{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T06:33:13Z","timestamp":1790749993556,"version":"4.1.0"},"reference-count":68,"publisher":"Association for Computing Machinery (ACM)","issue":"3","funder":[{"DOI":"10.13039\/501100006374","name":"NSF","doi-asserted-by":"publisher","award":["2238431, 2335881"],"award-info":[{"award-number":["2238431, 2335881"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2025,6,17]]},"abstract":"<jats:p>Query optimization is critical in relational database management systems (DBMSs) for ensuring efficient query processing. The query optimizer relies on precise selectivity and cost estimates to generate optimal query plans for execution. However, this static query optimization approach falls short for DBMSs handling machine learning (ML) queries. ML-centric DBMSs face distinct challenges in query optimization. First, performance bottlenecks shift to user-defined functions (UDFs), often encapsulating deep learning models, making it difficult to estimate UDF statistics without profiling the query. Second, optimal query plans for ML queries are data-dependent, requiring dynamic plan adjustments during execution.<\/jats:p>\n                  <jats:p>To address these challenges, we introduce Aero, an ML-centric DBMS that utilizes adaptive query processing (AQP) for efficiently processing ML queries. Aero optimizes the evaluation of UDF-based query predicates by dynamically adjusting predicate evaluation order and enhancing UDF execution scalability. By integrating AQP, Aero continuously monitors UDF statistics, routes data to predicates in an optimal order, and dynamically allocates resources for evaluating predicates. Aero achieves up to 6.4x speedup compared to a state-of-the-art ML-centric DBMS across four diverse use cases, with no impact on accuracy.<\/jats:p>","DOI":"10.1145\/3725408","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T21:22:29Z","timestamp":1750281749000},"page":"1-27","source":"Crossref","is-referenced-by-count":3,"title":["Aero: Adaptive Query Processing of ML Queries"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2750-5052","authenticated-orcid":false,"given":"Gaurav Tarlok","family":"Kakkar","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0079-2146","authenticated-orcid":false,"given":"Jiashen","family":"Cao","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0390-2615","authenticated-orcid":false,"given":"Aubhro","family":"Sengupta","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7706-6978","authenticated-orcid":false,"given":"Joy","family":"Arulraj","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6061-7825","authenticated-orcid":false,"given":"Hyesoon","family":"Kim","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology Tech, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"Introduction to Discrete Event Systems, Christos G","unstructured":"2008. Introduction to Queueing Theory. In Introduction to Discrete Event Systems, Christos G. Cassandras and St\u00e9phane Lafortune (Eds.). Springer US, 429--497."},{"key":"e_1_2_2_2_1","unstructured":"2017. Wayback Machine. https:\/\/web.archive.org\/web\/20170430085805\/https:\/\/f5.com\/Portals\/1\/Cache\/Pdfs\/2421\/load-balancing-101-nuts-and-bolts-.pdf"},{"key":"e_1_2_2_3_1","unstructured":"2024. NVIDIA Multi-Instance GPU User Guide. https:\/\/docs.nvidia.com\/datacenter\/tesla\/mig-user-guide\/"},{"key":"e_1_2_2_4_1","unstructured":"2024. NVIDIA Multi-Process Service. https:\/\/docs.nvidia.com\/deploy\/mps\/"},{"key":"e_1_2_2_5_1","unstructured":"2024. Using Third-Party Packages. https:\/\/docs.snowflake.com\/en\/developer-guide\/udf\/python\/udf-python-packages"},{"key":"e_1_2_2_6_1","volume-title":"Queueing theory","author":"Adan Ivo","year":"2002","unstructured":"Ivo Adan and Jacques Resing. 2002. Queueing theory. Eindhoven University of Technology 180 (2002)."},{"key":"e_1_2_2_7_1","unstructured":"Yuvanesh Anand Zach Nussbaum Brandon Duderstadt Benjamin Schmidt and Andriy Mulyar. 2023. GPT4All: Training an Assistant-style Chatbot with Large Scale Data Distillation from GPT-3.5-Turbo. https:\/\/github.com\/nomic-ai\/gpt4all."},{"key":"e_1_2_2_8_1","volume-title":"Wenisch","author":"Anderson Michael R.","year":"2019","unstructured":"Michael R. Anderson, Michael Cafarella, German Ros, and Thomas F. Wenisch. 2019. Physical Representation-Based Predicate Optimization for a Visual Analytics Database. In ICDE. 1466--1477."},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335420"},{"key":"e_1_2_2_10_1","doi-asserted-by":"crossref","unstructured":"Shivnath Babu Pedro Bizarro and David DeWitt. 2005. Proactive re-optimization. In SIGMOD. 107--118.","DOI":"10.1145\/1066157.1066171"},{"key":"e_1_2_2_11_1","volume-title":"Pramod Chunduri, Subrata Mitra, and Joy Arulraj.","author":"Bang Jaeho","year":"2023","unstructured":"Jaeho Bang, Gaurav Tarlok Kakkar, Pramod Chunduri, Subrata Mitra, and Joy Arulraj. 2023. Seiden: Revisiting Query Processing in Video Database Systems. PVLDB (2023), 2289--2301."},{"key":"e_1_2_2_12_1","volume-title":"MIRIS: Fast Object Track Queries in Video. In SIGMOD. 1907--1921.","author":"Bastani Favyen","year":"2020","unstructured":"Favyen Bastani, Songtao He, Arjun Balasingam, Karthik Gopalakrishnan, Mohammad Alizadeh, Hari Balakrishnan, Michael Cafarella, Tim Kraska, and Sam Madden. 2020. MIRIS: Fast Object Track Queries in Video. In SIGMOD. 1907--1921."},{"key":"e_1_2_2_13_1","volume-title":"Content-Based Routing: Different Plans for Different Data. PVLDB","author":"Bizarro Pedro","year":"2005","unstructured":"Pedro Bizarro, Shivnath Babu, David DeWitt, and Jennifer Widom. 2005. Content-Based Routing: Different Plans for Different Data. PVLDB (2005)."},{"key":"e_1_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Jiashen Cao Karan Sarkar Ramyad Hadidi Joy Arulraj and Hyesoon Kim. 2022. FiGO: Fine-Grained Query Optimization in Video Analytics. In SIGMOD. 559--572.","DOI":"10.1145\/3514221.3517857"},{"key":"e_1_2_2_15_1","volume-title":"Spatial and Temporal Constrained Ranked Retrieval over Videos. PVLDB","author":"Chen Yueting","year":"2022","unstructured":"Yueting Chen, Nick Koudas, Xiaohui Yu, and Ziqiang Yu. 2022. Spatial and Temporal Constrained Ranked Retrieval over Videos. PVLDB (2022), 3226--3239."},{"key":"e_1_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Yueting Chen Xiaohui Yu and Nick Koudas. 2022. Ranked Window Query Retrieval over Video Repositories. In ICDE. 2776--2791.","DOI":"10.1109\/ICDE53745.2022.00253"},{"key":"e_1_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Yueting Chen Xiaohui Yu Nick Koudas and Ziqiang Yu. 2021. Evaluating Temporal Queries Over Video Feeds. In SIGMOD. 287--299.","DOI":"10.1145\/3448016.3452803"},{"key":"e_1_2_2_18_1","unstructured":"Seungbeom Choi Sunho Lee Yeonjae Kim Jongse Park Youngjin Kwon and Jaehyuk Huh. 2022. Serving Heterogeneous Machine Learning Models on Multi-GPU Servers with Spatio-Temporal Sharing. In ATC. 199--216."},{"key":"e_1_2_2_19_1","volume-title":"Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning. In SIGMOD. 545--558.","author":"Chunduri Pramod","year":"2022","unstructured":"Pramod Chunduri, Jaeho Bang, Yao Lu, and Joy Arulraj. 2022. Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning. In SIGMOD. 545--558."},{"key":"e_1_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Daniel Crankshaw Gur-Eyal Sela Xiangxi Mo Corey Zumar Ion Stoica Joseph Gonzalez and Alexey Tumanov. 2020. InferLine: latency-aware provisioning and scaling for prediction serving pipelines. In SoCC. 477--491.","DOI":"10.1145\/3419111.3421285"},{"key":"e_1_2_2_21_1","volume-title":"Clipper: A Low-Latency Online Prediction Serving System.","author":"Crankshaw Daniel","year":"2017","unstructured":"Daniel Crankshaw, Xin Wang, Guilio Zhou, Michael J. Franklin, Joseph E. Gonzalez, and Ion Stoica. 2017. Clipper: A Low-Latency Online Prediction Serving System. (2017), 613--627."},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781601980359"},{"key":"e_1_2_2_23_1","doi-asserted-by":"crossref","unstructured":"Aditya Dhakal Sameer G Kulkarni and K. K. Ramakrishnan. 2020. GSLICE: controlled spatial sharing of GPUs for a scalable inference platform. In SoCC. 492--506.","DOI":"10.1145\/3419111.3421284"},{"key":"e_1_2_2_24_1","unstructured":"Jocher Glenn. 2020. YOLOv5 by Ultralytics. https:\/\/github.com\/ultralytics\/yolov5"},{"key":"e_1_2_2_25_1","unstructured":"Arpan Gujarati Reza Karimi Safya Alzayat Wei Hao Antoine Kaufmann Ymir Vigfusson and Jonathan Mace. 2020. Serving DNNs like Clockwork: Performance Predictability from the Bottom Up. (2020) 443--462."},{"key":"e_1_2_2_26_1","volume-title":"Prashanth Thinakaran, Bikash Sharma, Mahmut Taylan Kandemir, and Chita R. Das.","author":"Gunasekaran Jashwant Raj","year":"2022","unstructured":"Jashwant Raj Gunasekaran, Cyan Subhra Mishra, Prashanth Thinakaran, Bikash Sharma, Mahmut Taylan Kandemir, and Chita R. Das. 2022. Cocktail: A Multidimensional Optimization for Model Serving in Cloud. In NSDI. 1041--1057."},{"key":"e_1_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Joseph M Hellerstein. 1994. Practical predicate placement. In SIGMOD. 325--335.","DOI":"10.1145\/191839.191904"},{"key":"e_1_2_2_28_1","volume-title":"Focus: Querying Large Video Datasets with Low Latency and Low Cost. In OSDI. 269--286.","author":"Hsieh Kevin","year":"2018","unstructured":"Kevin Hsieh, Ganesh Ananthanarayanan, Peter Bodik, Shivaram Venkataraman, Paramvir Bahl, Matthai Philipose, Phillip B. Gibbons, and Onur Mutlu. 2018. Focus: Querying Large Video Datasets with Low Latency and Low Cost. In OSDI. 269--286."},{"key":"e_1_2_2_29_1","volume-title":"Scrooge: A Cost-Effective Deep Learning Inference System. In SoCC. 624--638.","author":"Hu Yitao","year":"2021","unstructured":"Yitao Hu, Rajrup Ghosh, and Ramesh Govindan. 2021. Scrooge: A Cost-Effective Deep Learning Inference System. In SoCC. 624--638."},{"key":"e_1_2_2_30_1","unstructured":"Dmytro Iakubovskyi. 2023. Facial Emotion Detection ViT. https:\/\/huggingface.co\/dima806\/facial_emotions_image_detection"},{"key":"e_1_2_2_31_1","volume-title":"Alexey Tumanov, Joseph Gonzalez, and Ion Stoica.","author":"Jain Paras","year":"2018","unstructured":"Paras Jain, Xiangxi Mo, Ajay Jain, Harikaran Subbaraj, Rehan Sohail Durrani, Alexey Tumanov, Joseph Gonzalez, and Ion Stoica. 2018. Dynamic Space-Time Scheduling for GPU Inference. http:\/\/arxiv.org\/abs\/1901.00041"},{"key":"e_1_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Junchen Jiang Ganesh Ananthanarayanan Peter Bod\u00edk Siddhartha Sen and Ion Stoica. 2018. Chameleon: scalable adaptation of video analytics. In SIGCOMM. 253--266.","DOI":"10.1145\/3230543.3230574"},{"key":"e_1_2_2_33_1","volume-title":"Mid-Query Re-Optimization of Sub-Optimal Execution Plans. SIGMOD","author":"Kabra Navin","year":"1998","unstructured":"Navin Kabra and David J Dewitt. 1998. Mid-Query Re-Optimization of Sub-Optimal Execution Plans. SIGMOD (1998)."},{"key":"e_1_2_2_34_1","doi-asserted-by":"crossref","unstructured":"Gaurav Tarlok Kakkar Jiashen Cao Pramod Chunduri Zhuangdi Xu Suryatej Reddy Vyalla Prashanth Dintyala Anirudh Prabakaran Jaeho Bang Aubhro Sengupta Kaushik Ravichandran Ishwarya Sivakumar Aryan Rajoria Ashmita Raju Tushar Aggarwal Abdullah Shah Sanjana Garg Shashank Suman Myna Prasanna Kalluraya Subrata Mitra Ali Payani Yao Lu Umakishore Ramachandran and Joy Arulraj. 2023. EVA: An End-to-End Exploratory Video Analytics System. In DEEM. 1--5.","DOI":"10.1145\/3595360.3595858"},{"key":"e_1_2_2_35_1","doi-asserted-by":"crossref","unstructured":"Daniel Kang Peter Bailis and Matei Zaharia. 2019. BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics. In VLDB. 533--546.","DOI":"10.14778\/3372716.3372725"},{"key":"e_1_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Daniel Kang John Emmons Firas Abuzaid Peter Bailis and Matei Zaharia. 2017. NoScope: Optimizing Deep CNN-Based Queries over Video Streams at Scale. In VLDB. 1586--1597.","DOI":"10.14778\/3137628.3137664"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.14778\/3407790.3407804"},{"key":"e_1_2_2_38_1","volume-title":"Accelerating Approximate Aggregation Queries with Expensive Predicates. PVLDB","author":"Kang Daniel","year":"2021","unstructured":"Daniel Kang, John Guibas, Peter Bailis, Tatsunori Hashimoto, Yi Sun, and Matei Zaharia. 2021. Accelerating Approximate Aggregation Queries with Expensive Predicates. PVLDB (2021), 2341--2354."},{"key":"e_1_2_2_39_1","volume-title":"TASTI: Semantic Indexes for Machine Learning-based Queries over Unstructured Data. In SIGMOD. 1934--1947.","author":"Kang Daniel","year":"2022","unstructured":"Daniel Kang, John Guibas, Peter D. Bailis, Tatsunori Hashimoto, and Matei Zaharia. 2022. TASTI: Semantic Indexes for Machine Learning-based Queries over Unstructured Data. In SIGMOD. 1934--1947."},{"key":"e_1_2_2_40_1","volume-title":"Extract-Transform-Load for Video Streams. PVLDB","author":"Kossmann Ferdi","year":"2023","unstructured":"Ferdi Kossmann, Ziniu Wu, Eugenie Lai, Nesime Tatbul, Lei Cao, Tim Kraska, and Sam Madden. 2023. Extract-Transform-Load for Video Streams. PVLDB (2023), 2302--2315."},{"key":"e_1_2_2_41_1","doi-asserted-by":"crossref","unstructured":"Nick Koudas Raymond Li and Ioannis Xarchakos. 2020. Video Monitoring Queries. In ICDE. 1285--1296.","DOI":"10.1109\/ICDE48307.2020.00115"},{"key":"e_1_2_2_42_1","doi-asserted-by":"crossref","unstructured":"Ziliang Lai Chenxia Han Chris Liu Pengfei Zhang Eric Lo and Ben Kao. 2021. Top-K Deep Video Analytics: A Probabilistic Approach. In SIGMOD. 1037--1050.","DOI":"10.1145\/3448016.3452786"},{"key":"e_1_2_2_43_1","volume-title":"Themis: Fair and Efficient GPU Cluster Scheduling. In NSDI. 289--304.","author":"Mahajan Kshiteej","year":"2020","unstructured":"Kshiteej Mahajan, Arjun Balasubramanian, Arjun Singhvi, Shivaram Venkataraman, Aditya Akella, Amar Phanishayee, and Shuchi Chawla. 2020. Themis: Fair and Efficient GPU Cluster Scheduling. In NSDI. 289--304."},{"key":"e_1_2_2_44_1","doi-asserted-by":"crossref","unstructured":"Michael Mitzenmacher Andr\u00e9a W. Richa and Ramesh Sitaraman. 2001. The Power of Two Random Choices: A Survey of Techniques and Results. In Handbook of Randomized Computing. 255--312.","DOI":"10.1007\/978-1-4615-0013-1_9"},{"key":"e_1_2_2_45_1","volume-title":"ExSample: Efficient Searches on Video Repositories through Adaptive Sampling. arXiv:2005.09141 [cs]","author":"Moll Oscar","year":"2020","unstructured":"Oscar Moll, Favyen Bastani, Sam Madden, Mike Stonebraker, Vijay Gadepally, and Tim Kraska. 2020. ExSample: Efficient Searches on Video Repositories through Adaptive Sampling. arXiv:2005.09141 [cs] (2020)."},{"key":"e_1_2_2_46_1","volume-title":"Ray: A Distributed Framework for Emerging AI Applications. In OSDI. 561--577.","author":"Moritz Philipp","year":"2018","unstructured":"Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael I. Jordan, and Ion Stoica. 2018. Ray: A Distributed Framework for Emerging AI Applications. In OSDI. 561--577."},{"key":"e_1_2_2_47_1","unstructured":"NVIDIA. 2020. TensorRT Inference Server. [Online] Available from: https:\/\/github.com\/NVIDIA\/tensorrt-inference-server."},{"key":"e_1_2_2_48_1","unstructured":"NVIDIA. 2021. NVIDIA Multi-Process Service Introduction. [Online] Available from: https:\/\/docs.nvidia.com\/deploy\/mps\/index.html."},{"key":"e_1_2_2_49_1","unstructured":"Christopher Olston Noah Fiedel Kiril Gorovoy Jeremiah Harmsen Li Lao Fangwei Li Vinu Rajashekhar Sukriti Ramesh and Jordan Soyke. 2017. TensorFlow-Serving: Flexible High-Performance ML Serving. http:\/\/arxiv.org\/abs\/1712.06139"},{"key":"e_1_2_2_50_1","unstructured":"Nate Raw. 2021. Facial Emotion Detection ViT. https:\/\/huggingface.co\/nateraw\/vit-age-classifier"},{"key":"e_1_2_2_51_1","volume-title":"Optimizing Video Analytics with Declarative Model Relationships. PVLDB","author":"Romero Francisco","year":"2022","unstructured":"Francisco Romero, Johann Hauswald, Aditi Partap, Daniel Kang, Matei Zaharia, and Christos Kozyrakis. 2022. Optimizing Video Analytics with Declarative Model Relationships. PVLDB (2022), 447--460."},{"key":"e_1_2_2_52_1","unstructured":"Francisco Romero Qian Li Neeraja J. Yadwadkar and Christos Kozyrakis. 2021. INFaaS: Automated Model-less Inference Serving. (2021) 397--411."},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0940-3"},{"key":"e_1_2_2_54_1","doi-asserted-by":"crossref","unstructured":"Haichen Shen Lequn Chen Yuchen Jin Liangyu Zhao Bingyu Kong Matthai Philipose Arvind Krishnamurthy and Ravi Sundaram. 2019. Nexus: a GPU cluster engine for accelerating DNN-based video analysis. In SOSP. 322--337.","DOI":"10.1145\/3341301.3359658"},{"key":"e_1_2_2_55_1","unstructured":"Ultralytics. 2023. Ultralytics YOLOv8. [Online] Available from: https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"e_1_2_2_56_1","volume-title":"Lottery Scheduling: Flexible Proportional-Share Resource Management. OSDI","author":"Waldspurger Carl A","year":"1994","unstructured":"Carl A Waldspurger and William E Weihl. 1994. Lottery Scheduling: Flexible Proportional-Share Resource Management. OSDI (1994)."},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3064051"},{"key":"e_1_2_2_58_1","volume-title":"Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures. PVLDB","author":"Wu Yongji","year":"2022","unstructured":"Yongji Wu, Matthew Lentz, Danyang Zhuo, and Yao Lu. 2022. Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures. PVLDB (2022), 406--419."},{"key":"e_1_2_2_59_1","volume-title":"Gandiva: Introspective Cluster Scheduling for Deep Learning. In OSDI. 595--610.","author":"Xiao Wencong","year":"2018","unstructured":"Wencong Xiao, Romil Bhardwaj, Ramachandran Ramjee, Muthian Sivathanu, Nipun Kwatra, Zhenhua Han, Pratyush Patel, Xuan Peng, Hanyu Zhao, Quanlu Zhang, Fan Yang, and Lidong Zhou. 2018. Gandiva: Introspective Cluster Scheduling for Deep Learning. In OSDI. 595--610."},{"key":"e_1_2_2_60_1","volume-title":"Joy Arulraj, and Umakishore Ramachandran.","author":"Xu Zhuangdi","year":"2022","unstructured":"Zhuangdi Xu, Gaurav Tarlok Kakkar, Joy Arulraj, and Umakishore Ramachandran. 2022. EVA: A Symbolic Approach to Accelerating Exploratory Video Analytics with Materialized Views. In SIGMOD. 602--616."},{"key":"e_1_2_2_61_1","volume-title":"Optimizing Machine Learning Inference Queries with Correlative Proxy Models. PVLDB","author":"Yang Zhihui","year":"2022","unstructured":"Zhihui Yang, Zuozhi Wang, Yicong Huang, Yao Lu, Chen Li, and X. Sean Wang. 2022. Optimizing Machine Learning Inference Queries with Correlative Proxy Models. PVLDB (2022), 2032--2044."},{"key":"e_1_2_2_62_1","unstructured":"Skylar Yau. 2023. Dog Breed Classifier ViT. https:\/\/huggingface.co\/skyau\/dog-breed-classifier-vit"},{"key":"e_1_2_2_63_1","volume-title":"Salus: Fine-Grained GPU Sharing Primitives for Deep Learning Applications. In MLSys.","author":"Yu Peifeng","year":"2020","unstructured":"Peifeng Yu and Mosharaf Chowdhury. 2020. Salus: Fine-Grained GPU Sharing Primitives for Deep Learning Applications. In MLSys."},{"key":"e_1_2_2_64_1","first-page":"279","article-title":"VQPy: An Object-Oriented Approach to Modern Video Analytics","volume":"6","author":"Yu Shan","year":"2024","unstructured":"Shan Yu, Zhenting Zhu, Yu Chen, Hanchen Xu, Pengzhan Zhao, Yang Wang, Arthi Padmanabhan, Hugo Latapie, and Harry Xu. 2024. VQPy: An Object-Oriented Approach to Modern Video Analytics. Proceedings of Machine Learning and Systems 6 (2024), 279--295.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934664"},{"key":"e_1_2_2_66_1","volume-title":"EQUIVOCAL: Synthesizing Queries for Compositional Video Events from Limited User Interactions. PVLDB","author":"Zhang Enhao","year":"2023","unstructured":"Enhao Zhang, Maureen Daum, Dong He, Brandon Haynes, Ranjay Krishna, and Magdalena Balazinska. 2023. EQUIVOCAL: Synthesizing Queries for Compositional Video Events from Limited User Interactions. PVLDB (2023), 2714--2727."},{"key":"e_1_2_2_67_1","unstructured":"Kai Zhang Bingsheng He Jiayu Hu Zeke Wang Bei Hua Jiayi Meng and Lishan Yang. 2018. G-NET: Effective GPU Sharing in NFV Systems. In NSDI. 187--200."},{"key":"e_1_2_2_68_1","volume-title":"Panorama: A Data System for Unbounded Vocabulary Querying over Video. In VLDB. 477--491.","author":"Zhang Yuhao","year":"2019","unstructured":"Yuhao Zhang and Arun Kumar. 2019. Panorama: A Data System for Unbounded Vocabulary Querying over Video. In VLDB. 477--491."}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T18:59:37Z","timestamp":1774983577000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725408"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,17]]},"references-count":68,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,6,17]]}},"alternative-id":["10.1145\/3725408"],"URL":"https:\/\/doi.org\/10.1145\/3725408","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,17]]}}}