Everest: A Top-K Deep Video Analytics System
Summary: Everest enables efficient Top-K video analytics with probabilistic guarantees to surface the most interesting frames/clips. It supports user-defined ranking via multiple deep vision models, blending CV, uncertain databases, and Top-K query processing. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Ziliang Lai
- 2. Chris Liu
- 3. Chenxia Han
- 4. Pengfei Zhang
- 5. Eric Lo
- 6. Ben Kao
Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 8,057 | Biathlon: Harnessing Model Resilience for Accelerating ML Inference Pipelines | 2024 | VLDB | 4.5903427e-05 |
| 10,675 | Déjà Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse | 2025 | VLDB | 4.1905499e-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 |
|---|---|---|---|---|
| 332 | Accelerating Machine Learning Inference with Probabilistic Predicates | 2018 | SIGMOD | 0.00027173479 |
| 694 | BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics | 2020 | VLDB | 0.00018031141 |
| 1,390 | MIRIS: Fast Object Track Queries in Video | 2020 | SIGMOD | 0.00012242018 |
| 2,536 | DeepLens: Towards a Visual Data Management System | 2019 | CIDR | 8.5817195e-05 |
| 3,553 | Approximate Selection with Guarantees using Proxies | 2020 | VLDB | 6.9763548e-05 |
| 4,947 | Evaluating Temporal Queries Over Video Feeds | 2021 | SIGMOD | 5.8107138e-05 |
| 5,232 | Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning | 2022 | SIGMOD | 5.6094155e-05 |
| 6,184 | Top-K Deep Video Analytics: A Probabilistic Approach | 2021 | SIGMOD | 5.1636368e-05 |
Previous
Page 1 / 1
Next