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 301–400 of 469
Optimizing Machine Learning Inference Queries for Multiple Objectives
Li, Z., Schönfeld, M., Hai, R., Bozzon, A., & Katsifodimos, A. (2023) · IEEE International Conference on Data Engineering Workshops (ICDEW) · doi:10.1109/icdew58674.2023.00017 · Cited by 4
COUPLE: Accelerating Video Analytics on Heterogeneous Mobile Processors
Bao, H., Zhou, Z., Xie, J., Huang, Q., Xu, F., & Chen, X. (2023) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3570361.3615749 · Cited by 3
Adaptive Scheduling for Edge-Assisted DNN Serving
He, J., Yang, C., He, Z., Baig, G., & Qiu, L. (2023) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass58611.2023.00071 · Cited by 3
EdgeMA: Model Adaptation System for Real-Time Video Analytics on Edge Devices
Wang, L., Zhang, N., Qu, X., Wang, J., Wan, J., Li, G., Hu, K., Jiang, G., & Xiao, J. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8079-6_23 · Cited by 3
Kossoski, C., Simão, J. M., & Lopes, H. S. (2024) · Applied Sciences · doi:10.3390/app14093566 · Cited by 3
COUPLE: Orchestrating Video Analytics on Heterogeneous Mobile Processors
Bao, H., Zhou, Z., Xu, F., & Chen, X. (2024) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde60146.2024.00128 · Cited by 5
Optimizing Video Queries with Declarative Clues
Chao, D., Chen, Y., Koudas, N., & Yu, X. (2024) · Proceedings of the VLDB Endowment · doi:10.14778/3681954.3681998 · Cited by 4
“We demonstrate how this can be adapted in our framework and also extend it to allow for the substitution of multiple models, not just one.”
BackgroundMethodInfluentialAdaptive Filtering of Visual Content in Distributed Publish/Subscribe Systems
Zaarour, T., & Curry, E. (2019) · IEEE International Symposium on Network Computing and Applications (NCA) · doi:10.1109/nca.2019.8935050 · Cited by 3
Dynamic prioritization of surveillance video data in real-time automated detection systems
Cameron, J. A. D., Kaye, M. E., & Scheme, E. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113672 · Cited by 3
MOTrack: Real-time Configuration Adaptation for Video Analytics through Movement Tracking
Wu, F., Gao, L., Zhou, T., & Wang, X. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685159 · Cited by 3
“MCDNN [4], NoScope [17] and Focus [18] optimize video analytics with resource-light specialized DNN models to detect objects.”
MethodData-Side Efficiencies for Lightweight Convolutional Neural NetworksPreprint
Cao, B. B., O’Gorman, L., Coss, M. J., & Jain, S. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.13057 · Cited by 3
Edge AI Enabled Real-Time Video Analytics: A Full-Lifecycle PerspectivePreprint
Wang, X., Zhao, Z., Min, G., Wang, Z., & Wang, Z. (2025) · doi:10.36227/techrxiv.175744961.11927967/v1 · Cited by 3
Deep Research is the New Analytics System: Towards Building the Runtime for AI-Driven AnalyticsPreprint
Russo, M., & Kraska, T. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.02751 · Cited by 3
Huang, Y., Zharfan, F., Hendrawan, H., Gunawi, H. S., & Jiang, J. (2024) · IEEE International Conference on Edge Computing and Communications (EDGE) · doi:10.1109/edge62653.2024.00017 · Cited by 4
CamTuner: Adaptive Video Analytics Pipelines via Real-Time Automated Camera Parameter Tuning
Paul, S., Rao, K., Coviello, G., Sankaradas, M., Hu, Y., & Chakradhar, S. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3540667 · Cited by 3
ARC: Approximate Relevant Clip Query in Large-Scale Video Repositories
Chen, Y., Jing, Y., Yu, Z., Yu, X., He, Z., Zhang, K., & Wang, X. S. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3729896 · Cited by 3
“In terms of query optimization, the computational cost is effectively reduced through techniques such as model specialization [11, 15, 20], operator result reuse [34], and adaptive sampling [16, 28, 38].”
InfluentialScaling bitrate in video compression using tuned parameters for efficient video analytics
Masykuroh, K., Hendrawan, H., & Mulyana, E. (2025) · Telematics and Informatics Reports · doi:10.1016/j.teler.2025.100274 · Cited by 3
Energy-efficient real-time vehicle detection using hybrid conditional frame skipping with YOLOv8
Sancar, Y., & Yıldırım, E. O. (2026) · ICT Express · doi:10.1016/j.icte.2026.07.004 · Cited by 2
Spider: Next generation Live Video Analytics over Millimeter-Wave Networks
Li, Z., Shu, Y., Ananthanarayanan, G., Shangguan, L., Jamieson, K., & Bahl, V. (2020) · Cited by 3
Wakatsuki, T., Kanai, S., & Fujiwara, Y. (2021) · Proceedings of Machine Learning and Systems · Cited by 4
Data Exchange Mechanism for Real-Time Object Detection in Cloud-Edge IoT System
Miao, W., Zeng, Z., Huang, J. L., Li, S., Xia, Y., Bi, S., & Wang, X. (2023) · Wireless Communications and Mobile Computing · doi:10.1155/2023/3842738 · Cited by 2
“Current video query systems, including Noscope [2], Focus, and Blazeit [9], specifically optimize large video queries and use neural networks to significantly improve query performance [10–12].”
BackgroundSVQ-ACT: Querying for Actions over Videos
Chao, D., Chen, K., & Koudas, N. (2023) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde55515.2023.00277 · Cited by 2
Elixir: A System to Enhance Data Quality for Multiple Analytics on a Video Stream
Paul, S., Rao, K., Coviello, G., Sankaradas, M., Hu, Y., & Chakradhar, S. (2023) · IEEE International Conference on Smart Computing · doi:10.1109/smartcomp58114.2023.00030 · Cited by 2
Scaling a Declarative Cluster Manager Architecture with Query Optimization Techniques
Rong, K., Budiu, M., Skiadopoulos, A., Suresh, L., & Tai, A. (2023) · Proceedings of the VLDB Endowment · doi:10.14778/3603581.3603599 · Cited by 2
PAINE Demo: Optimizing Video Selection Queries with Commonsense Knowledge
He, W., Sabek, I., Lou, Y., & Cafarella, M. (2023) · Proceedings of the VLDB Endowment · doi:10.14778/3611540.3611581 · Cited by 2
AIDB: a Sparsely Materialized Database for Queries using Machine Learning
Jin, T., Mittal, A., Mo, C., Fang, J., Zhang, C., Dai, T., & Kang, D. D. (2024) · Workshop on Data Management for End-to-End Machine Learning (DEEM) · doi:10.1145/3650203.3663329 · Cited by 3
Self-citationA Caching-based Framework for Scalable Temporal Graph Neural Network Training
Li, Y., Shen, Y., Chen, L., & Yuan, M. (2024) · ACM Transactions on Database Systems · doi:10.1145/3705894 · Cited by 3
“Such techniques have been adopted in a wide range of ML lifecycle management systems such as data versioning [10, 11], model management [55, 81], feature selection [58, 59, 74, 77, 98], model training [45, 56, 84], model serving [19, 40, 43], and model diagnosis [80].”
High-Throughput Ingestion for Video Warehouse: Comprehensive Configuration and Effective Exploration
Zhang, B., Li, H., Zhang, D., Li, H., Tan, K., & Chen, G. (2025) · Proceedings of the ACM on Management of Data · doi:10.1145/3725407 · Cited by 2
“NoScope [15] pioneers the use of smaller, faster specialized networks to improve model inference speed.”
Data-Driven Windows to Accelerate Video Stream Content Extraction in Complex Event Processing
Yadav, P., Das, D. P., & Curry, E. (2019) · International Middleware Conference · doi:10.1145/3366627.3368115 · Cited by 2
A query engine for zero-streaming cameras
Xu, M., Xu, T., Liu, Y., Liu, X., Huang, G., & Lin, F. X. (2020) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3372224.3417317 · Cited by 2
“However, with high compute need, traditional video analytics systems [14, 15, 26, 27] require all videos to be uploaded to a backend server, which stressesthescarcenetworkbandwidthbetweencamerasandservers.”
BackgroundShahin: Faster Algorithms for Generating Explanations for Multiple Predictions
Hasani, S., Thirumuruganathan, S., Koudas, N., & Das, G. (2021) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3448016.3457332 · Cited by 2
EScALation: a framework for efficient and scalable spatio-temporal action localization
Chen, B., & Nahrstedt, K. (2021) · ACM Multimedia Systems Conference (MMSys) · doi:10.1145/3458305.3459598 · Cited by 2
Compression of Neural Networks for Specialized Tasks via Value Locality
Gabbay, F., & Shomron, G. (2021) · Mathematics · doi:10.3390/math9202612 · Cited by 2
Energy-efficient parking analytics system using deep reinforcement learning
Rezaei, Y., Lee, S., & Mossé, D. (2021) · ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys) · doi:10.1145/3486611.3486660 · Cited by 2
Arulraj, J. J. P. (2022) · ACM SIGMOD Record · doi:10.1145/3516431.3516442 · Cited by 3
Adaptive Cross-Camera Video Analytics at the Edge
Chen, K., Zhu, Y., Han, Z., & Wang, X. (2022) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass56207.2022.00063 · Cited by 3
Addressing Training Bias via Automated Image AnnotationPreprint
Xiao, Z., Zhu, Y., Chen, Y., Zhao, B. Y., Jiang, J., & Zheng, H.-T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.10242 · Cited by 3
Data Analytics Service Composition and Deployment on Edge DevicesPreprint
Zhao, J., Tiplea, T., Mortier, R., Crowcroft, J., & Wang, L. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.05995 · Cited by 2
Towards real-time object detection on edge with deep neural networks
Zhang, Z. (2018) · MOspace Institutional Repository (University of Missouri) · doi:10.32469/10355/67715 · Cited by 2
Querying Zero-streaming CamerasPreprint
Xu, M., Xu, T., Liu, Y., Liu, X., Huang, G., & Lin, F. X. (2019) · arXiv (Cornell University) · Cited by 2
EKO: Adaptive Sampling of Compressed Video DataPreprint
Bang, J., Chunduri, P., & Arulraj, J. J. P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.01671 · Cited by 2
“NoScope [18] uses a difference detector for filtering out irrelevant frames and uses a specializedmodel for faster inference.”
BackgroundMethodInfluentialBoggart: Accelerating Retrospective Video Analytics via Model-Agnostic Ingest Processing.Preprint
Agarwal, N., & Netravali, R. (2021) · arXiv (Cornell University) · Cited by 3
MavVStream: Extending Database Capabilities for Situation Monitoring Using Extracted Video ContentsPreprint
Billah, H., Arora, M., & Chakravarthy, S. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.14344 · Cited by 2
“Custom solutions NoScope [9], MIRIS [10], SVQ++ [11] Video Fixed set of queries (e.”
MethodVQPy: An Object-Oriented Approach to Modern Video AnalyticsPreprint
Shan, Y., Zhu, Z., Chen, Y., Xu, H., Zhao, P., Wang, Y., Padmanabhan, A., Latapie, H. M., & Xu, H. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.01623 · Cited by 2
Towards causal physical error discovery in video analytics systems
Shaowang, T., Zhao, J., Sintos, S., & Krishnan, S. (2022) · Workshop on Human-In-the-Loop Data Analytics (HILDA) · doi:10.1145/3546930.3547495 · Cited by 1
Multi-level Matching of Natural Language-Based Vehicle Retrieval
Liu, Y., Zhang, Z., & Yang, X. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-2387-4_24 · Cited by 1
Data Storage and Management for Image AI Pipelines
Şirin, U., & Idreos, S. (2025) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3722212.3725640 · Cited by 1
QaVA: Query-Aware Video Analysis Framework Based on Data Access Pattern
Zhong, T., Zhang, Z., Fu, Y., Lu, G. S., Yuan, Y., & Wang, G. (2025) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65448.2025.00071 · Cited by 1
Querying large video datasets: a systematic literature review
Kossoski, C., Lopes, H. S., & Simão, J. M. (2025) · Journal of Internet Services and Applications · doi:10.5753/jisa.2025.5495 · Cited by 1
Learning to Optimize Edge Robotics: A Fast Integrated Perception-Motion-Communication Approach
Guo, D., Jin, X., Wang, S., Wen, Z., Wen, M., & Xu, C. (2025) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2025.3624379 · Cited by 1
ProxySampler: Proxy Informativeness Estimation for Efficient Data Selection in Active Learning
Song, M.-H., Zhang, L., Yuan, M., & Liu, Y. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761315 · Cited by 1
KEN: An Execution Engine for Unstructured Database Systems
Kossmann, F., Wu, Z., Turk, A., Tatbul, N., Cao, L., & Madden, S. R. (2026) · Proceedings of the VLDB Endowment · doi:10.14778/3796195.3796204 · Cited by 1
ConRAD: Conformal Risk-Aware Neural Databases
Horchidan, S., Zeiher, F., Shi, X., Kalavri, V., Boström, H., Kontoyiannis, I., & Carbone, P. (2026) · Proceedings of the VLDB Endowment · doi:10.14778/3836663.3836705 · Cited by 1
Fech, B., Masarykova, N., Galinski, M., & Trúchly, P. (2026) · IEEE Vehicular Networking Conference (VNC) · doi:10.1109/vnc69225.2026.11629146 · Cited by 1
Interactive Demonstration of Probabilistic Predicates
Lu, Y., Kandula, S., & Chaudhuri, S. (2018) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3183713.3193542 · Cited by 1
“Another prior work, NoScope [8], is a domain-specific model cascade customized for selection queries on videos.”
BackgroundVScan: Efficiently Analyzing Surveillance Videos via Model-joint Mechanism
Zhang, C., Cao, Q., Yao, J., Dong, Y., & Yang, P. (2019) · Proceedings of the International Conference on Parallel Processing · doi:10.1145/3337821.3337860 · Cited by 1
Training With Cache: Specializing Object Detectors From Live Streams Without Overfitting
Itsumi, H., Beye, F., Shinohara, Y., & Iwai, T. (2020) · International Conference on Information Photonics · doi:10.1109/icip40778.2020.9191312
Complex event processing on real-time video streams
Li, Z., Katsifodimos, A., Bozzon, A., & Houben, G. J. P. M. (2020) · Research Repository (Delft University of Technology) · Cited by 4
AlertMe: Towards Natural Language-Based Live Video Trigger Systems at the Edge
Ye, A. N., Hu, Z., Phillips, C., & Mohomed, I. (2021) · International Workshop on Edge Systems, Analytics and Networking (EdgeSys) · doi:10.1145/3434770.3459740 · Cited by 1
Pool of Experts: Realtime Querying Specialized Knowledge in Massive Neural Networks
Kim, H., & Choi, D.-W. (2021) · SIGMOD Conference · doi:10.1145/3448016.3457326 · Cited by 2
Optimizing the Neural Network Detector of Moving Objects
Svitov, D., & Alyamkin, S. A. (2021) · Optoelectronics Instrumentation and Data Processing · doi:10.3103/s875669902101012x · Cited by 1
A Low-Cost Video Analytics System with Velocity Based Configuration Adaptation in Edge Computing
Kim, W., & Youn, C. (2021) · Transactions on computational science and computational intelligence · doi:10.1007/978-3-030-70296-0_48 · Cited by 1
Videolytics: System for Data Analytics of Video Streams
Skopal, T., Ďurišková, D., Pechman, P., Dobranský, M., & Khachaturian, V. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3481980 · Cited by 1
ELIχR: Eliminating Computation Redundancy in CNN-Based Video Processing
Schmerge, J., Mawhirter, D., Holmes, C., McClurg, J., & Wu, B. (2021) · IEEE/ACM Redefining Scalability for Diversely Heterogeneous Architectures Workshop (RSDHA) · doi:10.1109/rsdha54838.2021.00010 · Cited by 1
Controlled Intentional Degradation in Analytical Video Systems
He, W., & Cafarella, M. (2022) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3514221.3517899 · Cited by 5
Fast Vehicle Track Counting in Traffic Video
Qi, R., Liu, Y., Zhang, Z., Yang, X., Wang, G., & Jiang, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-11217-1_18 · Cited by 1
Toward Efficient and Adaptive Design of Video Detection System with Deep Neural Networks
Mao, J., Yang, Q. X., Li, A., Nixon, K. W., Li, H. H., & Chen, Y. (2022) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3484946 · Cited by 1
Edge-Cloud Collaboration for Human Activity Recognition on Multiple Subjects
Xiao, W., Xie, L., Ning, J., Fu, Z., Zhao, M., Lin, Z., & Lin, Q. (2022) · IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM) · doi:10.1109/wowmom54355.2022.00030 · Cited by 2
Demonstration of accelerating machine learning inference queries with correlative proxy models
Yang, Z., Huang, Y., Wang, Z., Gao, F., Lu, Y., Li, C., & Wang, X. S. (2022) · Proceedings of the VLDB Endowment · doi:10.14778/3554821.3554887 · Cited by 1
Optimizing ML Inference Queries Under Constraints
Li, Z., Schönfeld, M., Sun, W., Fragkoulis, M., Hai, R., Bozzon, A., & Katsifodimos, A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-34444-2_4 · Cited by 3
Lin, J., Yu, L., & Yang, P. (2023) · IEEE International Conference on Sensing, Communication, and Networking (SECON) · doi:10.1109/secon58729.2023.10287455 · Cited by 1
Bi-Encoder Cascades for Efficient Image Search
Hönig, R., Ackermann, J., & Chi, M. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00146 · Cited by 4
MultiTASC++: A continuously adaptive scheduler for edge-based multi-device cascade inference
Nikolaidis, S., Venieris, S. I., & Venieris, I. S. (2024) · ITU Journal on Future and Evolving Technologies · doi:10.52953/tbyb6219 · Cited by 1
Adaptive Streaming Continuous Learning System for Video Analytics
Li, T., Li, Q., Zhang, M., Yuan, Z., & Jiang, Y. (2024) · International Workshop on Quality of Service · doi:10.1109/iwqos61813.2024.10682886 · Cited by 1
Jaini, S. (2022) · International Journal for Research Publication and Seminars · doi:10.36676/jrps.v13.i2.1600 · Cited by 1
Wen, Q., Zhou, J., Chen, R., Luo, Z., Gareth Tyson, A., Li, W., Wang, J., Pan, H., & Xu, Z. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3480089 · Cited by 1
Sharma, A., Subasharan, V., Gulati, M., Wanniarachchige, D., & Misra, A. (2025) · ACM Transactions on Internet of Things · doi:10.1145/3736420 · Cited by 1
On Fusion of Learned and Designed Features for Video Data Analytics
Dobranský, M., & Skopal, T. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-67835-7_23 · Cited by 1
Seeding Deep Learning using Wireless Localization.Preprint
Xiao, Z., Zhu, Y., Chen, Y., Zhao, B. Y., Jiang, J., & Zheng, H. (2018) · arXiv (Cornell University) · Cited by 1
Reinventing Data Stores for Video Analytics.Preprint
Xu, T., Botelho, L. M., & Lin, F. X. (2018) · arXiv (Cornell University) · Cited by 1
Souto, Y. M., Pereira, R. S., Zorrilla, R., Chaves, A., Tsan, B., Rusu, F., Ogasawara, E., Ziviani, A., & Porto, F. A. M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.11093 · Cited by 2
MultiScope: Efficient Video Pre-processing for Exploratory Video AnalyticsPreprint
Bastani, F., & Madden, S. R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.14695 · Cited by 1
Yadav, P. (2021) · Arrow@dit (Dublin Institute of Technology) · doi:10.13025/17114 · Cited by 5
Large-Scale Video Analytics through Object-Level ConsolidationPreprint
Rivas, D., Guim, F., Polo, J., & Carrera, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.15451 · Cited by 1
Automatic and Efficient Customization of Neural Networks for ML ApplicationsPreprint
Liu, Y.-H., Wan, C.-C., Du, K.-T., Hoffmann, H., Jiang, J.-C., Lu, S., & Maire, M. (2023) · arXiv.org · doi:10.48550/arxiv.2310.04685 · Cited by 2
EmpireDB: Data System to Accelerate Computational SciencesPreprint
Alabi, D., & Wu, E. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.10546 · Cited by 1
Query-Centric Optimization of AI Workflows via Approximate Query Processing and Proxy ModelsPreprint
Wang, H., Xu, J., & Chan, G. Y.-Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.00254 · Cited by 1
Querying Videos Using DNN Generated Labels
Wu, Y., Drucker, S. M., Philipose, M., & Ravindranath, L. (2018) · Workshop on Human-In-the-Loop Data Analytics (HILDA) · doi:10.1145/3209900.3209909
“Recently systems researchers have developed fast systems to answer basic (binary classification queries) [12] or predefined queries [22].”
BackgroundFast 3D Post Estimation of Human Based on Optical Flow and Particle Filter
Lan, J., Huang, G., & Cheng, L. (2019) · Journal of Software · doi:10.17706/jsw.14.10.437-448
Artificial Intelligence Inference in Edge
Wang, X., Han, Y., Leung, V. C. M., Niyato, D. T., Yan, X., & Chen, X. (2020) · Springer eBooks · doi:10.1007/978-981-15-6186-3_5
Customized Systems of Deep Neural Networks for Energy Efficiency
Zamirai, B. (2020) · Deep Blue (University of Michigan)
AmphibianDetector: adaptive computation for moving objects detectionPreprint
Svitov, D., & Alyamkin, S. A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.07513
“Noscope uses an inference-optimized model search that is optimal for a cascade of difference detectors and specialized networks for a given video, target object, and reference neural network.”
InfluentialAdhatarao, S. S. (2020) · eDiss (Georg-August-Universität Göttingen) · doi:10.53846/goediss-8341
Clique: Spatiotemporal Object Re-identification at the City ScalePreprint
Xu, T., Shen, K., Fu, Y. L., Shi, H., & Lin, F. X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.09329 · Cited by 1
Accelerating Queries over Unstructured Data with ML.
Kang, D. D. (2021) · Conference on Innovative Data Systems Research
Self-citationTowards Unsupervised Fine-Tuning for Edge Video Analytics.Preprint
Rivas-Barragan, D., Guim, F., Polo, J., Berral, J. L., Silva, P. M., & Carrera, D. (2021) · arXiv (Cornell University)
DVQShare: An Analytics System for DNN-based Video Queries
Fu, H., Tang, S., Yu, C., Li, Y., Sun, J., & Liu, Y. (2021) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid51090.2021.00026 · Cited by 2
VRefine: Refining Massive Surveillance Videos for Efficient Store and Fast Analyzing
Zhang, C., Cao, Q., Yao, J., & Xie, C. (2021) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid51090.2021.00048
Dong, L., Cai, X., & Yang, Z. (2021) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads53394.2021.00070
Structured Compression of Convolutional Neural Networks for Specialized Tasks
Gabbay, F., Salomon, B. G., & Shomron, G. (2022) · Mathematics · doi:10.3390/math10193679
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.