Optimizing Video Analytics with Declarative Model Relationships
Summary: Relational Hints: a declarative interface (CAN REPLACE, CAN FILTER) to capture domain-informed relationships among ML models for multi-predicate video SQL queries. VIVA automatically validates/applies hints, searches transformed plans to meet accuracy bounds and achieves up to 16.6x speedups on Spark without accuracy loss. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Francisco Romero
- 2. Johann Hauswald
- 3. Aditi Partap
- 4. Daniel Kang
- 5. Matei Zaharia
- 6. Christos Kozyrakis
Incoming Citations (Sorted by Pagerank)
Showing 9 of 9 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 7,334 | Aero: Adaptive Query Processing of ML Queries | 2025 | SIGMOD | 4.7538944e-05 |
| 9,129 | Spatialyze: A Geospatial Video Analytics System with Spatial-Aware Optimizations | 2024 | VLDB | 4.3861016e-05 |
| 9,767 | TVM: A Tile-based Video Management Framework | 2024 | VLDB | 4.2815042e-05 |
| 9,771 | VOCALExplore: Pay-as-You-Go Video Data Exploration and Model Building | 2023 | VLDB | 4.2815042e-05 |
| 10,095 | NeurStore: Efficient In-database Deep Learning Model Management System | 2026 | SIGMOD | 4.1905499e-05 |
| 10,103 | Query-Aware Path Inference from Spatial Videos | 2026 | SIGMOD | 4.1905499e-05 |
| 10,337 | KEN: An Execution Engine for Unstructured Database Systems | 2026 | VLDB | 4.1905499e-05 |
| 10,947 | Predictive and Near-Optimal Sampling for View Materialization in Video Databases | 2024 | SIGMOD | 4.1905499e-05 |
| 11,064 | Optimizing Video Queries with Declarative Clues | 2024 | VLDB | 4.1905499e-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