NoScope: optimizing neural network queries over video at scale
Open accessThe DOI matches its Crossref record; 103 of the 103 references it cites were found in a registry or an index.
Abstract
Recent advances in computer vision---in the form of deep neural networks---have made it possible to query increasing volumes of video data with high accuracy. However, neural network inference is computationally expensive at scale: applying a state-of-the-art object detector in real time (i.e., 30+ frames per second) to a single video requires a $4000 GPU. In response, we present N o S cope , a system for querying videos that can reduce the cost of neural network video analysis by up to three orders of magnitude via inference-optimized model search. Given a target video, object to detect, and reference neural network, N o S cope automatically searches for and trains a sequence, or cascade, of models that preserves the accuracy of the reference network but is specialized to the target video and are therefore far less computationally expensive. N o S cope cascades two types of models: specialized models that forego the full generality of the reference model but faithfully mimic its behavior for the target video and object; and difference detectors that highlight temporal differences across frames. We show that the optimal cascade architecture differs across videos and objects, so N o S cope uses an efficient cost-based optimizer to search across models and cascades. With this approach, N o S cope achieves two to three order of magnitude speed-ups (265-15,500x real-time) on binary classification tasks over fixed-angle webcam and surveillance video while maintaining accuracy within 1--5% of state-of-the-art neural networks.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 2×
“In recent times, however, deep neural networks (NNs) [40, 44, 58, 66, 67] have largely displaced classical computer”
BackgroundImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“NOSCOPE implements specialized NNs based on the AlexNet architecture [56] (filter doubling, dropout), using ReLU units for all the hidden layers and a softmax unit at the end to return a confidence for the class we are querying.”
MethodLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803 · cited 19×
“However, even in this video, NOSCOPE can offer an 30× speedup over YOLOv2 with no loss in accuracy.”
BackgroundInfluentialMicrosoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 4×
“geNet 2012 [82]), a variety of SIFT-based bag-of-words classifiers (varying the SIFT parameters), and selective search with a SIFTbased classifier [63] (which performed well on PASCAL VOC [32]).”
BackgroundMethodInfluentialYOLO9000: Better, Faster, Stronger
Redmon, J., & Farhadi, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.690 · Cited by 19,892 · cited 2×
“We used YOLOv2 [80] as our reference model.”
MethodRapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300 · cited 2×
“One of the first cascades, the Viola-Jones detector [90], cascades traditional image processing features; if any classifier is confident about the output, the Viola-Jones cascade short-circuits evaluation, improving execution speed.”
Research works printed but not linked: 24
- Abadi D. J., 2005, CIDR
- Ba J., 2014, NIPS
- Bailis P., 2017, CIDR
- Benenson R., 2014, ECCV
- Chandrasekaran S., 2003, CIDR
- Chaudhuri S., 2007, VLDB
- Chen W., 2015, ICML
- Feichtenhofer C., 2016, NIPS
- 10.5555/2354409.2354978 · doi:10.5555/2354409.2354978
- Gibbs S., 1993, ICDE
- Goodfellow I., 2016, MIT Press
- Han S., 2016, ICLR
- Hinton G., 2014, NIPS
- Idreos S., 2007, CIDR
- Kraska T., 2013, CIDR
- Krizhevsky A., 2012, NIPS
- 10.5555/850924.851523 · doi:10.5555/850924.851523
- Metz C., 2017, Wired
- Patait A., 2016, 2016 GPU Technology Conference (https://goo.gl/Bdjdgm)
- Ren S., 2015, NIPS
- Yue-Hei Ng J., 2015, CVPR, 53
- Zhang H., 2017, NSDI
- Zhanget S., 2016, CVPR
- Zoph B., 2017, ICLR
Cited by
Items 101–200 of 469
Xu, R., Lee, J., Wang, P., Bagchi, S., Li, Y., & Chaterji, S. (2022) · European Conference on Computer Systems · doi:10.1145/3492321.3519577 · Cited by 35
Toward an Online Continual Learning Architecture for Intrusion Detection of Video Surveillance
Kwon, B., & Kim, T. (2022) · IEEE Access · doi:10.1109/access.2022.3201139 · Cited by 35
Trine: Cloud-Edge-Device Cooperated Real-Time Video Analysis for Household Applications
Zhao, Y., Yang, Z., He, X., Cai, X., Miao, X., & Ma, Q. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3154721 · Cited by 31
BlinkML: Efficient Maximum Likelihood Estimation with Probabilistic Guarantees
Park, Y., Qing, J., Shen, X., & Mozafari, B. (2019) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3299869.3300077 · Cited by 34
“NoScope [58], tKDC [46], and NSH [83] speed up the prediction at the cost of more preprocessing.”
BackgroundKaur, B., & Bhattacharya, J. (2019) · Journal of Electronic Imaging · doi:10.1117/1.jei.28.1.013031 · Cited by 29
Visual Road: A Video Data Management Benchmark
Haynes, B. M., Mazumdar, A., Bałazińska, M., Ceze, L., & Cheung, A. (2019) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3299869.3324955 · Cited by 33
Panorama: a data system for unbounded vocabulary querying over video
Zhang, Y., & Kumar, A. (2019) · Proceedings of the VLDB Endowment · doi:10.14778/3372716.3372721 · Cited by 34
VSS: A Storage System for Video Analytics
Haynes, B. M., Daum, M., He, D., Mazumdar, A., Bałazińska, M., Cheung, A., & Ceze, L. (2021) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3448016.3459242 · Cited by 35
“To support this video data deluge, many systems and applications have emerged to ingest, transform, and reason about such data [18, 22, 24, 26, 27, 33, 42, 55].”
BackgroundMethodOTIF: Efficient Tracker Pre-processing over Large Video Datasets
Bastani, F., & Madden, S. R. (2022) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3514221.3517835 · Cited by 40
ExSample: Efficient Searches on Video Repositories through Adaptive Sampling
Moll, O., Bastani, F., Madden, S. R., Stonebraker, M., Gadepally, V. N., & Kraska, T. (2022) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde53745.2022.00266 · Cited by 31
“approaches such as principal component analysis and feature hashing to eciently skip processing of video frames that the classiers are condent do not contain objects relevant to the query. NoScope [9] trains specialized approximations to expensive CNNs while maintaining accuracy levels within a user-dened window. Howe…”
BackgroundPRETZEL: Opening the Black Box of Machine Learning Prediction Serving SystemsPreprint
Lee, Y., Scolari, A., Chun, B.-G., Santambrogio, M. D., Weimer, M., & Interlandi, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.06115 · Cited by 31
A Decade of Video Analytics at Edge: Training, Deployment, Orchestration, and Platforms
Bai, T., Zhao, H., Huang, L., Wang, Z., Kim, D. I., & Nallanathan, A. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3563377 · Cited by 43
Wang, X., Gao, G., Wu, X., Lyu, Y., & Wu, W. (2022) · International Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV) · doi:10.1145/3534088.3534352 · Cited by 28
“Noscope [6] designed a system that trains some small network models and a dierence detector to reduce model inference cost.”
BackgroundXarchakos, I., & Koudas, N. (2019) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3299869.3320230 · Cited by 25
Live Video Analytics with FPGA-based Smart Cameras
Wang, S., Zhang, C., Shu, Y., & Liu, Y. (2019) · doi:10.1145/3349614.3356027 · Cited by 26
“Many systems are designed to use a combination of cameras, edge clusters, and cloud resources to analyze video streams [9–12], including low-cost model design [10, 13, 14], partitioned processing [15–18], adaptation [9, 19, 20] and computation/memory sharing [21–23].”
BackgroundDeepSplit: Dynamic Splitting of Collaborative Edge-Cloud Convolutional Neural Networks
Mehta, R., & Shorey, R. (2020) · International Conference on Communication Systems & Networks (COMSNETS) · doi:10.1109/comsnets48256.2020.9027432 · Cited by 27
Irina: Accelerating DNN Inference with Efficient Online Scheduling
Wu, X., Xu, H. L., & Wang, Y. (2020) · Asia-Pacific Workshop on Networking (APNet) · doi:10.1145/3411029.3411035 · Cited by 32
“, [14, 27]) to opportunistically avoid expensive DNN inference on most video frames.”
BackgroundYadav, P., Salwala, D., & Curry, E. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3075336 · Cited by 28
Patel, L., Jha, S., Pan, M., Gupta, H., Asawa, P., Guestrin, C., & Zaharia, M. (2025) · Proceedings of the VLDB Endowment · doi:10.14778/3749646.3749685 · Cited by 23
Self-citationSeiden: Revisiting Query Processing in Video Database Systems
Bang, J., Kakkar, G. T., Chunduri, P., Mitra, S., & Arulraj, J. J. P. (2023) · Proceedings of the VLDB Endowment · doi:10.14778/3598581.3598599 · Cited by 23
Edge Intelligence in the Making: Optimization, Deep Learning, and Applications
Lin, S., Zhou, Z., Zhang, Z., Chen, X., & Zhang, J. (2020) · Synthesis lectures on learning, networks, and algorithms · doi:10.2200/s01054ed1v01y202009lna025 · Cited by 25
Incremental and Approximate Computations for Accelerating Deep CNN Inference
Nakandala, S., Nagrecha, K., Kumar, A., & Papakonstantinou, Y. (2020) · ACM Transactions on Database Systems · doi:10.1145/3397461 · Cited by 26
“ORV is gaining popularity due to the mass deployment of video cameras in applications such as security surveillance [15], traffic monitoring [16], and tracking animal species in the wild [6].”
BackgroundMethodMulti-user Edge-assisted Video Analytics Task Offloading Game based on Deep Reinforcement Learning
Chen, Y., Zhang, S., Xiao, M., Qian, Z., Wu, J., & Lu, S. (2020) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads51040.2020.00044 · Cited by 24
FrameHopper: Selective Processing of Video Frames in Detection-driven Real-Time Video Analytics
Arefeen, M. A., Nimi, S. T., & Uddin, M. Y. S. (2022) · International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT) · doi:10.1109/dcoss54816.2022.00033 · Cited by 31
A Feedback-Driven DNN Inference Acceleration System for Edge-Assisted Video Analytics
Lv, X., Wang, Q., Chen, Y., & Jin, H. (2023) · IEEE Transactions on Computers · doi:10.1109/tc.2023.3275094 · Cited by 23
Dai, X., Zhang, Z., Yang, P., Xu, Y., Liu, X., & Lui, J. C. S. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681269 · Cited by 25
Databases Unbound: Querying All of the World's Bytes with AI
Madden, S., Cafarella, M., Franklin, M. J. M., & Kraska, T. (2024) · Proceedings of the VLDB Endowment · doi:10.14778/3685800.3685916 · Cited by 30
Joint Model and Data Adaptation for Cloud Inference Serving
Jiang, J., Luo, Z., Hu, C., He, Z., Wang, Z., Xia, S., & Wu, C. (2021) · IEEE Real-Time Systems Symposium (RTSS) · doi:10.1109/rtss52674.2021.00034 · Cited by 27
A Novel Efficient Multi-View Traffic-Related Object Detection Framework
Yang, K., Liu, J., Yang, D., Wang, H., Sun, P., Zhang, Y., Liu, Y., & Song, L. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095027 · Cited by 21
Extract-Transform-Load for Video Streams
Kossmann, F., Wu, Z., Lai, E. Y., Tatbul, N., Cao, L., Kraska, T., & Madden, S. R. (2023) · Proceedings of the VLDB Endowment · doi:10.14778/3598581.3598600 · Cited by 27
Adaptive Lightweight Regularization Tool for Complex Analytics
Luo, Z., Cai, S., Gao, J., Zhang, M., Ngiam, K. Y., Chen, G., & Lee, W.-C. (2018) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde.2018.00051 · Cited by 26
“Recent developments in Deep Learning and Machine Learning technology [1], [2], [3] have led to a series of breakthroughs in many real world applications [4], [5], [6], [7].”
BackgroundData Management in Machine Learning Systems
Böehm, M., Kumar, A., & Yang, J. (2019) · Synthesis lectures on data management · doi:10.2200/s00895ed1v01y201901dtm057 · Cited by 25
Video Analytics with Zero-streaming CamerasPreprint
Xu, M., Xu, T., Liu, Y., & Lin, F. X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.12342 · Cited by 37
Poster: MobiSR -- Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors
Lee, R., Venieris, S. I., Dudziak, Ł., Bhattacharya, S., & Lane, N. D. (2019) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3300061.3343410 · Cited by 43
Perceptual Compression for Video Storage and Processing Systems
Mazumdar, A., Haynes, B. M., Bałazińska, M., Ceze, L., Cheung, A., & Oskin, M. (2019) · ACM Symposium on Cloud Computing (SoCC) · doi:10.1145/3357223.3362725 · Cited by 25
Visage: enabling timely analytics for drone imagery
Jha, S., Li, Y., Noghabi, S. A., Ranganathan, V. N., Kumar, P., Nelson, A., Toelle, M., Sinha, S. N., Chandra, R., & Badam, A. (2021) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3447993.3483273 · Cited by 21
CaTDet: Cascaded Tracked Detector for Efficient Object Detection from VideoPreprint
Mao, H., Kong, T., & Dally, W. J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.00434 · Cited by 20
On Efficient Approximate Queries over Machine Learning Models
Ding, D., Amer-Yahia, S., & Lakshmanan, L. V. S. (2022) · Proceedings of the VLDB Endowment · doi:10.14778/3574245.3574273 · Cited by 23
Model Selection for Latency-Critical Inference Serving
Mendoza, D., Romero, F., & Trippel, C. (2024) · European Conference on Computer Systems · doi:10.1145/3627703.3629565 · Cited by 28
A convolutional feature map-based deep network targeted towards traffic detection and classification
Kaur, B., & Bhattacharya, J. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.01.014 · Cited by 19
Model slicing for supporting complex analytics with elastic inference cost and resource constraints
Cai, S., Chen, G., Ooi, B. C., & Gao, J. (2019) · Proceedings of the VLDB Endowment · doi:10.14778/3364324.3364325 · Cited by 22
Evaluating Temporal Queries Over Video Feeds
Chen, Y., Yu, X., Koudas, N., & Yu, Z. (2021) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3448016.3452803 · Cited by 22
Enomoro, S., & Eda, T. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i8.16900 · Cited by 30
SmartFilter: An Edge System for Real-Time Application-Guided Video Frames Filtering
Tchaye-Kondi, J., Zhai, Y., Shen, J., Dong, L., & Zhu, L. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3188518 · Cited by 20
Multi-View Scheduling of Onboard Live Video Analytics to Minimize Frame Processing Latency
Liu, S., Wang, T., Guo, H., Fu, X., David, P., Wigness, M., Misra, A., & Abdelzaher, T. (2022) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs54860.2022.00055 · Cited by 26
“Centralized video processing approaches [2]–[5], where camera video streams are transferred for DNN execution to a powerful cloud server, impose significant bandwidth and energy overheads and also suffer from higher communication latency and privacy concerns.”
BackgroundEnhancing Video Analytics Accuracy via Real-time Automated Camera Parameter Tuning
Paul, S., Rao, K., Coviello, G., Sankaradas, M., Po, O., Hu, Y., & Chakradhar, S. (2022) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3560905.3568527 · Cited by 22
DeepLens: Towards a Visual Data Management SystemPreprint
Krishnan, S., Dziedzic, A., & Elmore, A. J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.07607 · Cited by 23
Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning InferencePreprint
Kraft, P., Kang, D. D., Narayanan, D., Palkar, S., Bailis, P. D., & Zaharia, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.01974 · Cited by 27
Self-citationAdaptive Network Configuration for Efficient and Accurate Neural Video Inference
Yang, P., Cheng, Y., Zhang, N., Cheng, Q., & Yu, L. (2023) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2023.3320879 · Cited by 18
Improving Data Analytics with Fast and Adaptive Regularization
Luo, Z., Cai, S., Chen, G., Gao, J., Lee, W.-C., Ngiam, K. Y., & Zhang, M. (2019) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2019.2916683 · Cited by 20
Metadata Representations for Queryable Repositories of Machine Learning Models
Li, Z., Kant, H., Hai, R., Katsifodimos, A., Brambilla, M., & Bozzon, A. (2023) · IEEE Access · doi:10.1109/access.2023.3330647 · Cited by 18
Accelerating Deep Learning Inference via Learned CachesPreprint
Balasubramanian, A., Kumar, A., Liu, Y., Cao, H., Venkataraman, S., & Akella, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.07344 · Cited by 25
Towards automatic model specialization for edge video analytics
Rivas, D., Guim, F., Polo, J., Silva, P. M., Berral, J. L., & Carrera, D. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.03.039 · Cited by 20
Adaptive On-Device Model Update for Responsive Video Analytics in Adverse Environments
Kong, Y.-X., Yang, P., & Cheng, Y. (2025) · IEEE transactions on circuits and systems for video technology (Print) · doi:10.1109/tcsvt.2024.3466524 · Cited by 20
Artificial intelligence in edge devices
Singh, A., Saini, K., Nagar, V., Aseri, V., Sankhla, M. S., Pandit, P. P., & Chopade, R. L. (2022) · Advances in computers · doi:10.1016/bs.adcom.2022.02.013 · Cited by 22
EQUI-VOCAL: Synthesizing Queries for Compositional Video Events from Limited User Interactions
Zhang, E., Daum, M., He, D., Haynes, B. M., Krishna, R., & Bałazińska, M. (2023) · Proceedings of the VLDB Endowment · doi:10.14778/3611479.3611482 · Cited by 27
“Although video database management systems (VDBMSs) have recently re-emerged as an active research area to support these applications [3, 5, 17, 21, 34, 35, 42], existing systems fall short of supporting many use cases.”
BackgroundNetworked Cameras Are the New Big Data Clusters
Jiang, J., Zhou, Y., Ananthanarayanan, G., Shu, Y., & Chien, A. A. (2019) · doi:10.1145/3349614.3356026 · Cited by 21
“, [25, 42, 50]), so not all models need to be called for each frame.”
BackgroundInfluentialTowards Performance Clarity of Edge Video AnalyticsPreprint
Xiao, Z., Xia, Z., Zheng, H.-T., Zhao, B. Y., & Jiang, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.08694 · Cited by 19
FFS-VA: A Fast Filtering System for Large-scale Video Analytics
Zhang, C., Cao, Q., Jiang, H., Zhang, W., Li, J., & Yao, J. (2018) · Proceedings of the 47th International Conference on Parallel Processing · doi:10.1145/3225058.3225103 · Cited by 16
“Using SNM for rapid image recognition in this case can ensure the accuracy to be over 95% [7].”
MethodInfluentialEVA: An End-to-End Exploratory Video Analytics System
Kakkar, G. T., Cao, J., Chunduri, P., Xu, Z., Vyalla, S. R., Dintyala, P., Prabakaran, A., Bang, J., Sengupta, A., Ravichandran, K., et al. (2023) · Workshop on Data Management for End-to-End Machine Learning (DEEM) · doi:10.1145/3595360.3595858 · Cited by 23
SmartLite: A DBMS-Based Serving System for DNN Inference in Resource-Constrained Environments
Lin, Q., Wu, S., Zhao, J., Dai, J., Shi, M., Chen, G., & Li, F. (2023) · Proceedings of the VLDB Endowment · doi:10.14778/3632093.3632095 · Cited by 20
Accelerated Neural Enhancement for Video Analytics With Video Quality Adaptation
Mi, L., Yuan, T., Wang, W., Dai, H., Sun, L., Zheng, J., Chen, G., & Fu, X. (2024) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2024.3375108 · Cited by 21
Gecko: Resource-Efficient and Accurate Queries in Real-Time Video Streams at the Edge
Wang, L., Qu, X., Wang, J., Li, G., Wan, J., Zhang, N., Guo, S., & Xiao, J. Z. (2024) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom52122.2024.10621399 · Cited by 18
SVQ++: Querying for Object Interactions in Video Streams
Chao, D., Koudas, N., & Xarchakos, I. (2020) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3318464.3384701 · Cited by 16
“Most of the state-of-the-art video query processing models focus on the queries about the number of classified objects and their location relationships [5, 6, 10].”
BackgroundA Method for Optimizing Opaque Filter Queries
He, W., Anderson, M. R., Strome, M. B., & Cafarella, M. (2020) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3318464.3389766 · Cited by 23
“Unfortunately, these methods are often not general-purpose, such as a frame-differencing method that works with video from stationary cameras [20].”
BackgroundInfluentialPrivid: Practical, Privacy-Preserving Video Analytics QueriesPreprint
Cangialosi, F., Agarwal, N., Arun, V., Jiang, J., Narayana, S., Sarwate, A. D., & Netravali, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.12083 · Cited by 20
“While these trends enable a variety of important applications [2,10,12,13] and fuel much work in the systems community [24, 27, 34, 37, 38, 41, 42, 47, 63], they also enable privacy intrusions at an unprecedented level [7, 53].”
BackgroundTURBO: Utility-Aware Bandwidth Allocation for Cloud-Augmented Autonomous Control
Schafhalter, P., Krentsel, A., Wei, H., Gonzalez, J. E., Ratnasamy, S., Shenker, S., & Stoica, I. (2025) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/oasics.nines.2026.18 · Cited by 17
ARISE: High-Capacity AR Offloading Inference Serving via Proactive Scheduling
Kong, Z. J., Xu, Q., & Hu, Y. (2024) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3643832.3661894 · Cited by 21
Wang, H., Li, T., Zhang, M., Li, Q., Cui, H., Jiang, Y., & Yuan, Z. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3465434 · Cited by 17
Indoor Video Flame Detection Based on Lightweight Convolutional Neural Network
Yang, Z., Bu, L., Wang, T., Yuan, P., & Ouyang, J. (2020) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661820030293 · Cited by 16
Spatial and temporal constrained ranked retrieval over videos
Chen, Y., Koudas, N., Yu, X., & Yu, Z. (2022) · Proceedings of the VLDB Endowment · doi:10.14778/3551793.3551865 · Cited by 19
“3551865 pipeline in the literature falls under two broad categories; one is to accelerate query answering via filtering based on cheap approximate filters utilizing DLmodels [20, 25, 48], while another approach applies CV algorithms as a pre-processing step and works on the extracted data only [8, 9].”
BackgroundMethodInfluentialTowards Data-Efficient Continuous Learning for Edge Video Analytics via Smart Caching
Zhang, L., Gao, G., & Zhang, H. (2022) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3560905.3568430 · Cited by 15
“Moreover, the models deployed on the edge devices are always compressed with fewer parameters and layers [13], which makes the on-edge deployed models more prone to the data drift issue under the unseen scenarios [3].”
BackgroundMethodAdapting Neural Networks at Runtime: Current Trends in At-Runtime Optimizations for Deep Learning
Sponner, M., Waschneck, B., & Kumar, A. S. (2024) · ACM Computing Surveys · doi:10.1145/3657283 · Cited by 24
Vaas: video analytics at scale
Bastani, F., Moll, O., & Madden, S. (2020) · Proceedings of the VLDB Endowment · doi:10.14778/3415478.3415498 · Cited by 22
“Additionally, Vaas incorporates recent work in approximate video query processing techniques, including probabilistic predicates [4, 5, 6] and variable framerate tracking [7], as well as an incremental query execution architecture, to ensure that interface interactions are fast and to rapidly execute queries over enti…”
MethodZeus: Efficiently Localizing Actions in Videos using Reinforcement Learning
Chunduri, P., Bang, J., Lu, Y., & Arulraj, J. J. P. (2022) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3514221.3526181 · Cited by 15
“Segment-PP extends the frame-level filtering optimization used in existing VDBMSs [15, 16, 22] to segments.”
BackgroundMethodInfluentialINFaaS: Managed & Model-less Inference ServingPreprint
Romero, F., Li, Q., Yadwadkar, N. J., & Kozyrakis, C. (2019) · arXiv (Cornell University) · Cited by 19
Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees
Zeighami, S., Shankar, S., & Parameswaran, A. (2025) · Proceedings of the ACM on Management of Data · doi:10.1145/3769776 · Cited by 30
Accelerating Aggregation Queries on Unstructured Streams of Data
Russo, M., Hashimoto, T., Kang, D. D., Sun, Y. J., & Zaharia, M. (2023) · Proceedings of the VLDB Endowment · doi:10.14778/3611479.3611496 · Cited by 14
Self-citationEdge-Based Discovery of Training Data for Machine Learning
Feng, Z., George, S., Harkes, J., Pillai, P. S., Klatzky, R. L., & Satyanarayanan, M. (2018) · IEEE/ACM Symposium on Edge Computing (SEC) · doi:10.1109/sec.2018.00018 · Cited by 14
“There has been recent work on the use of teacher models for early discard in computer vision [38], [39].”
BackgroundSommelier: Curating DNN Models for the Masses
Guo, P., Hu, B., & Hu, W. (2022) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3514221.3526173 · Cited by 25
Turbo: Opportunistic Enhancement for Edge Video Analytics
Lu, Y., Jiang, S., Cao, T., & Shu, Y. (2022) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3560905.3568501 · Cited by 21
Live video analytics as a service
Apostolo, G. H., Bauszat, P., Nigade, V., Bal, H. E., & Wang, L. (2022) · Workshop on Machine Learning and Systems (EuroMLSys) · doi:10.1145/3517207.3526973 · Cited by 15
Maxim: DRL-Based Cross-Camera Streaming Configuration for Real-Time Video Analytics
Zhang, R., Zhou, Y., Wang, F., & Wang, Z. (2022) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme52920.2022.9859614 · Cited by 14
SiEVE: Semantically Encoded Video Analytics on Edge and Cloud
Elgamal, T., Shi, S., Gupta, V., Jana, R., & Nahrstedt, K. (2020) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs47774.2020.00182 · Cited by 15
Zaarour, T., Bhattacharya, A., & Curry, E. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3158088 · Cited by 16
Learned Indexes for Dynamic WorkloadsPreprint
Tang, C., Dong, Z., Wang, M., Wang, Z., & Chen, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.00655 · Cited by 13
DeepStream: Bandwidth Efficient Multi-Camera Video Streaming for Deep Learning AnalyticsPreprint
Guo, H., Tian, B., Yang, Z., Chen, B., Zhou, Q., Liu, S., Nahrstedt, K., & Danilov, C. B. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.15129 · Cited by 13
“Reducto[18], NoScope[17] and FilterForward[8] design image features basedmodels or light computer visionmodels to determine whether frames can be filtered out or not.”
BackgroundKosaian, J., Phanishayee, A., Philipose, M., Dey, D., & Vinayak, R. (2021) · International Conference on Machine Learning · Cited by 31
Top-K Deep Video Analytics: A Probabilistic Approach
Lai, Z., Han, C., Liu, C., Zhang, P., Lo, E., & Kao, B. (2021) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3448016.3452786 · Cited by 18
“Such developments have created great demands on practical analytics over video data [9, 37, 38, 52, 66].”
BackgroundMethodInfluentialRALF: Accuracy-Aware Scheduling for Feature Store Maintenance
Wooders, S., Mo, X., Narang, A., Lin, K., Stoica, I. G., Hellerstein, J. M., Crooks, N., & Gonzalez, J. E. (2023) · Proceedings of the VLDB Endowment · doi:10.14778/3632093.3632116 · Cited by 15
Featurized-Decomposition Join: Low-Cost Semantic Joins with Guarantees
Zeighami, S., Shankar, S., & Parameswaran, A. (2026) · Proceedings of the VLDB Endowment · doi:10.14778/3836663.3836672 · Cited by 13
Croesus: Multi-Stage Processing and Transactions for Video-Analytics in Edge-Cloud Systems
Gazzaz, S., Chakraborty, V., & Nawab, F. (2022) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde53745.2022.00114 · Cited by 14
BiSwift: Bandwidth Orchestrator for Multi-Stream Video Analytics on Edge
Sun, L., Wang, W., Yuan, T., Mi, L., Dai, H., Liu, Y., & Fu, X. (2024) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom52122.2024.10621392 · Cited by 20
Data Analytics Service Composition and Deployment on Edge Devices
Zhao, J., Tiplea, T., Mortier, R., Crowcroft, J., & Wang, L. (2018) · doi:10.1145/3229607.3229615 · Cited by 11
Movement Tracks for the Automatic Detection of Fish Behavior in VideosPreprint
McIntosh, D., Marques, T. P., Albu, A. B., Rountree, R. A., & Leo, F. C. D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.14070 · Cited by 11
“Future work will address more fish behaviors (e.g. predation, spawining) and will adapt DL-based event detectors such as ReMotENet [15] and NoScope [24] to that end.”
BackgroundMethodInfluentialExpanding the Edge: Enabling Efficient Winograd CNN Inference With Deep Reuse on Edge Device
Zhang, F., Wu, R., Guan, J., Zheng, Z., Guo, X., Zhang, X., Du, X., & Shen, X. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3269017 · Cited by 10
Empower Vision Applications with LoRA LMM
Mi, L., Wang, W., Tu, W., He, Q., Kong, R., Fang, X., Dong, Y., Zhang, Y., Li, Y., Li, M., et al. (2025) · European Conference on Computer Systems · doi:10.1145/3689031.3717472 · Cited by 50
ExSample: Efficient Searches on Video Repositories through Adaptive Sampling
Moll, O., Bastani, F., Madden, S. R., Stonebraker, M., Gadepally, V. N., & Kraska, T. (2022) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde53745.2022.00275 · Cited by 22
MicroEdge: a multi-tenant edge cluster system architecture for scalable camera processing
Cao, D., Yoo, J., Xu, Z., Saurez, E., Gupta, H., Krishna, T., & Ramachandran, U. (2022) · International Middleware Conference · doi:10.1145/3528535.3565254 · Cited by 10
Hu, C., Peters, A., & Kang, D. D. (2024) · Proceedings of the VLDB Endowment · doi:10.14778/3705829.3705843 · Cited by 10
Self-citation
Metadata
- Authors
- Kang, D., Emmons, J., Abuzaid, F., Bailis, P., & Zaharia, M.
- Affiliations
- Stanford University (US)
- Venue
- Proceedings of the VLDB Endowment
- Published
- 2017-08
- Volume
- 10
- Issue
- 11
- Pages
- 1586-1597
- ISSN
- 2150-8097 (ISSN-L)
- OpenAlex
- W2752236330
- Cited by
- 367
- References
- 97
- Citations by year
- 2026: 23 · 2025: 33 · 2024: 35 · 2023: 40 · 2022: 60 · 2021: 49 · 2020: 45 · 2019: 53 · 2018: 28 · 2017: 1
- FWCI
- 14.42
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by-sa
- Locations
- Proceedings of the VLDB Endowment (publishedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Information Systems › Advanced Database Systems and Queries
- Keywords
- object detection, inference optimization, model search, cascade model, cost-based optimization, real-time video analysis, surveillance video, webcam video, binary classification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.