NoScope: Optimizing Neural Network Queries over Video at Scale
Summary: Auto-sequences a cascade of specialized and difference detectors to accelerate neural-network video queries while preserving reference-model accuracy. A cost-based optimizer tunes the cascade per video/object, delivering up to 15,500x real-time speedups with 1–5% accuracy loss. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Daniel Kang (Stanford University)
- 2. John Emmons (Stanford University)
- 3. Firas Abuzaid (Stanford University)
- 4. Peter Bailis (Stanford University)
- 5. Matei Zaharia (Stanford University)
BibTeX Citation
@article{kang_vldb17,
title = {{NoScope: Optimizing Neural Network Queries over Video at Scale}},
author = {Kang, Daniel and Emmons, John and Abuzaid, Firas and Bailis, Peter and Zaharia, Matei},
journal = {PVLDB},
series = {{VLDB} '17},
volume = {10},
number = {11},
doi = {10.14778/3137628.3137664},
url = {https://doi.org/10.14778/3137628.3137664},
year = {2017}
}Incoming Citations (Sorted by Pagerank)
Showing 7 of 57 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,795 | Scalable Complex Event Processing on Video Streams | 2025 | SIGMOD | 5.093636e-05 |
| 10,912 | ArrayMorph: Optimizing Hyperslab Queries on the Cloud for Machine Learning Pipelines | 2025 | VLDB | 5.093636e-05 |
| 10,917 | Deja Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse | 2025 | VLDB | 5.093636e-05 |
| 11,472 | PAINE Demo: Optimizing Video Selection Queries With Commonsense Knowledge | 2023 | VLDB | 5.093636e-05 |
| 11,624 | Accelerating Queries over Unstructured Data with ML | 2021 | CIDR | 5.093636e-05 |
| 11,681 | Shahin: Faster Algorithms for Generating Explanations for Multiple Predictions | 2021 | SIGMOD | 5.093636e-05 |
| 11,946 | Collaborative Edge and Cloud Neural Networks for Real-Time Video Processing | 2018 | VLDB | 5.093636e-05 |
Outgoing Citations (Sorted by Pagerank)
Showing 15 of 15 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 1,607 | Challenges and Opportunities in DNN-Based Video Analytics: A Demonstration of the BlazeIt Video Query Engine | 2019 | CIDR |
| 2 | 569 | BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics | 2020 | VLDB |
| 3 | 9,408 | SketchQL: Video Moment Querying with a Visual Query Interface | 2024 | SIGMOD |
| 4 | 4,375 | FiGO: Fine-Grained Query Optimization in Video Analytics | 2022 | SIGMOD |
| 5 | 4,213 | SVQ++: Querying for Object Interactions in Video Streams | 2020 | SIGMOD |
| 6 | 3,410 | SVQ: Streaming Video Queries | 2019 | SIGMOD |
| 7 | 2,702 | Panorama: A Data System for Unbounded Vocabulary Querying over Video | 2020 | VLDB |
| 8 | 11,268 | Optimizing Video Queries with Declarative Clues | 2024 | VLDB |
| 9 | 4,429 | Evaluating Temporal Queries Over Video Feeds | 2021 | SIGMOD |
| 10 | 8,589 | Optimizing Video Selection LIMIT Queries With Commonsense Knowledge | 2024 | VLDB |