{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T05:17:47Z","timestamp":1768108667635,"version":"3.49.0"},"reference-count":64,"publisher":"Association for Computing Machinery (ACM)","issue":"3","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2022,11]]},"abstract":"<jats:p>The availability of vast video collections and the accuracy of ML models has generated significant interest in video analytics systems. Since naively processing all frames using expensive models is impractical, researchers have proposed optimizations such as selectively using faster but less accurate models to replace or filter frames for expensive models. However, these optimizations are difficult to apply on queries with multiple predicates and models, as users must manually explore a large optimization space. Without significant systems expertise or time investment, an analyst may manually create an execution plan that is unnecessarily expensive and\/or terribly inaccurate.<\/jats:p>\n          <jats:p>\n            We propose\n            <jats:italic>Relational Hints<\/jats:italic>\n            , a declarative interface that allows users to suggest ML model relationships based on domain knowledge. Users can express two key relationships: when a model can replace another (CAN REPLACE) and when a model can be used to filter frames for another (CAN FILTER). We aim to design an interface to express\n            <jats:italic>model relationships informed by domain specific knowledge<\/jats:italic>\n            and define the constraints by which these relationships hold. We then present the\n            <jats:italic>VIVA video analytics system<\/jats:italic>\n            that uses relational hints to optimize SQL queries on video datasets. VIVA automatically selects and validates the hints applicable to the query, generates possible query plans using a formal set of transformations, and finds the best performance plan that meets a user's accuracy requirements. VIVA relieves users from rewriting and manually optimizing video queries as new models become available and execution environments evolve. We evaluate VIVA implemented on top of Spark and show that hints improve performance up to 16.6X without sacrificing accuracy.\n          <\/jats:p>","DOI":"10.14778\/3570690.3570695","type":"journal-article","created":{"date-parts":[[2023,1,23]],"date-time":"2023-01-23T17:29:55Z","timestamp":1674494995000},"page":"447-460","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Optimizing Video Analytics with Declarative Model Relationships"],"prefix":"10.14778","volume":"16","author":[{"given":"Francisco","family":"Romero","sequence":"first","affiliation":[{"name":"Stanford University"}]},{"given":"Johann","family":"Hauswald","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Aditi","family":"Partap","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Daniel","family":"Kang","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Matei","family":"Zaharia","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Christos","family":"Kozyrakis","sequence":"additional","affiliation":[{"name":"Stanford University"}]}],"member":"320","published-online":{"date-parts":[[2023,1,23]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Martin Abadi Paul Barham Jianmin Chen Zhifeng Chen Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Geoffrey Irving Michael Isard Manjunath Kudlur Josh Levenberg Rajat Monga Sherry Moore Derek G. Murray Benoit Steiner Paul Tucker Vijay Vasudevan Pete Warden Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2016. TensorFlow: A system for large-scale machine learning. In OSDI.  Martin Abadi Paul Barham Jianmin Chen Zhifeng Chen Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Geoffrey Irving Michael Isard Manjunath Kudlur Josh Levenberg Rajat Monga Sherry Moore Derek G. Murray Benoit Steiner Paul Tucker Vijay Vasudevan Pete Warden Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2016. TensorFlow: A system for large-scale machine learning. In OSDI."},{"key":"e_1_2_1_2_1","unstructured":"Internet Archive. 2022. TV News Archive. https:\/\/archive.org\/details\/tv.  Internet Archive. 2022. TV News Archive. https:\/\/archive.org\/details\/tv."},{"key":"e_1_2_1_3_1","volume-title":"MIRIS: Fast Object Track Queries in Video. In SIGMOD.","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. 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."},{"key":"e_1_2_1_4_1","volume-title":"The OpenCV Library. Dr. Dobb's Journal of Software Tools","author":"Bradski G.","year":"2000","unstructured":"G. Bradski . 2000. The OpenCV Library. Dr. Dobb's Journal of Software Tools ( 2000 ). G. Bradski. 2000. The OpenCV Library. Dr. Dobb's Journal of Software Tools (2000)."},{"key":"e_1_2_1_5_1","volume-title":"THIA: Accelerating Video Analytics using Early Inference and Fine-Grained Query Planning. arXiv:2102.08481","author":"Cao Jiashen","year":"2021","unstructured":"Jiashen Cao , Ramyad Hadidi , Joy Arulraj , and Hyesoon Kim . 2021 . THIA: Accelerating Video Analytics using Early Inference and Fine-Grained Query Planning. arXiv:2102.08481 Jiashen Cao, Ramyad Hadidi, Joy Arulraj, and Hyesoon Kim. 2021. THIA: Accelerating Video Analytics using Early Inference and Fine-Grained Query Planning. arXiv:2102.08481"},{"key":"e_1_2_1_6_1","unstructured":"Jiashen Cao Karan Sarkar Ramyad Hadidi Joy Arulraj and Hyesoon Kim. 2022. FiGO: Fine-Grained Query Optimization in Video Analytics. In SIGMOD.  Jiashen Cao Karan Sarkar Ramyad Hadidi Joy Arulraj and Hyesoon Kim. 2022. FiGO: Fine-Grained Query Optimization in Video Analytics. In SIGMOD."},{"key":"e_1_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Surajit Chaudhuri Bolin Ding and Srikanth Kandula. 2017. Approximate query processing: No silver bullet. In SIGMOD.  Surajit Chaudhuri Bolin Ding and Srikanth Kandula. 2017. Approximate query processing: No silver bullet. In SIGMOD.","DOI":"10.1145\/3035918.3056097"},{"key":"e_1_2_1_8_1","volume-title":"TASM: A Tile-Based Storage Manager for Video Analytics. In ICDE.","author":"Daum Maureen","year":"2021","unstructured":"Maureen Daum , Haynes Brandon , Dong He , Amrita Mazumdar , and Magdalena Balazinska . 2021 . TASM: A Tile-Based Storage Manager for Video Analytics. In ICDE. Maureen Daum, Haynes Brandon, Dong He, Amrita Mazumdar, and Magdalena Balazinska. 2021. TASM: A Tile-Based Storage Manager for Video Analytics. In ICDE."},{"key":"e_1_2_1_9_1","volume-title":"VOCAL: Video Organization and Interactive Compositional AnaLytics. In CIDR.","author":"Daum Maureen","year":"2022","unstructured":"Maureen Daum , Enhao Zhang , Dong He , Magdalena Balazinska , Brandon Haynes , Ranjay Krishna , Apryle Craig , and Aaron Wirsing . 2022 . VOCAL: Video Organization and Interactive Compositional AnaLytics. In CIDR. Maureen Daum, Enhao Zhang, Dong He, Magdalena Balazinska, Brandon Haynes, Ranjay Krishna, Apryle Craig, and Aaron Wirsing. 2022. VOCAL: Video Organization and Interactive Compositional AnaLytics. In CIDR."},{"key":"e_1_2_1_10_1","unstructured":"Tim Esler. 2022. InceptionResNet Face Recognition in PyTorch. https:\/\/github.com\/timesler\/facenet-pytorch  Tim Esler. 2022. InceptionResNet Face Recognition in PyTorch. https:\/\/github.com\/timesler\/facenet-pytorch"},{"key":"e_1_2_1_11_1","unstructured":"FFmpeg. 2022. FFmpeg. https:\/\/ffmpeg.org\/.  FFmpeg. 2022. FFmpeg. https:\/\/ffmpeg.org\/."},{"key":"e_1_2_1_12_1","volume-title":"Rekall: Specifying video events using compositions of spatiotemporal labels. arXiv:1910.02993","author":"Fu Daniel Y","year":"2019","unstructured":"Daniel Y Fu , Will Crichton , James Hong , Xinwei Yao , Haotian Zhang , Anh Truong , Avanika Narayan , Maneesh Agrawala , Christopher R\u00e9 , and Kayvon Fatahalian . 2019 . Rekall: Specifying video events using compositions of spatiotemporal labels. arXiv:1910.02993 Daniel Y Fu, Will Crichton, James Hong, Xinwei Yao, Haotian Zhang, Anh Truong, Avanika Narayan, Maneesh Agrawala, Christopher R\u00e9, and Kayvon Fatahalian. 2019. Rekall: Specifying video events using compositions of spatiotemporal labels. arXiv:1910.02993"},{"key":"e_1_2_1_13_1","volume-title":"YOLOX: Exceeding YOLO Series in","author":"Ge Zheng","year":"2021","unstructured":"Zheng Ge , Songtao Liu , Feng Wang , Zeming Li , and Jian Sun . 2021 . YOLOX: Exceeding YOLO Series in 2021. arXiv:2107.08430 Zheng Ge, Songtao Liu, Feng Wang, Zeming Li, and Jian Sun. 2021. YOLOX: Exceeding YOLO Series in 2021. arXiv:2107.08430"},{"key":"e_1_2_1_14_1","unstructured":"Google. 2022. Google Compute Engine: GPUs Pricing. https:\/\/cloud.google.com\/compute\/gpus-pricing.  Google. 2022. Google Compute Engine: GPUs Pricing. https:\/\/cloud.google.com\/compute\/gpus-pricing."},{"key":"e_1_2_1_15_1","unstructured":"Google. 2022. Tesseract OCR. https:\/\/github.com\/tesseract-ocr\/tesseract.  Google. 2022. Tesseract OCR. https:\/\/github.com\/tesseract-ocr\/tesseract."},{"key":"e_1_2_1_16_1","volume-title":"VSS: A Storage System for Video Analytics. In SIGMOD.","author":"Haynes Brandon","year":"2021","unstructured":"Brandon Haynes , Maureen Daum , Dong He , Amrita Mazumdar , Magdalena Balazinska , Alvin Cheung , and Luis Ceze . 2021 . VSS: A Storage System for Video Analytics. In SIGMOD. Brandon Haynes, Maureen Daum, Dong He, Amrita Mazumdar, Magdalena Balazinska, Alvin Cheung, and Luis Ceze. 2021. VSS: A Storage System for Video Analytics. In SIGMOD."},{"key":"e_1_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Caner Hazirbas Joanna Bitton Brian Dolhansky Jacqueline Pan Albert Gordo and Cristian Canton Ferrer. 2021. Towards Measuring Fairness in AI: the Casual Conversations Dataset. arXiv:2104.02821  Caner Hazirbas Joanna Bitton Brian Dolhansky Jacqueline Pan Albert Gordo and Cristian Canton Ferrer. 2021. Towards Measuring Fairness in AI: the Casual Conversations Dataset. arXiv:2104.02821","DOI":"10.1109\/TBIOM.2021.3132237"},{"key":"e_1_2_1_18_1","volume-title":"Mask r-cnn","author":"He Kaiming","unstructured":"Kaiming He , Georgia Gkioxari , Piotr Doll\u00e1r , and Ross Girshick . 2017. Mask r-cnn . In ICCV. IEEE. Kaiming He, Georgia Gkioxari, Piotr Doll\u00e1r, and Ross Girshick. 2017. Mask r-cnn. In ICCV. IEEE."},{"key":"e_1_2_1_19_1","unstructured":"Wenjia He Michael R. Anderson Maxwell Strome and Michael Cafarella. 2020. A Method for Optimizing Opaque Filter Queries. In SIGMOD.  Wenjia He Michael R. Anderson Maxwell Strome and Michael Cafarella. 2020. A Method for Optimizing Opaque Filter Queries. In SIGMOD."},{"key":"e_1_2_1_20_1","doi-asserted-by":"crossref","unstructured":"James Hong Will Crichton Haotian Zhang Daniel Y. Fu Jacob Ritchie Jeremy Barenholtz Ben Hannel Xinwei Yao Michaela Murray Geraldine Moriba Maneesh Agrawala and Kayvon Fatahalian. 2021. Analysis of Faces in a Decade of US Cable TV News. In SIGKDD.  James Hong Will Crichton Haotian Zhang Daniel Y. Fu Jacob Ritchie Jeremy Barenholtz Ben Hannel Xinwei Yao Michaela Murray Geraldine Moriba Maneesh Agrawala and Kayvon Fatahalian. 2021. Analysis of Faces in a Decade of US Cable TV News. In SIGKDD.","DOI":"10.1145\/3447548.3467134"},{"key":"e_1_2_1_21_1","doi-asserted-by":"crossref","unstructured":"James Hong Matthew Fisher Micha\u00ebl Gharbi and Kayvon Fatahalian. 2021. Video Pose Distillation for Few-Shot Fine-Grained Sports Action Recognition. In ICCV.  James Hong Matthew Fisher Micha\u00ebl Gharbi and Kayvon Fatahalian. 2021. Video Pose Distillation for Few-Shot Fine-Grained Sports Action Recognition. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00912"},{"key":"e_1_2_1_22_1","volume-title":"CORDS: Automatic Discovery of Correlations and Soft Functional Dependencies. In SIGMOD.","author":"Ilyas Ihab F.","year":"2004","unstructured":"Ihab F. Ilyas , Volker Markl , Peter Haas , Paul Brown , and Ashraf Aboulnaga . 2004 . CORDS: Automatic Discovery of Correlations and Soft Functional Dependencies. In SIGMOD. Ihab F. Ilyas, Volker Markl, Peter Haas, Paul Brown, and Ashraf Aboulnaga. 2004. CORDS: Automatic Discovery of Correlations and Soft Functional Dependencies. In SIGMOD."},{"key":"e_1_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Benoit Jacob Skirmantas Kligys Bo Chen Menglong Zhu Matthew Tang Andrew Howard Hartwig Adam and Dmitry Kalenichenko. 2018. Quantization and training of neural networks for efficient integer-arithmetic-only inference. In CVPR.  Benoit Jacob Skirmantas Kligys Bo Chen Menglong Zhu Matthew Tang Andrew Howard Hartwig Adam and Dmitry Kalenichenko. 2018. Quantization and training of neural networks for efficient integer-arithmetic-only inference. In CVPR.","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_2_1_24_1","volume-title":"Christopher Canel, Lilia Tang, Ishan Misra, Michael Kaminsky, Michael A Kozuch, Padmanabhan Pillai, David G Andersen, and Gregory R Ganger.","author":"Jiang Angela H","year":"2018","unstructured":"Angela H Jiang , Daniel L-K Wong , Christopher Canel, Lilia Tang, Ishan Misra, Michael Kaminsky, Michael A Kozuch, Padmanabhan Pillai, David G Andersen, and Gregory R Ganger. 2018 . Mainstream : Dynamic {Stem-Sharing} for {Multi-Tenant} Video Processing. In ATC. Angela H Jiang, Daniel L-K Wong, Christopher Canel, Lilia Tang, Ishan Misra, Michael Kaminsky, Michael A Kozuch, Padmanabhan Pillai, David G Andersen, and Gregory R Ganger. 2018. Mainstream: Dynamic {Stem-Sharing} for {Multi-Tenant} Video Processing. In ATC."},{"key":"e_1_2_1_25_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 PVLDB.  Daniel Kang Peter Bailis and Matei Zaharia. 2019. BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics. In PVLDB.","DOI":"10.14778\/3372716.3372725"},{"key":"e_1_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Daniel Kang John Emmons Firas Abuzaid Peter Bailis and Matei Zaharia. 2017. NoScope: optimizing neural network queries over video at scale. In PVLDB.  Daniel Kang John Emmons Firas Abuzaid Peter Bailis and Matei Zaharia. 2017. NoScope: optimizing neural network queries over video at scale. In PVLDB.","DOI":"10.14778\/3137628.3137664"},{"key":"e_1_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Daniel Kang Edward Gan Peter Bailis Tatsunori Hashimoto and Matei Zaharia. 2020. Approximate Selection with Guarantees using Proxies. In PVLDB.  Daniel Kang Edward Gan Peter Bailis Tatsunori Hashimoto and Matei Zaharia. 2020. Approximate Selection with Guarantees using Proxies. In PVLDB.","DOI":"10.14778\/3407790.3407804"},{"key":"e_1_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Daniel Kang John Guibas Peter Bailis Tatsunori Hashimoto and Matei Zaharia. 2022. Semantic Indexes for Machine Learning-based Queries over Unstructured Data. In SIGMOD.  Daniel Kang John Guibas Peter Bailis Tatsunori Hashimoto and Matei Zaharia. 2022. Semantic Indexes for Machine Learning-based Queries over Unstructured Data. In SIGMOD.","DOI":"10.1145\/3514221.3517897"},{"key":"e_1_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Daniel Kang John Guibas Peter Bailis Yi Sun Tatsunori Hashimoto and Matei Zaharia. 2021. Accelerating Approximate Aggregation Queries with Expensive Predicates. In PVLDB.  Daniel Kang John Guibas Peter Bailis Yi Sun Tatsunori Hashimoto and Matei Zaharia. 2021. Accelerating Approximate Aggregation Queries with Expensive Predicates. In PVLDB.","DOI":"10.14778\/3476249.3476285"},{"key":"e_1_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Daniel Kang Ankit Mathur Teja Veeramacheneni Peter Bailis and Matei Zaharia. 2021. Jointly optimizing preprocessing and inference for DNN-based visual analytics. In PVLDB.  Daniel Kang Ankit Mathur Teja Veeramacheneni Peter Bailis and Matei Zaharia. 2021. Jointly optimizing preprocessing and inference for DNN-based visual analytics. In PVLDB.","DOI":"10.14778\/3425879.3425881"},{"key":"e_1_2_1_31_1","volume-title":"VIVA: An End-to-End System for Interactive Video Analytics. In CIDR.","author":"Kang Daniel","year":"2022","unstructured":"Daniel Kang , Francisco Romero , Peter Bailis , Christos Kozyrakis , and Matei Zaharia . 2022 . VIVA: An End-to-End System for Interactive Video Analytics. In CIDR. Daniel Kang, Francisco Romero, Peter Bailis, Christos Kozyrakis, and Matei Zaharia. 2022. VIVA: An End-to-End System for Interactive Video Analytics. In CIDR."},{"key":"e_1_2_1_32_1","unstructured":"Fiodar Kazhamiaka Matei Zaharia and Peter Bailis. 2021. Challenges and Opportunities for Autonomous Vehicle Query Systems. In CIDR.  Fiodar Kazhamiaka Matei Zaharia and Peter Bailis. 2021. Challenges and Opportunities for Autonomous Vehicle Query Systems. In CIDR."},{"key":"e_1_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Sebastian Kruse and Felix Naumann. 2018. Efficient Discovery of Approximate Dependencies. In PVLDB.  Sebastian Kruse and Felix Naumann. 2018. Efficient Discovery of Approximate Dependencies. In PVLDB.","DOI":"10.14778\/3192965.3192968"},{"key":"e_1_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Michael A Laurenzano Parker Hill Mehrzad Samadi Scott Mahlke Jason Mars and Lingjia Tang. 2016. Input responsiveness: using canary inputs to dynamically steer approximation. In PLDI.  Michael A Laurenzano Parker Hill Mehrzad Samadi Scott Mahlke Jason Mars and Lingjia Tang. 2016. Input responsiveness: using canary inputs to dynamically steer approximation. In PLDI.","DOI":"10.1145\/2908080.2908087"},{"key":"e_1_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Yao Lu Aakanksha Chowdhery Srikanth Kandula and Surajit Chaudhuri. 2018. Accelerating Machine Learning Inference with Probabilistic Predicates. In SIGMOD.  Yao Lu Aakanksha Chowdhery Srikanth Kandula and Surajit Chaudhuri. 2018. Accelerating Machine Learning Inference with Probabilistic Predicates. In SIGMOD.","DOI":"10.1145\/3183713.3183751"},{"key":"e_1_2_1_37_1","unstructured":"Microsoft. 2022. MicrosoftSQL Hints (Transact-SQL). https:\/\/docs.microsoft.com\/en-us\/sql\/t-sql\/queries\/hints-transact-sql?view=sql-server-ver15.  Microsoft. 2022. MicrosoftSQL Hints (Transact-SQL). https:\/\/docs.microsoft.com\/en-us\/sql\/t-sql\/queries\/hints-transact-sql?view=sql-server-ver15."},{"key":"e_1_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Oscar Moll Favyen Bastani Sam Madden Mike Stonebraker Vijay Gadepally and Tim Kraska. 2022. ExSample: Efficient Searches on Video Repositories through Adaptive Sampling. In ICDE.  Oscar Moll Favyen Bastani Sam Madden Mike Stonebraker Vijay Gadepally and Tim Kraska. 2022. ExSample: Efficient Searches on Video Repositories through Adaptive Sampling. In ICDE.","DOI":"10.1109\/ICDE53745.2022.00275"},{"key":"e_1_2_1_39_1","unstructured":"MySQL. 2022. MySQL Optimizer Hints. https:\/\/dev.mysql.com\/doc\/refman\/8.0\/en\/optimizer-hints.html.  MySQL. 2022. MySQL Optimizer Hints. https:\/\/dev.mysql.com\/doc\/refman\/8.0\/en\/optimizer-hints.html."},{"key":"e_1_2_1_40_1","unstructured":"Scoreboard OCR. 2022. Scoreboard OCR. https:\/\/scoreboard-ocr.com\/start.  Scoreboard OCR. 2022. Scoreboard OCR. https:\/\/scoreboard-ocr.com\/start."},{"key":"e_1_2_1_41_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","unstructured":"Adam Paszke , Sam Gross , Francisco Massa , Adam Lerer , James Bradbury , Gregory Chanan , Trevor Killeen , Zeming Lin , Natalia Gimelshein , Luca Antiga , Alban Desmaison , Andreas K\u00f6pf , Edward Yang , Zach DeVito , Martin Raison , Alykhan Tejani , Sasank Chilamkurthy , Benoit Steiner , Lu Fang , Junjie Bai , and Soumith Chintala . 2019. PyTorch: An Imperative Style , High-Performance Deep Learning Library . In NeurIPS. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6pf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In NeurIPS."},{"key":"e_1_2_1_42_1","volume-title":"Scanner: Efficient Video Analysis at Scale. In SIGGRAPH.","author":"Poms Alex","year":"2018","unstructured":"Alex Poms , William Crichton , Pat Hanrahan , and Kayvon Fatahalian . 2018 . Scanner: Efficient Video Analysis at Scale. In SIGGRAPH. Alex Poms, William Crichton, Pat Hanrahan, and Kayvon Fatahalian. 2018. Scanner: Efficient Video Analysis at Scale. In SIGGRAPH."},{"key":"e_1_2_1_43_1","unstructured":"PyTorch. 2022. 3D ResNet Video Classification in PyTorch. https:\/\/pytorch.org\/hub\/facebookresearch_pytorchvideo_resnet\/  PyTorch. 2022. 3D ResNet Video Classification in PyTorch. https:\/\/pytorch.org\/hub\/facebookresearch_pytorchvideo_resnet\/"},{"key":"e_1_2_1_44_1","volume-title":"Image Classification: Models and Pre-Trained Weights. https:\/\/pytorch.org\/vision\/stable\/models.html#classification","year":"2022","unstructured":"PyTorch. 2022 . Image Classification: Models and Pre-Trained Weights. https:\/\/pytorch.org\/vision\/stable\/models.html#classification PyTorch. 2022. Image Classification: Models and Pre-Trained Weights. https:\/\/pytorch.org\/vision\/stable\/models.html#classification"},{"key":"e_1_2_1_45_1","volume-title":"Object Detection: Models and Pre-Trained Weights. https:\/\/pytorch.org\/vision\/stable\/models.html#object-detection-instance-segmentation-and-person-keypoint-detection","year":"2022","unstructured":"PyTorch. 2022 . Object Detection: Models and Pre-Trained Weights. https:\/\/pytorch.org\/vision\/stable\/models.html#object-detection-instance-segmentation-and-person-keypoint-detection PyTorch. 2022. Object Detection: Models and Pre-Trained Weights. https:\/\/pytorch.org\/vision\/stable\/models.html#object-detection-instance-segmentation-and-person-keypoint-detection"},{"key":"e_1_2_1_46_1","volume-title":"Dilip Sequeira, Ashish Sirasao, Fei Sun, Hanlin Tang, Michael Thomson, Frank Wei, Ephrem Wu, Lingjie Xu, Koichi Yamada, Bing Yu, George Yuan, Aaron Zhong, Peizhao Zhang, and Yuchen Zhou.","author":"Reddi Vijay Janapa","year":"2020","unstructured":"Vijay Janapa Reddi , Christine Cheng , David Kanter , Peter Mattson , Guenther Schmuelling , Carole-Jean Wu , Brian Anderson , Maximilien Breughe , Mark Charlebois , William Chou , Ramesh Chukka , Cody Coleman , Sam Davis , Pan Deng , Greg Diamos , Jared Duke , Dave Fick , J. Scott Gardner , Itay Hubara , Sachin Idgunji , Thomas B. Jablin , Jeff Jiao , Tom St. John , Pankaj Kanwar , David Lee , Jeffery Liao , Anton Lokhmotov , Francisco Massa , Peng Meng , Paulius Micikevicius , Colin Osborne , Gennady Pekhimenko , Arun Tejusve Raghunath Rajan , Dilip Sequeira, Ashish Sirasao, Fei Sun, Hanlin Tang, Michael Thomson, Frank Wei, Ephrem Wu, Lingjie Xu, Koichi Yamada, Bing Yu, George Yuan, Aaron Zhong, Peizhao Zhang, and Yuchen Zhou. 2020 . MLPerf Inference Benchmark. In ISCA. Vijay Janapa Reddi, Christine Cheng, David Kanter, Peter Mattson, Guenther Schmuelling, Carole-Jean Wu, Brian Anderson, Maximilien Breughe, Mark Charlebois, William Chou, Ramesh Chukka, Cody Coleman, Sam Davis, Pan Deng, Greg Diamos, Jared Duke, Dave Fick, J. Scott Gardner, Itay Hubara, Sachin Idgunji, Thomas B. Jablin, Jeff Jiao, Tom St. John, Pankaj Kanwar, David Lee, Jeffery Liao, Anton Lokhmotov, Francisco Massa, Peng Meng, Paulius Micikevicius, Colin Osborne, Gennady Pekhimenko, Arun Tejusve Raghunath Rajan, Dilip Sequeira, Ashish Sirasao, Fei Sun, Hanlin Tang, Michael Thomson, Frank Wei, Ephrem Wu, Lingjie Xu, Koichi Yamada, Bing Yu, George Yuan, Aaron Zhong, Peizhao Zhang, and Yuchen Zhou. 2020. MLPerf Inference Benchmark. In ISCA."},{"key":"e_1_2_1_47_1","unstructured":"Francisco Romero Qian Li Neeraja J Yadwadkar and Christos Kozyrakis. 2021. INFaaS: Automated Model-less Inference Serving. In ATC.  Francisco Romero Qian Li Neeraja J Yadwadkar and Christos Kozyrakis. 2021. INFaaS: Automated Model-less Inference Serving. In ATC."},{"key":"e_1_2_1_48_1","volume-title":"Llama: A Heterogeneous & Serverless Framework for Auto-Tuning Video Analytics Pipelines. In SoCC.","author":"Romero Francisco","year":"2021","unstructured":"Francisco Romero , Mark Zhao , Neeraja J. Yadwadkar , and Christos Kozyrakis . 2021 . Llama: A Heterogeneous & Serverless Framework for Auto-Tuning Video Analytics Pipelines. In SoCC. Francisco Romero, Mark Zhao, Neeraja J. Yadwadkar, and Christos Kozyrakis. 2021. Llama: A Heterogeneous & Serverless Framework for Auto-Tuning Video Analytics Pipelines. In SoCC."},{"key":"e_1_2_1_49_1","volume-title":"Abbas Kazerouni, Ian Osband, and Zheng Wen.","author":"Russo Daniel","year":"2017","unstructured":"Daniel Russo , Benjamin Van Roy , Abbas Kazerouni, Ian Osband, and Zheng Wen. 2017 . A Tutorial on Thompson Sampling . arXiv:1707.02038 Daniel Russo, Benjamin Van Roy, Abbas Kazerouni, Ian Osband, and Zheng Wen. 2017. A Tutorial on Thompson Sampling. arXiv:1707.02038"},{"key":"e_1_2_1_50_1","unstructured":"Scikit. 2022. Support Vector Classifier in Scikit. https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.svm.SVC.html  Scikit. 2022. Support Vector Classifier in Scikit. https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.svm.SVC.html"},{"key":"e_1_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Sefik Ilkin Serengil and Alper Ozpinar. 2021. HyperExtended LightFace: A Facial Attribute Analysis Framework. In ICEET.  Sefik Ilkin Serengil and Alper Ozpinar. 2021. HyperExtended LightFace: A Facial Attribute Analysis Framework. In ICEET.","DOI":"10.1109\/ICEET53442.2021.9659697"},{"key":"e_1_2_1_52_1","volume-title":"Nexus: A GPU Cluster Engine for Accelerating DNN-Based Video Analysis. In SOSP.","author":"Shen Haichen","year":"2019","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. 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."},{"key":"e_1_2_1_53_1","unstructured":"Justin Shenk. 2022. Facial Expression Recognition. https:\/\/github.com\/justinshenk\/fer  Justin Shenk. 2022. Facial Expression Recognition. https:\/\/github.com\/justinshenk\/fer"},{"key":"e_1_2_1_54_1","unstructured":"TensorFlow. 2022. Signatures in TensorFlow Lite. https:\/\/www.tensorflow.org\/lite\/guide\/signatures.  TensorFlow. 2022. Signatures in TensorFlow Lite. https:\/\/www.tensorflow.org\/lite\/guide\/signatures."},{"key":"e_1_2_1_55_1","unstructured":"Ultralytics. 2022. Yolov5 Object Detection in PyTorch. https:\/\/github.com\/ultralytics\/yolov5.  Ultralytics. 2022. Yolov5 Object Detection in PyTorch. https:\/\/github.com\/ultralytics\/yolov5."},{"key":"e_1_2_1_56_1","unstructured":"Paul Viola and Michael Jones. 2001. Rapid object detection using a boosted cascade of simple features. In CVPR.  Paul Viola and Michael Jones. 2001. Rapid object detection using a boosted cascade of simple features. In CVPR."},{"key":"e_1_2_1_57_1","unstructured":"Chien-Yao Wang I-Hau Yeh and Hong-Yuan Mark Liao. 2021. You Only Learn One Representation: Unified Network for Multiple Tasks. arXiv:2105.04206  Chien-Yao Wang I-Hau Yeh and Hong-Yuan Mark Liao. 2021. You Only Learn One Representation: Unified Network for Multiple Tasks. arXiv:2105.04206"},{"key":"e_1_2_1_58_1","unstructured":"Yongji Wu Matthew Lentz Danyang Zhuo and Yao Lu. 2023. Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures. In PVLDB.  Yongji Wu Matthew Lentz Danyang Zhuo and Yao Lu. 2023. Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures. In PVLDB."},{"key":"e_1_2_1_59_1","unstructured":"Ran Xu Jinkyu Koo Rakesh Kumar Peter Bai Subrata Mitra Sasa Misailovic and Saurabh Bagchi. 2018. VideoChef: Efficient Approximation for Streaming Video Processing Pipelines. In ATC.  Ran Xu Jinkyu Koo Rakesh Kumar Peter Bai Subrata Mitra Sasa Misailovic and Saurabh Bagchi. 2018. VideoChef: Efficient Approximation for Streaming Video Processing Pipelines. In ATC."},{"key":"e_1_2_1_60_1","unstructured":"Shangliang Xu Xinxin Wang Wenyu Lv Qinyao Chang Cheng Cui Kaipeng Deng Guanzhong Wang Qingqing Dang Shengyu Wei Yuning Du and Baohua Lai. 2022. PP-YOLOE: An evolved version of YOLO. arXiv:2203.16250  Shangliang Xu Xinxin Wang Wenyu Lv Qinyao Chang Cheng Cui Kaipeng Deng Guanzhong Wang Qingqing Dang Shengyu Wei Yuning Du and Baohua Lai. 2022. PP-YOLOE: An evolved version of YOLO. arXiv:2203.16250"},{"key":"e_1_2_1_61_1","volume-title":"Luis Materon Botelho, and Felix Xiaozhu Lin","author":"Xu Tiantu","year":"2019","unstructured":"Tiantu Xu , Luis Materon Botelho, and Felix Xiaozhu Lin . 2019 . VStore: A Data Store for Analytics on Large Videos. In EuroSys . Tiantu Xu, Luis Materon Botelho, and Felix Xiaozhu Lin. 2019. VStore: A Data Store for Analytics on Large Videos. In EuroSys."},{"key":"e_1_2_1_62_1","volume-title":"EVA: A Symbolic Approach to Accelerating Exploratory Video Analytics with Materialized Views. In SIGMOD.","author":"Xu Zhuangdi","year":"2022","unstructured":"Zhuangdi Xu , Gaurav Kakker , Joy Arulraj , and Umakishore Ramachandran . 2022 . EVA: A Symbolic Approach to Accelerating Exploratory Video Analytics with Materialized Views. In SIGMOD. Zhuangdi Xu, Gaurav Kakker, Joy Arulraj, and Umakishore Ramachandran. 2022. EVA: A Symbolic Approach to Accelerating Exploratory Video Analytics with Materialized Views. In SIGMOD."},{"key":"e_1_2_1_63_1","doi-asserted-by":"crossref","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. In PVLDB.  Zhihui Yang Zuozhi Wang Yicong Huang Yao Lu Chen Li and X. Sean Wang. 2022. Optimizing Machine Learning Inference Queries with Correlative Proxy Models. In PVLDB.","DOI":"10.14778\/3547305.3547310"},{"key":"e_1_2_1_64_1","volume-title":"Spark: Cluster computing with working sets.. In HotCloud.","author":"Zaharia Matei","year":"2010","unstructured":"Matei Zaharia , Mosharaf Chowdhury , Michael J Franklin , Scott Shenker , and Ion Stoica . 2010 . Spark: Cluster computing with working sets.. In HotCloud. Matei Zaharia, Mosharaf Chowdhury, Michael J Franklin, Scott Shenker, and Ion Stoica. 2010. Spark: Cluster computing with working sets.. In HotCloud."},{"key":"e_1_2_1_65_1","volume":"201","author":"Zhang Haoyu","unstructured":"Haoyu Zhang , Ganesh Ananthanarayanan , Peter Bodik , Matthai Philipose , Paramvir Bahl , and Michael J Freedman. 201 7. Live Video Analytics at Scale with Approximation and Delay-Tolerance. In NSDI. 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 NSDI.","journal-title":"Michael J Freedman."}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3570690.3570695","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,23]],"date-time":"2023-01-23T17:36:34Z","timestamp":1674495394000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3570690.3570695"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11]]},"references-count":64,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,11]]}},"alternative-id":["10.14778\/3570690.3570695"],"URL":"https:\/\/doi.org\/10.14778\/3570690.3570695","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2022,11]]},"assertion":[{"value":"2023-01-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}