{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:17:51Z","timestamp":1780053471605,"version":"3.54.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,7,26]],"date-time":"2021-07-26T00:00:00Z","timestamp":1627257600000},"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":[[2021,7,26]]},"DOI":"10.1145\/3466772.3467037","type":"proceedings-article","created":{"date-parts":[[2021,6,29]],"date-time":"2021-06-29T10:38:19Z","timestamp":1624963099000},"page":"81-90","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Real-Time Deep Video Analytics on Mobile Devices"],"prefix":"10.1145","author":[{"given":"Jian","family":"He","sequence":"first","affiliation":[{"name":"The University of Texas at Austin, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ghufran","family":"Baig","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lili","family":"Qiu","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,7,26]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Convolutional filter. http:\/\/cs231n.github.io\/convolutional-networks\/#conv.  Convolutional filter. http:\/\/cs231n.github.io\/convolutional-networks\/#conv."},{"key":"e_1_3_2_1_2_1","unstructured":"Dynamic voltage and frequency scaling on nvidia jetson tx2. https:\/\/devblogs.nvidia.com\/jetson-tx2-delivers-twice-intelligence-edge\/.  Dynamic voltage and frequency scaling on nvidia jetson tx2. https:\/\/devblogs.nvidia.com\/jetson-tx2-delivers-twice-intelligence-edge\/."},{"key":"e_1_3_2_1_3_1","unstructured":"Nvidia geforce 940m. https:\/\/www.geforce.com\/hardware\/notebook-gpus\/geforce-940m.  Nvidia geforce 940m. https:\/\/www.geforce.com\/hardware\/notebook-gpus\/geforce-940m."},{"key":"e_1_3_2_1_4_1","unstructured":"Nvidia jetson tx2. https:\/\/developer.nvidia.com\/embedded\/buy\/jetson-tx2.  Nvidia jetson tx2. https:\/\/developer.nvidia.com\/embedded\/buy\/jetson-tx2."},{"key":"e_1_3_2_1_5_1","unstructured":"Nvidia titan xp. https:\/\/www.nvidia.com\/en-us\/titan\/titan-xp\/.  Nvidia titan xp. https:\/\/www.nvidia.com\/en-us\/titan\/titan-xp\/."},{"key":"e_1_3_2_1_6_1","unstructured":"Software-based powerconsumption modeling. http:\/\/developer2.download.nvidia.com\/embedded\/L4T\/r27_Release_v1.0\/Docs\/Tegra_Linux_Driver_Package_Release_Notes_R27.1.pdf.  Software-based powerconsumption modeling. http:\/\/developer2.download.nvidia.com\/embedded\/L4T\/r27_Release_v1.0\/Docs\/Tegra_Linux_Driver_Package_Release_Notes_R27.1.pdf."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3356250.3360044"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01420984"},{"key":"e_1_3_2_1_9_1","volume-title":"The OpenCV Library. Dr. Dobb's Journal of Software Tools","author":"Bradski G.","year":"2000","unstructured":"G. Bradski . The OpenCV Library. Dr. Dobb's Journal of Software Tools , 2000 . G. Bradski. The OpenCV Library. Dr. Dobb's Journal of Software Tools, 2000."},{"key":"e_1_3_2_1_10_1","volume-title":"Scaling video analytics on constrained edge nodes. arXiv preprint arXiv:1905.13536","author":"Canel C.","year":"2019","unstructured":"C. Canel , T. Kim , G. Zhou , C. Li , H. Lim , D. G. Andersen , M. Kaminsky , and S. R. Dulloor . Scaling video analytics on constrained edge nodes. arXiv preprint arXiv:1905.13536 , 2019 . C. Canel, T. Kim, G. Zhou, C. Li, H. Lim, D. G. Andersen, M. Kaminsky, and S. R. Dulloor. Scaling video analytics on constrained edge nodes. arXiv preprint arXiv:1905.13536, 2019."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274783.3274834"},{"key":"e_1_3_2_1_12_1","volume-title":"Proc. of IEEE 10th Workshop on Multimedia Signal Processing","author":"Chen T.-W.","year":"2008","unstructured":"T.-W. Chen , Y.-L. Chen , and S.-Y. Chien . Fast image segmentation based on k-means clustering with histograms in hsv color space . In Proc. of IEEE 10th Workshop on Multimedia Signal Processing , 2008 . T.-W. Chen, Y.-L. Chen, and S.-Y. Chien. Fast image segmentation based on k-means clustering with histograms in hsv color space. In Proc. of IEEE 10th Workshop on Multimedia Signal Processing, 2008."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2809695.2809711"},{"key":"e_1_3_2_1_14_1","volume-title":"CoRR","author":"Chetlur S.","year":"2014","unstructured":"S. Chetlur , C. Woolley , P. Vandermersch , J. Cohen , J. Tran , B. Catanzaro , and E. Shelhamer . cudnn: Efficient primitives for deep learning . CoRR , 2014 . S. Chetlur, C. Woolley, P. Vandermersch, J. Cohen, J. Tran, B. Catanzaro, and E. Shelhamer. cudnn: Efficient primitives for deep learning. CoRR, 2014."},{"key":"e_1_3_2_1_15_1","volume-title":"proc. systems","author":"Dai J.","year":"2016","unstructured":"J. Dai , Y. Li , K. He , and J. Sun . R-fcn: Object detection via region-based fully convolutional networks. In Adv. in neural info . proc. systems , 2016 . J. Dai, Y. Li, K. He, and J. Sun. R-fcn: Object detection via region-based fully convolutional networks. In Adv. in neural info. proc. systems, 2016."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.84"},{"key":"e_1_3_2_1_17_1","volume-title":"The pascal visual object classes challenge 2007 (voc2007) results","author":"Everingham M.","year":"2007","unstructured":"M. Everingham , L. Van Gool , C. K. Williams , J. Winn , and A. Zisserman . The pascal visual object classes challenge 2007 (voc2007) results . 2007 . M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman. The pascal visual object classes challenge 2007 (voc2007) results. 2007."},{"key":"e_1_3_2_1_18_1","volume-title":"Pascal visual object classes (voc) challenge. Intl. journal of computer vision, 88(2)","author":"Everingham M.","year":"2010","unstructured":"M. Everingham , L. Van Gool , C. K. Williams , J. Winn , and A. Zisserman . Pascal visual object classes (voc) challenge. Intl. journal of computer vision, 88(2) , 2010 . M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman. Pascal visual object classes (voc) challenge. Intl. journal of computer vision, 88(2), 2010."},{"key":"e_1_3_2_1_19_1","volume-title":"J. Bigun and T. Gustavsson","author":"Farneb\u00e4ck G.","year":"2003","unstructured":"G. Farneb\u00e4ck . Two-frame motion estimation based on polynomial expansion. In J. Bigun and T. Gustavsson , editors, Image Analysis, Berlin, Heidelberg , 2003 . Springer Berlin Heidelberg . G. Farneb\u00e4ck. Two-frame motion estimation based on polynomial expansion. In J. Bigun and T. Gustavsson, editors, Image Analysis, Berlin, Heidelberg, 2003. Springer Berlin Heidelberg."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC47752.2019.9041955"},{"key":"e_1_3_2_1_21_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149","author":"Han S.","year":"2015","unstructured":"S. Han , H. Mao , and W. J. Dally . Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 , 2015 . S. Han, H. Mao, and W. 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_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3204949.3204975"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3081333.3081360"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037698"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2516982"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405874"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3300116"},{"key":"e_1_3_2_1_30_1","volume-title":"Proc. of the IEEE Conference on CVPR","author":"Liu M.","year":"2018","unstructured":"M. Liu and M. Zhu . Mobile video object detection with temporally-aware feature maps . In Proc. of the IEEE Conference on CVPR , 2018 . M. Liu and M. Zhu. Mobile video object detection with temporally-aware feature maps. In Proc. of the IEEE Conference on CVPR, 2018."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP.2018.00011"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3210240.3210337"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.352"},{"key":"e_1_3_2_1_36_1","volume-title":"Nvidia video codec sdk. https:\/\/developer.nvidia.com\/nvidia-video-codec-sdk","year":"2019","unstructured":"Nvidia. Nvidia video codec sdk. https:\/\/developer.nvidia.com\/nvidia-video-codec-sdk , 2019 . Nvidia. Nvidia video codec sdk. https:\/\/developer.nvidia.com\/nvidia-video-codec-sdk, 2019."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/78.127962"},{"key":"e_1_3_2_1_38_1","volume-title":"Advances in Neural Information Processing Systems","author":"Pinheiro P. O.","year":"2015","unstructured":"P. O. Pinheiro , R. Collobert , and P. Doll\u00e1r . Learning to segment object candidates . In Advances in Neural Information Processing Systems , 2015 . P. O. Pinheiro, R. Collobert, and P. Doll\u00e1r. Learning to segment object candidates. In Advances in Neural Information Processing Systems, 2015."},{"key":"e_1_3_2_1_39_1","volume-title":"The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675","author":"Pont-Tuset J.","year":"2017","unstructured":"J. Pont-Tuset , F. Perazzi , S. Caelles , P. Arbel\u00e1ez , A. Sorkine-Hornung , and L. Van Gool . The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675 , 2017 . J. Pont-Tuset, F. Perazzi, S. Caelles, P. Arbel\u00e1ez, A. Sorkine-Hornung, and L. Van Gool. The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675, 2017."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485905"},{"key":"e_1_3_2_1_41_1","unstructured":"J. Redmon. Darknet: Open source neural networks in c. http:\/\/pjreddie.com\/darknet\/ 2013--2016.  J. Redmon. Darknet: Open source neural networks in c. http:\/\/pjreddie.com\/darknet\/ 2013--2016."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_3_2_1_44_1","volume-title":"proc. sys.","author":"Ren S.","year":"2015","unstructured":"S. Ren , K. He , R. Girshick , and J. Sun . Faster R-CNN: Towards real-time object detection with region proposal networks. In Adv. in neural info . proc. sys. , 2015 . S. Ren, K. He, R. Girshick, and J. Sun. Faster R-CNN: Towards real-time object detection with region proposal networks. In Adv. in neural info. proc. sys., 2015."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"issue":"3","key":"e_1_3_2_1_46_1","volume":"14","author":"Sabirin H.","year":"2012","unstructured":"H. Sabirin and M. Kim . Moving object detection and tracking using a spatiotemporal graph in h. 264\/avc bitstreams for video surveillance. IEEE Transactions on Multimedia , 14 ( 3 ), 2012 . H. Sabirin and M. Kim. Moving object detection and tracking using a spatiotemporal graph in h. 264\/avc bitstreams for video surveillance. IEEE Transactions on Multimedia, 14(3), 2012.","journal-title":"264\/avc bitstreams for video surveillance. IEEE Transactions on Multimedia"},{"key":"e_1_3_2_1_47_1","volume":"1","author":"Sanderson C.","year":"2016","unstructured":"C. Sanderson and R. Curtin . Armadillo: a template-based C++ library for linear algebra. The Journal of Open Source Software , 1 , June 2016 . C. Sanderson and R. Curtin. Armadillo: a template-based C++ library for linear algebra. The Journal of Open Source Software, 1, June 2016.","journal-title":"Armadillo: a template-based C++ library for linear algebra. The Journal of Open Source Software"},{"issue":"2","key":"e_1_3_2_1_48_1","volume":"2","author":"Shantaiya S.","year":"2015","unstructured":"S. Shantaiya , K. Verma , and K. Mehta . Multiple object tracking using kalman filter and optical flow. European Journal of Adv. in Eng. and Tech. , 2 ( 2 ), 2015 . S. Shantaiya, K. Verma, and K. Mehta. Multiple object tracking using kalman filter and optical flow. European Journal of Adv. in Eng. and Tech., 2(2), 2015.","journal-title":"European Journal of Adv. in Eng. and Tech."},{"key":"e_1_3_2_1_49_1","volume-title":"Optical flow-based real-time object tracking using non-prior training active feature model. Real-Time Imaging, 11(3)","author":"Shin J.","year":"2005","unstructured":"J. Shin , S. Kim , S. Kang , S.-W. Lee , J. Paik , B. Abidi , and M. Abidi . Optical flow-based real-time object tracking using non-prior training active feature model. Real-Time Imaging, 11(3) , 2005 . J. Shin, S. Kim, S. Kang, S.-W. Lee, J. Paik, B. Abidi, and M. Abidi. Optical flow-based real-time object tracking using non-prior training active feature model. Real-Time Imaging, 11(3), 2005."},{"key":"e_1_3_2_1_50_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan K.","year":"2014","unstructured":"K. Simonyan and A. Zisserman . Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 , 2014 . K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.357"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"issue":"7","key":"e_1_3_2_1_53_1","volume":"13","author":"Wiegand T.","year":"2003","unstructured":"T. Wiegand , G. J. Sullivan , G. Bjontegaard , and A. Luthra . Overview of the h. 264\/avc video coding standard. IEEE Transactions on circuits and systems for video technology , 13 ( 7 ), 2003 . T. Wiegand, G. J. Sullivan, G. Bjontegaard, and A. Luthra. Overview of the h. 264\/avc video coding standard. IEEE Transactions on circuits and systems for video technology, 13(7), 2003.","journal-title":"Overview of the h. 264\/avc video coding standard. IEEE Transactions on circuits and systems for video technology"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241563"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73417-8_57"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS46320.2019.00040"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00472"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"}],"event":{"name":"MobiHoc '21: The Twenty-second International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing","location":"Shanghai China","acronym":"MobiHoc '21","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the Twenty-second International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3466772.3467037","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3466772.3467037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:57Z","timestamp":1750191537000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3466772.3467037"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,26]]},"references-count":58,"alternative-id":["10.1145\/3466772.3467037","10.1145\/3466772"],"URL":"https:\/\/doi.org\/10.1145\/3466772.3467037","relation":{},"subject":[],"published":{"date-parts":[[2021,7,26]]},"assertion":[{"value":"2021-07-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}