ODIN: Automated Drift Detection and Recovery in Video Analytics
Summary: ODIN automates drift detection and recovery in video analytics using adversarial autoencoders to model high-dimensional image distributions. Unsupervised drift detection contrasts current vs. prior distributions; on drift, it deploys specialized models and an ensemble selector to boost accuracy, throughput, and memory. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Abhijit Suprem (Georgia Institute of Technology)
- 2. Joy Arulraj (Georgia Institute of Technology)
- 3. Calton Pu (Georgia Institute of Technology)
- 4. Joao Ferreira (University of Sao Paulo)
BibTeX Citation
@article{suprem_vldb20,
title = {{ODIN: Automated Drift Detection and Recovery in Video Analytics}},
author = {Suprem, Abhijit and Arulraj, Joy and Pu, Calton and Ferreira, Joao},
journal = {PVLDB},
series = {{VLDB} '20},
volume = {13},
number = {11},
pages = {2453--2465},
doi = {10.14778/3407790.3407837},
url = {https://doi.org/10.14778/3407790.3407837},
year = {2020}
}Incoming Citations (Sorted by Pagerank)
Showing 6 of 6 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,720 | VSS: A Storage System for Video Analytics | 2021 | SIGMOD | 7.1739329e-05 |
| 4,694 | Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning | 2022 | SIGMOD | 6.5592238e-05 |
| 8,855 | ANN Softmax: Acceleration of Extreme Classification Training | 2022 | VLDB | 5.3573227e-05 |
| 10,670 | MAST: Towards Efficient Analytical Query Processing on Point Cloud Data | 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 |
| 11,433 | An Experimental Evaluation of Process Concept Drift Detection | 2023 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 8 of 8 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 142 | LOF: Identifying Density-Based Local Outliers | 2000 | SIGMOD | 0.0002962566 |
| 205 | Snorkel: Rapid Training Data Creation with Weak Supervision | 2018 | VLDB | 0.00025235185 |
| 284 | NoScope: Optimizing Neural Network Queries over Video at Scale | 2017 | VLDB | 0.00022370521 |
| 295 | Accelerating Machine Learning Inference with Probabilistic Predicates | 2018 | SIGMOD | 0.00022238183 |
| 369 | Locality-Sensitive Hashing Scheme Based on Dynamic Collision Counting | 2012 | SIGMOD | 0.00019945234 |
| 569 | BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics | 2020 | VLDB | 0.00016348191 |
| 891 | Adaptive Stream Resource Management Using Kalman Filters | 2004 | SIGMOD | 0.00013382575 |
| 2,384 | DeepLens: Towards a Visual Data Management System | 2019 | CIDR | 8.6494525e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,393 | Query-Aware Path Inference from Spatial Videos | 2026 | SIGMOD |
| 2 | 7,354 | DeepTEA: Effective and Efficient Online Time-dependent Trajectory Outlier Detection | 2022 | VLDB |
| 3 | 5,827 | Top-K Deep Video Analytics: A Probabilistic Approach | 2021 | SIGMOD |
| 4 | 8,516 | Origin-Destination Travel Time Oracle for Map-based Services | 2023 | SIGMOD |
| 5 | 8,230 | TOD: GPU-accelerated Outlier Detection via Tensor Operations | 2023 | VLDB |
| 6 | 11,260 | Efficiently Mitigating the Impact of Data Drift on Machine Learning Pipelines | 2024 | VLDB |
| 7 | 4,814 | METER: A Dynamic Concept Adaptation Framework for Online Anomaly Detection | 2024 | VLDB |
| 8 | 4,298 | OTIF: Efficient Tracker Pre-processing over Large Video Datasets | 2022 | SIGMOD |
| 9 | 4,062 | AutoOD: Automatic Outlier Detection | 2023 | SIGMOD |
| 10 | 4,582 | A Demonstration of AutoOD: A Self-Tuning Anomaly Detection System | 2022 | VLDB |