{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T15:33:13Z","timestamp":1759937593891,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":95,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T00:00:00Z","timestamp":1698624000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2146496,2131826,2313190,1901466"],"award-info":[{"award-number":["2146496,2131826,2313190,1901466"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,30]]},"DOI":"10.1145\/3620678.3624653","type":"proceedings-article","created":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T13:58:07Z","timestamp":1698760687000},"page":"158-176","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["OneAdapt"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3964-4079","authenticated-orcid":false,"given":"Kuntai","family":"Du","sequence":"first","affiliation":[{"name":"University of Chicago"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5957-5071","authenticated-orcid":false,"given":"Yuhan","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Chicago"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4330-1228","authenticated-orcid":false,"given":"Yitian","family":"Hao","sequence":"additional","affiliation":[{"name":"University of Chicago"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3208-4601","authenticated-orcid":false,"given":"Qizheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7459-5893","authenticated-orcid":false,"given":"Haodong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Chicago"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8822-3115","authenticated-orcid":false,"given":"Yuyang","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Chicago"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7479-1664","authenticated-orcid":false,"given":"Ganesh","family":"Ananthanarayanan","sequence":"additional","affiliation":[{"name":"Microsoft Research"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6877-1683","authenticated-orcid":false,"given":"Junchen","family":"Jiang","sequence":"additional","affiliation":[{"name":"University of Chicago"}]}],"member":"320","published-online":{"date-parts":[[2023,10,31]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"1 000-meter autonomous truck perception system - tusimple. https:\/\/www.tusimple.com\/blogs\/tusimple-1000-meter-perception-system\/. (Accessed on 09\/14\/2022)."},{"key":"e_1_3_2_1_2_1","unstructured":"Audioset. http:\/\/research.google.com\/audioset\/index.html. (Accessed on 02\/09\/2023)."},{"key":"e_1_3_2_1_3_1","unstructured":"The best frame rate for video. https:\/\/photographylife.com\/best-frame-rate-for-video. (Accessed on 09\/22\/2023)."},{"key":"e_1_3_2_1_4_1","unstructured":"Chameleon projects. https:\/\/www.chameleonprojects.com\/. (Accessed on 09\/29\/2023)."},{"key":"e_1_3_2_1_5_1","unstructured":"End-to-end deep learning for self-driving cars | nvidia technical blog. https:\/\/developer.nvidia.com\/blog\/deep-learning-self-driving-cars\/. (Accessed on 06\/09\/2023)."},{"key":"e_1_3_2_1_6_1","unstructured":"Enhancing smart-home experiences with ai-based voice control | electronic design. https:\/\/www.electronicdesign.com\/technologies\/embedded\/article\/21252996\/knowles-electronics-enhancing-smarthome-experiences-with-aibased-voice-control. (Accessed on 09\/24\/2023)."},{"key":"e_1_3_2_1_7_1","unstructured":"fairseq\/readme.md at main \u00b7 facebookresearch\/fairseq \u00b7 github. https:\/\/github.com\/facebookresearch\/fairseq\/blob\/main\/examples\/wav2vec\/README.md. (Accessed on 02\/09\/2023)."},{"key":"e_1_3_2_1_8_1","unstructured":"Jpeg - wikipedia. https:\/\/en.wikipedia.org\/wiki\/JPEG. (Accessed on 09\/26\/2023)."},{"key":"e_1_3_2_1_9_1","unstructured":"Kuntaidu\/oneadapt. https:\/\/github.com\/KuntaiDu\/OneAdapt. (Accessed on 09\/29\/2023)."},{"key":"e_1_3_2_1_10_1","unstructured":"lec19.pdf. https:\/\/www.cs.princeton.edu\/courses\/archive\/fall13\/cos521\/lecnotes\/lec19.pdf. (Accessed on 06\/09\/2023)."},{"key":"e_1_3_2_1_11_1","unstructured":"Microsoft rocket video analytics platform. https:\/\/github.com\/microsoft\/Microsoft-Rocket-Video-Analytics-Platform."},{"key":"e_1_3_2_1_12_1","unstructured":"Modified discrete cosine transform - wikipedia. https:\/\/en.wikipedia.org\/wiki\/Modified_discrete_cosine_transform. (Accessed on 09\/26\/2023)."},{"key":"e_1_3_2_1_13_1","unstructured":"Mta to install security cameras in nyc subway cars -- nbc new york. https:\/\/www.nbcnewyork.com\/news\/local\/mta-to-install-security-cameras-in-nyc-subway\/-cars-to-deter-crime\/3872485\/. (Accessed on 09\/20\/2022)."},{"key":"e_1_3_2_1_14_1","unstructured":"New york to install surveillance cameras in every subway car. https:\/\/www.nbcnews.com\/tech\/tech-news\/new-york-subway-cameras-surveillance-mta-train-\/cars-hochul-rcna48582. (Accessed on 09\/20\/2022)."},{"key":"e_1_3_2_1_15_1","unstructured":"nsdi17-alipourfard.pdf. https:\/\/www.usenix.org\/system\/files\/conference\/nsdi17\/nsdi17-alipourfard.pdf. (Accessed on 09\/24\/2023)."},{"key":"e_1_3_2_1_16_1","unstructured":"N.y.c. subway system to install security cameras in train cars - the new york times. https:\/\/www.nytimes.com\/2022\/09\/20\/nyregion\/nyc-subway-security-cameras.html. (Accessed on 09\/20\/2022)."},{"key":"e_1_3_2_1_17_1","unstructured":"OneAdapt: Driving Videos --- docs.google.com. https:\/\/docs.google.com\/spreadsheets\/d\/1KwRDkt2B7h_WemrK5K86MRz6_Y1czK3bz9u4kBnhvk4. [Accessed 02\/15\/2023]."},{"key":"e_1_3_2_1_18_1","unstructured":"Oneadapt proof on numerical gradient case - google docs. https:\/\/docs.google.com\/document\/d\/1zSISyfzBirW0kD6hc-lWpj4ykhodobhnPlBQh_T3bBA\/edit?usp=sharing. (Accessed on 09\/29\/2023)."},{"key":"e_1_3_2_1_19_1","unstructured":"Pytorch_yolov3\/yolov3.py at master \u00b7 dena\/pytorch_yolov3 \u00b7 github. https:\/\/github.com\/DeNA\/PyTorch_YOLOv3\/blob\/master\/models\/yolov3.py. (Accessed on 02\/09\/2023)."},{"key":"e_1_3_2_1_20_1","unstructured":"Top 10 smart home voice control devices | home matters | ahs. https:\/\/www.ahs.com\/home-matters\/tech\/smart-home-voice-control-devices\/. (Accessed on 09\/24\/2023)."},{"key":"e_1_3_2_1_21_1","unstructured":"Video coding for machines (the moving picture experts group). https:\/\/mpeg.chiariglione.org\/standards\/exploration\/video-coding-machines."},{"key":"e_1_3_2_1_22_1","unstructured":"Vision navigates obstacles on the road to autonomous vehicles | automate. https:\/\/www.automate.org\/industry-insights\/vision-navigates-obstacles-on-the-road-to-autonomous-vehicles. (Accessed on 06\/09\/2023)."},{"key":"e_1_3_2_1_23_1","unstructured":"Voice control in the smart \/ connected home what you need to know. https:\/\/htacertified.org\/app\/articles\/voice-control-in-the-smart-home\/. (Accessed on 09\/24\/2023)."},{"key":"e_1_3_2_1_24_1","unstructured":"Waymo datase. https:\/\/waymo.com\/open\/."},{"key":"e_1_3_2_1_25_1","unstructured":"x264 ffmpeg options guide - linux encoding. https:\/\/sites.google.com\/site\/linuxencoding\/x264-ffmpeg-mapping. (Accessed on 09\/10\/2022)."},{"key":"e_1_3_2_1_26_1","first-page":"933","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Agarwal Neil","year":"2023","unstructured":"Neil Agarwal and Ravi Netravali. Boggart: Towards {General-Purpose} acceleration of retrospective video analytics. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23), pages 933--951, 2023."},{"key":"e_1_3_2_1_27_1","volume-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems, 33:12449--12460","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems, 33:12449--12460, 2020."},{"key":"e_1_3_2_1_28_1","first-page":"119","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Bhardwaj Romil","year":"2022","unstructured":"Romil Bhardwaj, Zhengxu Xia, Ganesh Ananthanarayanan, Junchen Jiang, Yuanchao Shu, Nikolaos Karianakis, Kevin Hsieh, Paramvir Bahl, and Ion Stoica. Ekya: Continuous learning of video analytics models on edge compute servers. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22), pages 119--135, 2022."},{"key":"e_1_3_2_1_29_1","volume-title":"Scaling video analytics on constrained edge nodes. arXiv preprint arXiv:1905.13536","author":"Canel Christopher","year":"2019","unstructured":"Christopher Canel, Thomas Kim, Giulio Zhou, Conglong Li, Hyeontaek Lim, David G Andersen, Michael Kaminsky, and Subramanya R Dulloor. Scaling video analytics on constrained edge nodes. arXiv preprint arXiv:1905.13536, 2019."},{"key":"e_1_3_2_1_30_1","first-page":"32","article-title":"Backprop with approximate activations for memory-efficient network training","author":"Chakrabarti Ayan","year":"2019","unstructured":"Ayan Chakrabarti and Benjamin Moseley. Backprop with approximate activations for memory-efficient network training. Advances in Neural Information Processing Systems, 32, 2019.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_31_1","volume-title":"Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174","author":"Chen Tianqi","year":"2016","unstructured":"Tianqi Chen, Bing Xu, Chiyuan Zhang, and Carlos Guestrin. Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174, 2016."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2809695.2809711"},{"key":"e_1_3_2_1_33_1","first-page":"5","article-title":"The fully reversible bidirectional feature pyramid network","author":"Chiley Vitaliy","year":"2023","unstructured":"Vitaliy Chiley, Vithursan Thangarasa, Abhay Gupta, Anshul Samar, Joel Hestness, and Dennis DeCoste. Revbifpn: The fully reversible bidirectional feature pyramid network. Proceedings of Machine Learning and Systems, 5, 2023.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_34_1","volume-title":"Adascale: Towards real-time video object detection using adaptive scaling. arXiv preprint arXiv:1902.02910","author":"Chin Ting-Wu","year":"2019","unstructured":"Ting-Wu Chin, Ruizhou Ding, and Diana Marculescu. Adascale: Towards real-time video object detection using adaptive scaling. arXiv preprint arXiv:1902.02910, 2019."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-015-0709-9"},{"key":"e_1_3_2_1_36_1","volume-title":"Convergence rates of gradient methods for convex optimization in the space of measures. arXiv preprint arXiv:2105.08368","author":"Chizat L\u00e9na\u00efc","year":"2021","unstructured":"L\u00e9na\u00efc Chizat. Convergence rates of gradient methods for convex optimization in the space of measures. arXiv preprint arXiv:2105.08368, 2021."},{"key":"e_1_3_2_1_37_1","volume-title":"Pkummd: A large scale benchmark for continuous multi-modal human action understanding. arXiv preprint arXiv:1703.07475","author":"Chunhui Liu","year":"2017","unstructured":"Liu Chunhui, Hu Yueyu, Li Yanghao, Song Sijie, and Liu Jiaying. Pkummd: A large scale benchmark for continuous multi-modal human action understanding. arXiv preprint arXiv:1703.07475, 2017."},{"key":"e_1_3_2_1_38_1","volume-title":"265 and iso","author":"Video Coding High Efficiency","year":"2013","unstructured":"High Efficiency Video Coding and ITUT Rec. H. 265 and iso, 2013."},{"key":"e_1_3_2_1_39_1","volume-title":"Exponential regret bounds for gaussian process bandits with deterministic observations. arXiv preprint arXiv:1206.6457","author":"Freitas Nando De","year":"2012","unstructured":"Nando De Freitas, Alex Smola, and Masrour Zoghi. Exponential regret bounds for gaussian process bandits with deterministic observations. arXiv preprint arXiv:1206.6457, 2012."},{"key":"e_1_3_2_1_40_1","unstructured":"Detectron2. Detectron2 model zoo. https:\/\/github.com\/facebookresearch\/detectron2."},{"key":"e_1_3_2_1_41_1","first-page":"343","volume-title":"15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18)","author":"Dong Mo","year":"2018","unstructured":"Mo Dong, Tong Meng, Doron Zarchy, Engin Arslan, Yossi Gilad, Brighten Godfrey, and Michael Schapira. {PCC} vivace:{Online-Learning} congestion control. In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18), pages 343--356, 2018."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405887"},{"key":"e_1_3_2_1_43_1","first-page":"4","article-title":"Optimizing video encoding for accurate video analytics","author":"Du Kuntai","year":"2022","unstructured":"Kuntai Du, Qizheng Zhang, Anton Arapin, Haodong Wang, Zhengxu Xia, and Junchen Jiang. Accmpeg: Optimizing video encoding for accurate video analytics. Proceedings of Machine Learning and Systems, 4, 2022.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415048"},{"key":"e_1_3_2_1_45_1","volume-title":"Adam Tauman Kalai, and H Brendan McMahan. Online convex optimization in the bandit setting: gradient descent without a gradient. arXiv preprint cs\/0408007","author":"Flaxman Abraham D","year":"2004","unstructured":"Abraham D Flaxman, Adam Tauman Kalai, and H Brendan McMahan. Online convex optimization in the bandit setting: gradient descent without a gradient. arXiv preprint cs\/0408007, 2004."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2886739"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.treng.2022.100115"},{"key":"e_1_3_2_1_49_1","volume-title":"The reversible residual network: Backpropagation without storing activations. Advances in neural information processing systems, 30","author":"Gomez Aidan N","year":"2017","unstructured":"Aidan N Gomez, Mengye Ren, Raquel Urtasun, and Roger B Grosse. The reversible residual network: Backpropagation without storing activations. Advances in neural information processing systems, 30, 2017."},{"volume-title":"Goodvision: Smart traffic data analytics. https:\/\/goodvisionlive.com\/","year":"2021","key":"e_1_3_2_1_50_1","unstructured":"GoodVision. Goodvision: Smart traffic data analytics. https:\/\/goodvisionlive.com\/, 2021."},{"key":"e_1_3_2_1_51_1","volume-title":"Memory-efficient backpropagation through time. Advances in neural information processing systems, 29","author":"Gruslys Audrunas","year":"2016","unstructured":"Audrunas Gruslys, R\u00e9mi Munos, Ivo Danihelka, Marc Lanctot, and Alex Graves. Memory-efficient backpropagation through time. Advances in neural information processing systems, 29, 2016."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2906388.2906396"},{"key":"e_1_3_2_1_53_1","volume-title":"Prajit Ramachandran, Mohammad Babaeizadeh, Honghui Shi, Jianan Li, Shuicheng Yan, and Thomas S Huang. Seq-nms for video object detection. arXiv preprint arXiv:1602.08465","author":"Han Wei","year":"2016","unstructured":"Wei Han, Pooya Khorrami, Tom Le Paine, Prajit Ramachandran, Mohammad Babaeizadeh, Honghui Shi, Jianan Li, Shuicheng Yan, and Thomas S Huang. Seq-nms for video object detection. arXiv preprint arXiv:1602.08465, 2016."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-434"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/JCSSE.2016.7748895"},{"key":"e_1_3_2_1_57_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_58_1","volume-title":"Spoken Language Processing: A Guide to Theory, Algorithm, and System Development","author":"Huang Xuedong","year":"2001","unstructured":"Xuedong Huang, Alex Acero, Hsiao-Wuen Hon, and Raj Reddy. Spoken Language Processing: A Guide to Theory, Algorithm, and System Development. Prentice Hall PTR, USA, 1st edition, 2001.","edition":"1"},{"volume-title":"intuvision va traffic use case. https:\/\/www.intuvisiontech.com\/intuvisionVA_solutions\/intuvisionVA_traffic","year":"2021","key":"e_1_3_2_1_59_1","unstructured":"intuVision. intuvision va traffic use case. https:\/\/www.intuvisiontech.com\/intuvisionVA_solutions\/intuvisionVA_traffic, 2021."},{"key":"e_1_3_2_1_60_1","volume-title":"Experimental investigation on stft phase representations for deep learning-based dysarthric speech detection","author":"Janbakhshi Parvaneh","year":"2021","unstructured":"Parvaneh Janbakhshi and Ina Kodrasi. Experimental investigation on stft phase representations for deep learning-based dysarthric speech detection, 2021."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230574"},{"key":"e_1_3_2_1_62_1","volume-title":"Blazeit: optimizing declarative aggregation and limit queries for neural network-based video analytics. arXiv preprint arXiv:1805.01046","author":"Kang Daniel","year":"2018","unstructured":"Daniel Kang, Peter Bailis, and Matei Zaharia. Blazeit: optimizing declarative aggregation and limit queries for neural network-based video analytics. arXiv preprint arXiv:1805.01046, 2018."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137664"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093336.3037698"},{"key":"e_1_3_2_1_65_1","volume-title":"Bayesian optimization with exponential convergence. Advances in neural information processing systems, 28","author":"Kawaguchi Kenji","year":"2015","unstructured":"Kenji Kawaguchi, Leslie P Kaelbling, and Tom\u00e1s Lozano-P\u00e9rez. Bayesian optimization with exponential convergence. Advances in neural information processing systems, 28, 2015."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405874"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3300116"},{"key":"e_1_3_2_1_68_1","first-page":"14139","volume-title":"International Conference on Machine Learning","author":"Liu Xiaoxuan","year":"2022","unstructured":"Xiaoxuan Liu, Lianmin Zheng, Dequan Wang, Yukuo Cen, Weize Chen, Xu Han, Jianfei Chen, Zhiyuan Liu, Jie Tang, Joey Gonzalez, et al. Gact: Activation compressed training for generic network architectures. In International Conference on Machine Learning, pages 14139--14152. PMLR, 2022."},{"volume-title":"Traffic video analytics -- case study report. https:\/\/www.microsoft.com\/en-us\/research\/publication\/traffic-video-analytics-case-study-report\/","year":"2019","key":"e_1_3_2_1_69_1","unstructured":"Microsoft. Traffic video analytics -- case study report. https:\/\/www.microsoft.com\/en-us\/research\/publication\/traffic-video-analytics-case-study-report\/, 2019."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-012-0629-5"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.479"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1515\/dma.2011.029"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485905"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_3_2_1_76_1","first-page":"91","volume-title":"Advances in neural information processing systems","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems, pages 91--99, 2015."},{"key":"e_1_3_2_1_77_1","volume-title":"Convergence rates of inexact proximal-gradient methods for convex optimization. Advances in neural information processing systems, 24","author":"Schmidt Mark","year":"2011","unstructured":"Mark Schmidt, Nicolas Roux, and Francis Bach. Convergence rates of inexact proximal-gradient methods for convex optimization. Advances in neural information processing systems, 24, 2011."},{"volume-title":"Ai traffic video analytics platform being developed. https:\/\/www.traffictechnologytoday.com\/news\/traffic-management\/ai-traffic-video-analytics-platform-being-developed.html","year":"2019","key":"e_1_3_2_1_78_1","unstructured":"TrafficTechnologyToday. Ai traffic video analytics platform being developed. https:\/\/www.traffictechnologytoday.com\/news\/traffic-management\/ai-traffic-video-analytics-platform-being-developed.html, 2019."},{"key":"e_1_3_2_1_79_1","unstructured":"TrafficVision. Trafficvision: Traffic intelligence from video. http:\/\/www.trafficvision.com\/ 2021."},{"key":"e_1_3_2_1_80_1","unstructured":"VisionZero. The vision zero initiative. http:\/\/www.visionzeroinitiative.com\/."},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563502"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544243"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796657"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3013234"},{"key":"e_1_3_2_1_86_1","first-page":"148","volume-title":"2021 IEEE\/ACM Symposium on Edge Computing (SEC)","author":"Xiao Zhujun","year":"2021","unstructured":"Zhujun Xiao, Zhengxu Xia, Haitao Zheng, Ben Y Zhao, and Junchen Jiang. Towards performance clarity of edge video analytics. In 2021 IEEE\/ACM Symposium on Edge Computing (SEC), pages 148--164. IEEE, 2021."},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519577"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303971"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230554"},{"key":"e_1_3_2_1_90_1","volume-title":"Operations Research","author":"Zhang Haixiang","year":"2022","unstructured":"Haixiang Zhang, Zeyu Zheng, and Javad Lavaei. Gradient-based algorithms for convex discrete optimization via simulation. Operations Research, 2022."},{"key":"e_1_3_2_1_91_1","first-page":"377","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Zhang Haoyu","year":"2017","unstructured":"Haoyu Zhang, Ganesh Ananthanarayanan, Peter Bodik, Matthai Philipose, Paramvir Bahl, and Michael J Freedman. Live video analytics at scale with approximation and {Delay-Tolerance}. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17), pages 377--392, 2017."},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796875"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1145\/3508396.3512872"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1145\/2789168.2790123"},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3448628"}],"event":{"name":"SoCC '23: ACM Symposium on Cloud Computing","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGOPS ACM Special Interest Group on Operating Systems"],"location":"Santa Cruz CA USA","acronym":"SoCC '23"},"container-title":["Proceedings of the 2023 ACM Symposium on Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620678.3624653","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3620678.3624653","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:53:08Z","timestamp":1755877988000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620678.3624653"}},"subtitle":["Fast Adaptation for Deep Learning Applications via Backpropagation"],"short-title":[],"issued":{"date-parts":[[2023,10,30]]},"references-count":95,"alternative-id":["10.1145\/3620678.3624653","10.1145\/3620678"],"URL":"https:\/\/doi.org\/10.1145\/3620678.3624653","relation":{},"subject":[],"published":{"date-parts":[[2023,10,30]]},"assertion":[{"value":"2023-10-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}