{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T14:56:18Z","timestamp":1773413778855,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":78,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"RGC GRF","award":["14202923"],"award-info":[{"award-number":["14202923"]}]},{"name":"atural Science Foundation of China under Grant","award":["62072117"],"award-info":[{"award-number":["62072117"]}]},{"name":"Shanghai Natural Science Foundation","award":["22ZR1407000"],"award-info":[{"award-number":["22ZR1407000"]}]},{"name":"Natural Science Foundation of China","award":["62001180"],"award-info":[{"award-number":["62001180"]}]},{"name":"Young Elite Scientists Sponsorship Program by CAST","award":["2022QNRC001"],"award-info":[{"award-number":["2022QNRC001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681269","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"7229-7238","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["AxiomVision: Accuracy-Guaranteed Adaptive Visual Model Selection for Perspective-Aware Video Analytics"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0179-196X","authenticated-orcid":false,"given":"Xiangxiang","family":"Dai","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4508-671X","authenticated-orcid":false,"given":"Zeyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8964-0597","authenticated-orcid":false,"given":"Peng","family":"Yang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4168-3998","authenticated-orcid":false,"given":"Yuedong","family":"Xu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8628-5873","authenticated-orcid":false,"given":"Xutong","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7466-0384","authenticated-orcid":false,"given":"John C.S.","family":"Lui","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"March 17","author":"Life K Urban","year":"2024","unstructured":"4K Urban Life. Accessed: March 17, 2024a. 5K Vancouver Downtown 360\u00b0 VR Video - Vancouver Harbourfront, Canada - 1 HR.[Online] https:\/\/www.youtube.com\/watch?v=oeKr9O6z4IU."},{"key":"e_1_3_2_1_2_1","volume-title":"March 17","author":"Life K Urban","year":"2024","unstructured":"4K Urban Life. Accessed: March 17, 2024b. Seattle 5K 360\u00b0 VR Video - Seattle City North Downtown. Part #2. [Online] https:\/\/www.youtube.com\/watch?v=sAMF5BkmO50."},{"key":"e_1_3_2_1_3_1","volume-title":"March 17","author":"Life K Urban","year":"2024","unstructured":"4K Urban Life. Accessed: March 17, 2024c. Seattle Downtown - City Tour 360 VR - 4K Video. Part 1 - 1 HR. [Online] https:\/\/www.youtube.com\/watch?v=Zy2ihEV-ooI."},{"key":"e_1_3_2_1_4_1","volume-title":"March 17","author":"Life K Urban","year":"2024","unstructured":"4K Urban Life. Accessed: March 17, 2024d. Seattle Traffic in 5K 360\u00b0 VR Video - Seattle Highways & Stadiums. [Online] https:\/\/www.youtube.com\/watch?v=znSzP4R_1a8."},{"key":"e_1_3_2_1_5_1","volume-title":"Improved algorithms for linear stochastic bandits. Advances in neural information processing systems","author":"Abbasi-Yadkori Yasin","year":"2011","unstructured":"Yasin Abbasi-Yadkori, D\u00e1vid P\u00e1l, and Csaba Szepesv\u00e1ri. 2011. Improved algorithms for linear stochastic bandits. Advances in neural information processing systems, Vol. 24 (2011), 2312--2320."},{"key":"e_1_3_2_1_6_1","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. 2022. Ekya: Continuous learning of video analytics models on edge compute servers. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). 119--135."},{"key":"e_1_3_2_1_7_1","first-page":"406","article-title":"Scaling video analytics on constrained edge nodes","volume":"1","author":"Canel Christopher","year":"2019","unstructured":"Christopher Canel, Thomas Kim, Giulio Zhou, Conglong Li, Hyeontaek Lim, David G Andersen, Michael Kaminsky, and Subramanya Dulloor. 2019. Scaling video analytics on constrained edge nodes. Proceedings of Machine Learning and Systems, Vol. 1 (2019), 406--417.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems. 155--168","author":"Yu-Han Chen Tiffany","year":"2015","unstructured":"Tiffany Yu-Han Chen, Lenin Ravindranath, Shuo Deng, Paramvir Bahl, and Hari Balakrishnan. 2015. Glimpse: Continuous, real-time object recognition on mobile devices. In Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems. 155--168."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2666805"},{"key":"e_1_3_2_1_10_1","volume-title":"Cost-Effective Online Multi-LLM Selection with Versatile Reward Models. arXiv preprint arXiv:2405.16587","author":"Dai Xiangxiang","year":"2024","unstructured":"Xiangxiang Dai, Jin Li, Xutong Liu, Anqi Yu, and John Lui. 2024. Cost-Effective Online Multi-LLM Selection with Versatile Reward Models. arXiv preprint arXiv:2405.16587 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"Lui","author":"Dai Xiangxiang","year":"2024","unstructured":"Xiangxiang Dai, Zhiyong Wang, Jize Xie, Xutong Liu, and John C.S. Lui. 2024. Conversational Recommendation with Online Learning and Clustering on Misspecified Users. IEEE Transactions on Knowledge and Data Engineering (2024), 1--14."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3162598"},{"key":"e_1_3_2_1_13_1","volume-title":"Conference on Learning Theory.","author":"Dani Varsha","year":"2008","unstructured":"Varsha Dani, Thomas P Hayes, and Sham M Kakade. 2008. Stochastic linear optimization under bandit feedback. In Conference on Learning Theory."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646436"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405887"},{"key":"e_1_3_2_1_16_1","volume-title":"Parametric bandits: The generalized linear case. Advances in neural information processing systems","author":"Filippi Sarah","year":"2010","unstructured":"Sarah Filippi, Olivier Cappe, Aur\u00e9lien Garivier, and Csaba Szepesv\u00e1ri. 2010. Parametric bandits: The generalized linear case. Advances in neural information processing systems, Vol. 23 (2010)."},{"key":"e_1_3_2_1_17_1","volume-title":"International conference on machine learning. PMLR, 757--765","author":"Gentile Claudio","year":"2014","unstructured":"Claudio Gentile, Shuai Li, and Giovanni Zappella. 2014. Online clustering of bandits. In International conference on machine learning. PMLR, 757--765."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458305.3463381"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3355639"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"e_1_3_2_1_21_1","first-page":"1","article-title":"InSS: An Intelligent Scheduling Orchestrator for Multi-GPU Inference with Spatio-Temporal Sharing","volume":"01","author":"Han Ziyi","year":"2024","unstructured":"Ziyi Han, Ruiting Zhou, Chengzhong Xu, Yifan Zeng, and Renli Zhang. 2024. InSS: An Intelligent Scheduling Orchestrator for Multi-GPU Inference with Spatio-Temporal Sharing. IEEE Transactions on Parallel & Distributed Systems 01 (2024), 1--13.","journal-title":"IEEE Transactions on Parallel & Distributed Systems"},{"key":"e_1_3_2_1_22_1","volume-title":"End-Edge Coordinated Joint Encoding and Neural Enhancement for Low-Light Video Analytics. arXiv preprint arXiv:2308.16418","author":"He Yuanyi","year":"2023","unstructured":"Yuanyi He, Peng Yang, Tian Qin, and Ning Zhang. 2023. End-Edge Coordinated Joint Encoding and Neural Enhancement for Low-Light Video Analytics. arXiv preprint arXiv:2308.16418 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098184"},{"key":"e_1_3_2_1_24_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. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/SEC.2018.00016"},{"key":"e_1_3_2_1_26_1","volume-title":"Research Report","author":"Insights Business Research","year":"2020","unstructured":"Business Research Insights. Accessed: 2023--11. Global PTZ Camera Market Research Report 2020. https:\/\/www.businessresearchinsights.com\/market-reports\/ptz-cameras-market-100130."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/SEC50012.2020.00016"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230574"},{"key":"e_1_3_2_1_29_1","unstructured":"Glenn Jocher Ayush Chaurasia Alex Stoken Jirka Borovec Yonghye Kwon Jiacong Fang Kalen Michael Diego Montes Jebastin Nadar Piotr Skalski et al. 2022. ultralytics\/yolov5: v6. 1-TensorRT TensorFlow edge TPU and OpenVINO export and inference. Zenodo (2022)."},{"key":"e_1_3_2_1_30_1","volume-title":"Noscope: optimizing neural network queries over video at scale. arXiv preprint arXiv:1703.02529","author":"Kang Daniel","year":"2017","unstructured":"Daniel Kang, John Emmons, Firas Abuzaid, Peter Bailis, and Matei Zaharia. 2017. Noscope: optimizing neural network queries over video at scale. arXiv preprint arXiv:1703.02529 (2017)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612585"},{"key":"e_1_3_2_1_32_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR","author":"Kveton Branislav","year":"2020","unstructured":"Branislav Kveton, Manzil Zaheer, Csaba Szepesvari, Lihong Li, Mohammad Ghavamzadeh, and Craig Boutilier. 2020. Randomized exploration in generalized linear bandits. In International Conference on Artificial Intelligence and Statistics. PMLR, 2066--2076."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2892818"},{"key":"e_1_3_2_1_34_1","volume-title":"Bandit algorithms","author":"Lattimore Tor","unstructured":"Tor Lattimore and Csaba Szepesv\u00e1ri. 2020. Bandit algorithms. Cambridge University Press."},{"key":"e_1_3_2_1_35_1","volume-title":"Philippe Gentet, Soon Chul Kwon, Kwang Chul Son, and Cheong Ghil Kim.","author":"Lee Seung Hyun","year":"2023","unstructured":"Seung Hyun Lee, Ji Youn Lee, Philippe Gentet, Soon Chul Kwon, Kwang Chul Son, and Cheong Ghil Kim. 2023. Holographic Stereogram Portrait of a Multi-view Camera-based Digital Human. In 2023 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON). IEEE, 378--380."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12493"},{"key":"e_1_3_2_1_37_1","volume-title":"Improved algorithm on online clustering of bandits. arXiv preprint arXiv:1902.09162","author":"Li Shuai","year":"2019","unstructured":"Shuai Li, Wei Chen, and Kwong-Sak Leung. 2019. Improved algorithm on online clustering of bandits. arXiv preprint arXiv:1902.09162 (2019)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11763"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.3390\/app8091678"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405874"},{"key":"e_1_3_2_1_41_1","volume-title":"Learning-Based Query Scheduling and Resource Allocation for Low-Latency Mobile Edge Video Analytics","author":"Lin Jie","year":"2023","unstructured":"Jie Lin, Peng Yang, Wen Wu, Ning Zhang, Tao Han, and Li Yu. 2023. Learning-Based Query Scheduling and Resource Allocation for Low-Latency Mobile Edge Video Analytics. IEEE Internet of Things Journal (2023)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3181986"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings, Part I 14","author":"Liu Wei","year":"2016","unstructured":"Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg. 2016. Ssd: Single shot multibox detector. In Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part I 14. Springer, 21--37."},{"key":"e_1_3_2_1_44_1","unstructured":"Xutong Liu Haoru Zhao Tong Yu Shuai Li and John CS Lui. 2022. Federated online clustering of bandits. In Uncertainty in Artificial Intelligence. PMLR 1221--1231."},{"key":"e_1_3_2_1_45_1","volume-title":"International Conference on Machine Learning. PMLR, 22559--22593","author":"Liu Xutong","year":"2023","unstructured":"Xutong Liu, Jinhang Zuo, Siwei Wang, John CS Lui, Mohammad Hajiesmaili, Adam Wierman, and Wei Chen. 2023. Contextual combinatorial bandits with probabilistically triggered arms. In International Conference on Machine Learning. PMLR, 22559--22593."},{"key":"e_1_3_2_1_46_1","volume-title":"Variance-Adaptive Algorithm for Probabilistic Maximum Coverage Bandits with General Feedback. In IEEE INFOCOM 2023-IEEE Conference on Computer Communications. IEEE, 1--10","author":"Liu Xutong","year":"2023","unstructured":"Xutong Liu, Jinhang Zuo, Hong Xie, Carlee Joe-Wong, and John CS Lui. 2023. Variance-Adaptive Algorithm for Probabilistic Maximum Coverage Bandits with General Feedback. In IEEE INFOCOM 2023-IEEE Conference on Computer Communications. IEEE, 1--10."},{"key":"e_1_3_2_1_47_1","unstructured":"Yi Liu Lutao Chu Guowei Chen Zewu Wu Zeyu Chen Baohua Lai and Yuying Hao. 2021. PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation. arxiv: 2101.06175 [cs.CV]"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2003.815297"},{"key":"e_1_3_2_1_50_1","volume-title":"Rtmdet: An empirical study of designing real-time object detectors. arXiv preprint arXiv:2212.07784","author":"Lyu Chengqi","year":"2022","unstructured":"Chengqi Lyu, Wenwei Zhang, Haian Huang, Yue Zhou, Yudong Wang, Yanyi Liu, Shilong Zhang, and Kai Chen. 2022. Rtmdet: An empirical study of designing real-time object detectors. arXiv preprint arXiv:2212.07784 (2022)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934890"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920979368"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413618"},{"key":"e_1_3_2_1_54_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.03.039"},{"key":"e_1_3_2_1_56_1","volume-title":"March 12","year":"2024","unstructured":"SeeJH.com. Accessed: March 12, 2024 a. Jackson Hole Wyoming USA Town Square Live Cam. [Online] https:\/\/www.youtube.com\/watch?v=1EiC9bvVGnk."},{"key":"e_1_3_2_1_57_1","volume-title":"March 12","year":"2024","unstructured":"SeeJH.com. Accessed: March 12, 2024 b. Jackson Town Square Cache Street @ Roadhouse Pub. [Online] https:\/\/www.youtube.com\/watch?v=FmoclK_hKz8."},{"key":"e_1_3_2_1_58_1","volume-title":"March 12","year":"2024","unstructured":"SeeJH.com. Accessed: March 12, 2024 c. Jackson Town Square Live PTZ webcam. [Online] https:\/\/www.youtube.com\/watch?v=BN7gzH-i-zo."},{"key":"e_1_3_2_1_59_1","volume-title":"March 12","year":"2024","unstructured":"SeeJH.com. Accessed: March 12, 2024 d. Town Square Webcam. [Online] https:\/\/www.youtube.com\/watch?v=Zj0pXlq2-jI."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359658"},{"key":"e_1_3_2_1_61_1","volume-title":"International conference on machine learning. PMLR, 6105--6114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105--6114."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3180801"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26225"},{"key":"e_1_3_2_1_64_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Zhiyong","year":"2024","unstructured":"Zhiyong Wang, Jize Xie, Xutong Liu, Shuai Li, and John Lui. 2024. Online clustering of bandits with misspecified user models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_65_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Zhiyong","year":"2024","unstructured":"Zhiyong Wang, Jize Xie, Tong Yu, Shuai Li, and John Lui. 2024. Online corrupted user detection and regret minimization. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_66_1","volume-title":"MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Wong Mike","year":"2024","unstructured":"Mike Wong, Murali Ramanujam, Guha Balakrishnan, and Ravi Netravali. 2024. MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 549--568."},{"key":"e_1_3_2_1_67_1","volume-title":"Ilcas: Imitation learning-based configuration-adaptive streaming for live video analytics with cross-camera collaboration","author":"Wu Duo","year":"2023","unstructured":"Duo Wu, Dayou Zhang, Miao Zhang, Ruoyu Zhang, Fangxin Wang, and Shuguang Cui. 2023. Ilcas: Imitation learning-based configuration-adaptive streaming for live video analytics with cross-camera collaboration. IEEE Transactions on Mobile Computing (2023)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2949347"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2870521"},{"key":"e_1_3_2_1_70_1","volume-title":"Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"You Jie","year":"2023","unstructured":"Jie You, Jae-Won Chung, and Mosharaf Chowdhury. 2023. Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 119--139."},{"key":"e_1_3_2_1_71_1","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. 2017. Live video analytics at scale with approximation and Delay-Tolerance. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). 377--392."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450051"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796875"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"e_1_3_2_1_75_1","volume-title":"EdgeAdaptor: Online Configuration Adaption, Model Selection and Resource Provisioning for Edge DNN Inference Serving at Scale","author":"Zhao Kongyange","year":"2022","unstructured":"Kongyange Zhao, Zhi Zhou, Xu Chen, Ruiting Zhou, Xiaoxi Zhang, Shuai Yu, and Di Wu. 2022. EdgeAdaptor: Online Configuration Adaption, Model Selection and Resource Provisioning for Edge DNN Inference Serving at Scale. IEEE Transactions on Mobile Computing (2022)."},{"key":"e_1_3_2_1_76_1","volume-title":"Scheduling Generative-AI DAGs with Model Serving in Data Centers. In IEEE\/ACM International Symposium on Quality of Service.","author":"Zheng Ying","year":"2024","unstructured":"Ying Zheng, Lei Jiao, Yuedong Xu, Bo An, Xin Wang, and Zongpeng Li. 2024. Scheduling Generative-AI DAGs with Model Serving in Data Centers. In IEEE\/ACM International Symposium on Quality of Service."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10279708"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3360077"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681269","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681269","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:42Z","timestamp":1750295862000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681269"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":78,"alternative-id":["10.1145\/3664647.3681269","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681269","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}