Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning
Summary: Zeus uses an RL agent to localize actions in video by selecting sampling rate, length, and resolution to meet a target accuracy. Yields up to 22.1x speedups over frame-based and window-based baselines, while consistently meeting accuracy. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Pramod Chunduri (Georgia Institute of Technology)
- 2. Jaeho Bang (Georgia Institute of Technology)
- 3. Yao Lu (Microsoft)
- 4. Joy Arulraj (Georgia Institute of Technology)
BibTeX Citation
@inproceedings{chunduri_sigmod22,
title = {{Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning}},
author = {Chunduri, Pramod and Bang, Jaeho and Lu, Yao and Arulraj, Joy},
series = {{SIGMOD} '22},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3514221.3526181},
url = {https://dl.acm.org/doi/10.1145/3514221.3526181},
year = {2022}
}
Incoming Citations (Sorted by Pagerank)
Showing 13 of 13 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 268 | Extensible Query Processing in Starburst | 1989 | SIGMOD | 0.00022788687 |
| 295 | Accelerating Machine Learning Inference with Probabilistic Predicates | 2018 | SIGMOD | 0.00022238183 |
| 569 | BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics | 2020 | VLDB | 0.00016348191 |
| 1,042 | MIRIS: Fast Object Track Queries in Video | 2020 | SIGMOD | 0.00012451966 |
| 4,924 | ODIN: Automated Drift Detection and Recovery in Video Analytics | 2020 | VLDB | 6.4429959e-05 |
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 | 4,375 | FiGO: Fine-Grained Query Optimization in Video Analytics | 2022 | SIGMOD |
| 4 | 4,429 | Evaluating Temporal Queries Over Video Feeds | 2021 | SIGMOD |
| 5 | 9,464 | Self-Enhancing Video Data Management System for Compositional Events with Large Language Models | 2025 | SIGMOD |
| 6 | 9,927 | Everest: A Top-K Deep Video Analytics System | 2022 | SIGMOD |
| 7 | 3,365 | Spatial and Temporal Constrained Ranked Retrieval over Videos | 2022 | VLDB |
| 8 | 8,589 | Optimizing Video Selection LIMIT Queries With Commonsense Knowledge | 2024 | VLDB |
| 9 | 11,268 | Optimizing Video Queries with Declarative Clues | 2024 | VLDB |
| 10 | 5,827 | Top-K Deep Video Analytics: A Probabilistic Approach | 2021 | SIGMOD |