{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T09:52:09Z","timestamp":1773481929068,"version":"3.50.1"},"reference-count":72,"publisher":"Association for Computing Machinery (ACM)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2020,10]]},"abstract":"<jats:p>\n            While deep neural networks (DNNs) are an increasingly popular way to query large corpora of data, their significant runtime remains an active area of research. As a result, researchers have proposed systems and optimizations to reduce these costs by allowing users to trade off accuracy and speed. In this work, we examine\n            <jats:italic>end-to-end<\/jats:italic>\n            DNN execution in visual analytics systems on modern accelerators. Through a novel measurement study, we show that the\n            <jats:italic>preprocessing of data<\/jats:italic>\n            (e.g., decoding, resizing) can be the bottleneck in many visual analytics systems on modern hardware.\n          <\/jats:p>\n          <jats:p>\n            To address the bottleneck of preprocessing, we introduce two optimizations for\n            <jats:italic>end-to-end<\/jats:italic>\n            visual analytics systems. First, we introduce novel methods of achieving accuracy and throughput trade-offs by using natively present, low-resolution visual data. Second, we develop a runtime engine for efficient visual DNN inference. This runtime engine a) efficiently pipelines preprocessing and DNN execution for inference, b) places preprocessing operations on the CPU or GPU in a hardware- and input-aware manner, and c) efficiently manages memory and threading for high throughput execution. We implement these optimizations in a novel system, Smol, and evaluate Smol on eight visual datasets. We show that its optimizations can achieve up to 5.9X\n            <jats:italic>end-to-end<\/jats:italic>\n            throughput improvements at a fixed accuracy over recent work in visual analytics.\n          <\/jats:p>","DOI":"10.14778\/3425879.3425881","type":"journal-article","created":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T02:45:23Z","timestamp":1606272323000},"page":"87-100","source":"Crossref","is-referenced-by-count":30,"title":["Jointly optimizing preprocessing and inference for DNN-based visual analytics"],"prefix":"10.14778","volume":"14","author":[{"given":"Daniel","family":"Kang","sequence":"first","affiliation":[{"name":"Stanford DAWN Project"}]},{"given":"Ankit","family":"Mathur","sequence":"additional","affiliation":[{"name":"Stanford DAWN Project"}]},{"given":"Teja","family":"Veeramacheneni","sequence":"additional","affiliation":[{"name":"Stanford DAWN Project"}]},{"given":"Peter","family":"Bailis","sequence":"additional","affiliation":[{"name":"Stanford DAWN Project"}]},{"given":"Matei","family":"Zaharia","sequence":"additional","affiliation":[{"name":"Stanford DAWN Project"}]}],"member":"320","published-online":{"date-parts":[[2020,11,16]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"2018. MLPerf. https:\/\/mlperf.org\/.  2018. MLPerf. https:\/\/mlperf.org\/."},{"key":"e_1_2_1_2_1","unstructured":"2019. NVIDIA TensorRT. https:\/\/developer.nvidia.com\/tensorrt  2019. NVIDIA TensorRT. https:\/\/developer.nvidia.com\/tensorrt"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123982"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001138"},{"key":"e_1_2_1_5_1","unstructured":"Corrado Alessio. 2019. Animals-10. https:\/\/www.kaggle.com\/alessiocorrado99\/animals10  Corrado Alessio. 2019. Animals-10. https:\/\/www.kaggle.com\/alessiocorrado99\/animals10"},{"key":"e_1_2_1_6_1","volume-title":"Predicate Optimization for a Visual Analytics Database. ICDE","author":"Anderson Michael R","year":"2019","unstructured":"Michael R Anderson , Michael Cafarella , Thomas F Wenisch , and German Ros . 2019. Predicate Optimization for a Visual Analytics Database. ICDE ( 2019 ). Michael R Anderson, Michael Cafarella, Thomas F Wenisch, and German Ros. 2019. Predicate Optimization for a Visual Analytics Database. ICDE (2019)."},{"key":"e_1_2_1_7_1","unstructured":"Elizabeth Arens. 2019. Always Up-to-Date Guide to Social Media Image Sizes. https:\/\/sproutsocial.com\/insights\/social-media-image-sizes-guide\/  Elizabeth Arens. 2019. Always Up-to-Date Guide to Social Media Image Sizes. https:\/\/sproutsocial.com\/insights\/social-media-image-sizes-guide\/"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/1162264"},{"key":"e_1_2_1_9_1","volume-title":"Unrestricted adversarial examples. arXiv preprint arXiv:1809.08352","author":"Brown Tom B","year":"2018","unstructured":"Tom B Brown , Nicholas Carlini , Chiyuan Zhang , Catherine Olsson , Paul Christiano , and Ian Goodfellow . 2018. Unrestricted adversarial examples. arXiv preprint arXiv:1809.08352 ( 2018 ). Tom B Brown, Nicholas Carlini, Chiyuan Zhang, Catherine Olsson, Paul Christiano, and Ian Goodfellow. 2018. Unrestricted adversarial examples. arXiv preprint arXiv:1809.08352 (2018)."},{"key":"e_1_2_1_10_1","volume-title":"Scaling Video Analytics on Constrained Edge Nodes. SysML","author":"Canel Christopher","year":"2019","unstructured":"Christopher Canel , Thomas Kim , Giulio Zhou , Conglong Li , Hyeontaek Lim , David Andersen , Michael Kaminsky , and Subramanya Dulloor . 2019. Scaling Video Analytics on Constrained Edge Nodes. SysML ( 2019 ). Christopher Canel, Thomas Kim, Giulio Zhou, Conglong Li, Hyeontaek Lim, David Andersen, Michael Kaminsky, and Subramanya Dulloor. 2019. Scaling Video Analytics on Constrained Edge Nodes. SysML (2019)."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1816038.1815993"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/3291168.3291211"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2996864"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001140"},{"key":"e_1_2_1_16_1","unstructured":"Fran\u00e7ois Chollet et al. 2015. Keras.  Fran\u00e7ois Chollet et al. 2015. Keras."},{"key":"e_1_2_1_17_1","volume-title":"Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark. arXiv preprint arXiv:1806.01427","author":"Coleman Cody","year":"2018","unstructured":"Cody Coleman , Daniel Kang , Deepak Narayanan , Luigi Nardi , Tian Zhao , Jian Zhang , Peter Bailis , Kunle Olukotun , Chris Re , and Matei Zaharia . 2018. Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark. arXiv preprint arXiv:1806.01427 ( 2018 ). Cody Coleman, Daniel Kang, Deepak Narayanan, Luigi Nardi, Tian Zhao, Jian Zhang, Peter Bailis, Kunle Olukotun, Chris Re, and Matei Zaharia. 2018. Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark. arXiv preprint arXiv:1806.01427 (2018)."},{"key":"e_1_2_1_18_1","first-page":"102","article-title":"DAWNBench","volume":"100","author":"Coleman Cody","year":"2017","unstructured":"Cody Coleman , Deepak Narayanan , Daniel Kang , Tian Zhao , Jian Zhang , Luigi Nardi , Peter Bailis , Kunle Olukotun , Chris R\u00e9 , and Matei Zaharia . 2017 . DAWNBench : An End-to-End Deep Learning Benchmark and Competition. Training 100 , 101 (2017), 102 . Cody Coleman, Deepak Narayanan, Daniel Kang, Tian Zhao, Jian Zhang, Luigi Nardi, Peter Bailis, Kunle Olukotun, Chris R\u00e9, and Matei Zaharia. 2017. DAWNBench: An End-to-End Deep Learning Benchmark and Competition. Training 100, 101 (2017), 102.","journal-title":"An End-to-End Deep Learning Benchmark and Competition. Training"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_1_20_1","volume-title":"dMath: Distributed Linear Algebra for DL. arXiv preprint arXiv:1611.07819","author":"Eliuk Steven","year":"2016","unstructured":"Steven Eliuk , Cameron Upright , Hars Vardhan , Stephen Walsh , and Trevor Gale . 2016. dMath: Distributed Linear Algebra for DL. arXiv preprint arXiv:1611.07819 ( 2016 ). Steven Eliuk, Cameron Upright, Hars Vardhan, Stephen Walsh, and Trevor Gale. 2016. dMath: Distributed Linear Algebra for DL. arXiv preprint arXiv:1611.07819 (2016)."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2011.5981829"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00012"},{"key":"e_1_2_1_23_1","volume-title":"GPU technology conference","author":"Gale T","year":"2017","unstructured":"T Gale , S Eliuk , and C Upright . 2017. High-Performance Data Loading and Augmentation for Deep Neural Network Training . In GPU technology conference 2017 . T Gale, S Eliuk, and C Upright. 2017. High-Performance Data Loading and Augmentation for Deep Neural Network Training. In GPU technology conference 2017."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.106"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"e_1_2_1_26_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149","author":"Han Song","year":"2015","unstructured":"Song Han , Huizi Mao , and William J Dally . 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 ( 2015 ). Song Han, Huizi Mao, and William J Dally. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)."},{"key":"e_1_2_1_27_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 , 2980--2988. Kaiming He, Georgia Gkioxari, Piotr Doll\u00e1r, and Ross Girshick. 2017. Mask r-cnn. In ICCV. IEEE, 2980--2988."},{"key":"e_1_2_1_28_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778.  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778."},{"key":"e_1_2_1_29_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton , Oriol Vinyals , and Jeff Dean . 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 ( 2015 ). Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_2_1_30_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). 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_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/3291168.3291188"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080246"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195661"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.14778\/3372716.3372725"},{"key":"e_1_2_1_35_1","unstructured":"Daniel Kang Peter Bailis and Matei Zaharia. 2019. Challenges and Opportunities in DNN-Based Video Analytics: A Demonstration of the BlazeIt Video Query Engine. CIDR.  Daniel Kang Peter Bailis and Matei Zaharia. 2019. Challenges and Opportunities in DNN-Based Video Analytics: A Demonstration of the BlazeIt Video Query Engine. CIDR."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137664"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.14778\/3407790.3407804"},{"key":"e_1_2_1_38_1","volume-title":"Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics. arXiv preprint arXiv:2007.13005","author":"Kang Daniel","year":"2020","unstructured":"Daniel Kang , Ankit Mathur , Teja Veeramacheneni , Peter Bailis , and Matei Zaharia . 2020. Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics. arXiv preprint arXiv:2007.13005 ( 2020 ). Daniel Kang, Ankit Mathur, Teja Veeramacheneni, Peter Bailis, and Matei Zaharia. 2020. Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics. arXiv preprint arXiv:2007.13005 (2020)."},{"key":"e_1_2_1_39_1","volume-title":"XLA: TensorFlow, compiled. TensorFlow Dev Summit","author":"Leary Chris","year":"2017","unstructured":"Chris Leary and Todd Wang . 2017 . XLA: TensorFlow, compiled. TensorFlow Dev Summit (2017). Chris Leary and Todd Wang. 2017. XLA: TensorFlow, compiled. TensorFlow Dev Summit (2017)."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123977"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183751"},{"key":"e_1_2_1_43_1","unstructured":"Peter Mattson Christine Cheng Cody Coleman Greg Diamos Paulius Micikevicius David Patterson Hanlin Tang Gu-Yeon Wei Peter Bailis Victor Bittorf etal 2019. Mlperf training benchmark. arXiv preprint arXiv:1910.01500 (2019).  Peter Mattson Christine Cheng Cody Coleman Greg Diamos Paulius Micikevicius David Patterson Hanlin Tang Gu-Yeon Wei Peter Bailis Victor Bittorf et al. 2019. Mlperf training benchmark. arXiv preprint arXiv:1910.01500 (2019)."},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/VLSIC.2016.7573525"},{"key":"e_1_2_1_45_1","unstructured":"NVIDIA. 2019. NVIDIA DALI. https:\/\/docs.nvidia.com\/deeplearning\/sdk\/dali-developer-guide\/docs\/index.html  NVIDIA. 2019. NVIDIA DALI. https:\/\/docs.nvidia.com\/deeplearning\/sdk\/dali-developer-guide\/docs\/index.html"},{"key":"e_1_2_1_46_1","unstructured":"NVIDIA. 2020. NVIDIA T4 Tensor Core GPU for AI Inference. https:\/\/www.nvidia.com\/en-us\/data-center\/tesla-t4\/  NVIDIA. 2020. NVIDIA T4 Tensor Core GPU for AI Inference. https:\/\/www.nvidia.com\/en-us\/data-center\/tesla-t4\/"},{"key":"e_1_2_1_47_1","volume-title":"Conference on Innovative Data Systems Research (CIDR).","author":"Palkar Shoumik","year":"2017","unstructured":"Shoumik Palkar , James J Thomas , Anil Shanbhag , Deepak Narayanan , Holger Pirk , Malte Schwarzkopf , Saman Amarasinghe , Matei Zaharia , and Stanford InfoLab . 2017 . Weld: A common runtime for high performance data analytics . In Conference on Innovative Data Systems Research (CIDR). Shoumik Palkar, James J Thomas, Anil Shanbhag, Deepak Narayanan, Holger Pirk, Malte Schwarzkopf, Saman Amarasinghe, Matei Zaharia, and Stanford InfoLab. 2017. Weld: A common runtime for high performance data analytics. In Conference on Innovative Data Systems Research (CIDR)."},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080254"},{"key":"e_1_2_1_49_1","volume-title":"An energy-efficient and scalable deep learning\/inference processor with tetra-parallel MIMD architecture for big data applications","author":"Park Seong-Wook","year":"2015","unstructured":"Seong-Wook Park , Junyoung Park , Kyeongryeol Bong , Dongjoo Shin , Jinmook Lee , Sungpill Choi , and Hoi-Jun Yoo . 2015. An energy-efficient and scalable deep learning\/inference processor with tetra-parallel MIMD architecture for big data applications . IEEE transactions on biomedical circuits and systems 9, 6 ( 2015 ), 838--848. Seong-Wook Park, Junyoung Park, Kyeongryeol Bong, Dongjoo Shin, Jinmook Lee, Sungpill Choi, and Hoi-Jun Yoo. 2015. An energy-efficient and scalable deep learning\/inference processor with tetra-parallel MIMD architecture for big data applications. IEEE transactions on biomedical circuits and systems 9, 6 (2015), 838--848."},{"key":"e_1_2_1_50_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017).  Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017)."},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2013.6657019"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.5555\/573326"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201394"},{"key":"e_1_2_1_54_1","unstructured":"PyTorch Team. 2018. The road to 1.0: production ready PyTorch. https:\/\/pytorch.org\/blog\/the-road-to-1_0\/  PyTorch Team. 2018. The road to 1.0: production ready PyTorch. https:\/\/pytorch.org\/blog\/the-road-to-1_0\/"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.5555\/2971808.2972132"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001165"},{"key":"e_1_2_1_57_1","unstructured":"Vijay Janapa Reddi Christine Cheng David Kanter Peter Mattson Guenther Schmuelling Carole-Jean Wu Brian Anderson Maximilien Breughe Mark Charlebois William Chou etal 2019. Mlperf inference benchmark. arXiv preprint arXiv:1911.02549 (2019).  Vijay Janapa Reddi Christine Cheng David Kanter Peter Mattson Guenther Schmuelling Carole-Jean Wu Brian Anderson Maximilien Breughe Mark Charlebois William Chou et al. 2019. Mlperf inference benchmark. arXiv preprint arXiv:1911.02549 (2019)."},{"key":"e_1_2_1_58_1","volume-title":"Missing the Forest for the Trees: End-to-End AI Application Performance in Edge Data Centers. In 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA). IEEE, 515--528","author":"Richins Daniel","year":"2020","unstructured":"Daniel Richins , Dharmisha Doshi , Matthew Blackmore , Aswathy Thulaseedharan Nair , Neha Pathapati , Ankit Patel , Brainard Daguman , Daniel Dobrijalowski , Ramesh Illikkal , Kevin Long , 2020 . Missing the Forest for the Trees: End-to-End AI Application Performance in Edge Data Centers. In 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA). IEEE, 515--528 . Daniel Richins, Dharmisha Doshi, Matthew Blackmore, Aswathy Thulaseedharan Nair, Neha Pathapati, Ankit Patel, Brainard Daguman, Daniel Dobrijalowski, Ramesh Illikkal, Kevin Long, et al. 2020. Missing the Forest for the Trees: End-to-End AI Application Performance in Edge Data Centers. In 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA). IEEE, 515--528."},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080221"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"e_1_2_1_61_1","volume-title":"Efficientnet: Rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc V Le . 2019 . Efficientnet: Rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946 (2019). Mingxing Tan and Quoc V Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946 (2019)."},{"key":"e_1_2_1_62_1","volume-title":"Efficientdet: Scalable and efficient object detection. arXiv preprint arXiv:1911.09070","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan , Ruoming Pang , and Quoc V Le . 2019 . Efficientdet: Scalable and efficient object detection. arXiv preprint arXiv:1911.09070 (2019). Mingxing Tan, Ruoming Pang, and Quoc V Le. 2019. Efficientdet: Scalable and efficient object detection. arXiv preprint arXiv:1911.09070 (2019)."},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.5555\/2588198"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080244"},{"key":"e_1_2_1_65_1","unstructured":"Catherine Wah Steve Branson Peter Welinder Pietro Perona and Serge Belongie. 2011. The caltech-ucsd birds-200-2011 dataset. (2011).  Catherine Wah Steve Branson Peter Welinder Pietro Perona and Serge Belongie. 2011. The caltech-ucsd birds-200-2011 dataset. (2011)."},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/30.125072"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"e_1_2_1_68_1","unstructured":"Hao Wu. 2019. Low Precision Inference on GPU. https:\/\/developer.download.nvidia.com\/video\/gputechconf\/gtc\/2019\/presentation\/s9659-inference-at-reduced-precision-on-gpus.pdf  Hao Wu. 2019. Low Precision Inference on GPU. https:\/\/developer.download.nvidia.com\/video\/gputechconf\/gtc\/2019\/presentation\/s9659-inference-at-reduced-precision-on-gpus.pdf"},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303971"},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.5555\/3154630.3154661"},{"key":"e_1_2_1_72_1","volume-title":"Flow-guided feature aggregation for video object detection. arXiv preprint arXiv:1703.10025","author":"Zhu Xizhou","year":"2017","unstructured":"Xizhou Zhu , Yujie Wang , Jifeng Dai , Lu Yuan , and Yichen Wei . 2017. Flow-guided feature aggregation for video object detection. arXiv preprint arXiv:1703.10025 ( 2017 ). Xizhou Zhu, Yujie Wang, Jifeng Dai, Lu Yuan, and Yichen Wei. 2017. Flow-guided feature aggregation for video object detection. arXiv preprint arXiv:1703.10025 (2017)."}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3425879.3425881","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T11:06:05Z","timestamp":1672225565000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3425879.3425881"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":72,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,10]]}},"alternative-id":["10.14778\/3425879.3425881"],"URL":"https:\/\/doi.org\/10.14778\/3425879.3425881","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2020,10]]}}}