Optimizing Video Analytics with Declarative Model Relationships
Summary: Introduces declarative CAN REPLACE/CAN FILTER hints for expressing relationships among video ML models. VIVA validates hints and explores transformed SQL plans to meet accuracy constraints, achieving up to 16.6× speedups without accuracy loss. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Francisco Romero (Stanford University)
- 2. Johann Hauswald (Stanford University; Sutter Hill Ventures)
- 3. Aditi Partap (Stanford University)
- 4. Daniel Kang (Stanford University)
- 5. Matei Zaharia (Stanford University)
- 6. Christos Kozyrakis (Stanford University)
BibTeX Citation
@article{romero_vldb23,
title = {{Optimizing Video Analytics with Declarative Model Relationships}},
author = {Romero, Francisco and Hauswald, Johann and Partap, Aditi and Kang, Daniel and Zaharia, Matei and Kozyrakis, Christos},
journal = {PVLDB},
series = {{VLDB} '23},
volume = {16},
number = {3},
pages = {447--460},
doi = {10.14778/3570690.3570695},
url = {https://doi.org/10.14778/3570690.3570695},
year = {2023}
}Incoming Citations (Sorted by Pagerank)
Showing 9 of 9 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 7,066 | Aero: Adaptive Query Processing of ML Queries | 2025 | SIGMOD | 5.712204e-05 |
| 9,144 | Spatialyze: A Geospatial Video Analytics System with Spatial-Aware Optimizations | 2024 | VLDB | 5.315132e-05 |
| 9,924 | TVM: A Tile-based Video Management Framework | 2024 | VLDB | 5.1955087e-05 |
| 9,926 | VOCALExplore: Pay-as-You-Go Video Data Exploration and Model Building | 2023 | VLDB | 5.1955087e-05 |
| 10,386 | NeurStore: Efficient In-database Deep Learning Model Management System | 2026 | SIGMOD | 5.093636e-05 |
| 10,393 | Query-Aware Path Inference from Spatial Videos | 2026 | SIGMOD | 5.093636e-05 |
| 10,623 | KEN: An Execution Engine for Unstructured Database Systems | 2026 | VLDB | 5.093636e-05 |
| 11,162 | Predictive and Near-Optimal Sampling for View Materialization in Video Databases | 2024 | SIGMOD | 5.093636e-05 |
| 11,268 | Optimizing Video Queries with Declarative Clues | 2024 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 20 of 20 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 | 8,589 | Optimizing Video Selection LIMIT Queries With Commonsense Knowledge | 2024 | VLDB |
| 2 | 7,739 | Video-zilla: An Indexing Layer for Large-Scale Video Analytics | 2022 | SIGMOD |
| 3 | 4,375 | FiGO: Fine-Grained Query Optimization in Video Analytics | 2022 | SIGMOD |
| 4 | 9,464 | Self-Enhancing Video Data Management System for Compositional Events with Large Language Models | 2025 | SIGMOD |
| 5 | 9,408 | SketchQL: Video Moment Querying with a Visual Query Interface | 2024 | SIGMOD |
| 6 | 1,607 | Challenges and Opportunities in DNN-Based Video Analytics: A Demonstration of the BlazeIt Video Query Engine | 2019 | CIDR |
| 7 | 569 | BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics | 2020 | VLDB |
| 8 | 2,933 | EVA: A Symbolic Approach to Accelerating Exploratory Video Analytics with Materialized Views | 2022 | SIGMOD |
| 9 | 11,268 | Optimizing Video Queries with Declarative Clues | 2024 | VLDB |
| 10 | 4,256 | VIVA: An End-to-End System for Interactive Video Analytics | 2022 | CIDR |