Seiden: Revisiting Query Processing in Video Database Systems
Summary: Notes modern oracle CV models rival or exceed proxy latency, so Seiden builds a query-agnostic index by running the oracle on a subset of frames. At query time it uses exploration–exploitation sampling and temporal continuity to answer queries faster and more accurately than SoTA (≈6.6× speedup). (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Jaeho Bang (Georgia Institute of Technology)
- 2. Gaurav Tarlok Kakkar (Georgia Institute of Technology)
- 3. Pramod Chunduri (Georgia Institute of Technology)
- 4. Subrata Mitra (Adobe)
- 5. Joy Arulraj (Georgia Institute of Technology)
BibTeX Citation
@article{bang_vldb23,
title = {{Seiden: Revisiting Query Processing in Video Database Systems}},
author = {Bang, Jaeho and Kakkar, Gaurav Tarlok and Chunduri, Pramod and Mitra, Subrata and Arulraj, Joy},
journal = {PVLDB},
series = {{VLDB} '23},
volume = {16},
number = {9},
pages = {2289--2301},
doi = {10.14778/3598581.3598599},
url = {https://doi.org/10.14778/3598581.3598599},
year = {2023}
}Incoming Citations (Sorted by Pagerank)
Showing 8 of 8 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 7,066 | Aero: Adaptive Query Processing of ML Queries | 2025 | SIGMOD | 5.712204e-05 |
| 8,043 | Falcon: Fair Active Learning using Multi-armed Bandits | 2024 | VLDB | 5.5013766e-05 |
| 9,464 | Self-Enhancing Video Data Management System for Compositional Events with Large Language Models | 2025 | SIGMOD | 5.2634238e-05 |
| 10,623 | KEN: An Execution Engine for Unstructured Database Systems | 2026 | VLDB | 5.093636e-05 |
| 10,670 | MAST: Towards Efficient Analytical Query Processing on Point Cloud Data | 2025 | SIGMOD | 5.093636e-05 |
| 10,795 | Scalable Complex Event Processing on Video Streams | 2025 | SIGMOD | 5.093636e-05 |
| 10,917 | Deja Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse | 2025 | VLDB | 5.093636e-05 |
| 11,268 | Optimizing Video Queries with Declarative Clues | 2024 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 13 of 13 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 | 11,624 | Accelerating Queries over Unstructured Data with ML | 2021 | CIDR |
| 2 | 410 | SeeDB: Efficient Data-Driven Visualization Recommendations to Support Visual Analytics | 2015 | VLDB |
| 3 | 8,589 | Optimizing Video Selection LIMIT Queries With Commonsense Knowledge | 2024 | VLDB |
| 4 | 9,925 | DoveDB: A Declarative and Low-Latency Video Database | 2023 | VLDB |
| 5 | 9,408 | SketchQL: Video Moment Querying with a Visual Query Interface | 2024 | SIGMOD |
| 6 | 14,322 | Modelling and Querying Video Data | 1994 | VLDB |
| 7 | 9,924 | TVM: A Tile-based Video Management Framework | 2024 | VLDB |
| 8 | 5,329 | SeeDB: Visualizing Database Queries Efficiently | 2014 | VLDB |
| 9 | 4,991 | VisualWorldDB: A DBMS for the Visual World | 2020 | CIDR |
| 10 | 11,268 | Optimizing Video Queries with Declarative Clues | 2024 | VLDB |