Special Interest Group on Data Communication","SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGOPS ACM Special Interest Group on Operating Systems","SIGBED ACM Special Interest Group on Embedded Systems","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3560905.3568520","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3560905.3568520","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:15Z","timestamp":1750182555000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3560905.3568520"}},"subtitle":["Exploiting Duo-Blocks for Cross-Processor Real-Time DNN Inference"],"short-title":[],"issued":{"date-parts":[[2022,11,6]]},"references-count":63,"alternative-id":["10.1145\/3560905.3568520","10.1145\/3560905"],"URL":"https:\/\/doi.org\/10.1145\/3560905.3568520","relation":{},"subject":[],"published":{"date-parts":[[2022,11,6]]},"assertion":[{"value":"2023-01-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}