Back to papers
Déjà Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse
Summary: Déjà Vu speeds ViT-based VideoLMs by learning when to reuse inter-frame ViT computations (ReuseViT), trading minimal accuracy loss for large computation savings. It couples this with memory–compute joint compaction to turn FLOP savings into up to 2.64× embedding throughput within 2% error.
(summarized by gpt-5-mini on Feb 09 2026)
- Paper ID
- 13960
- Venue
- VLDB
- Year
- 2025
- Pagerank
- 4.1945683e-05
- Overall Rank
- 10,667 | 25.80%
- DOI
-
10.14778/3748191.3748195
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank |
Citing Paper |
Year |
Venue |
Pagerank |
Outgoing Citations (Sorted by Pagerank)
Showing 23 of 23 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank |
Cited Paper |
Year |
Venue |
Pagerank |
| 210 |
Gorilla: A Fast, Scalable, In-Memory Time Series Database |
2015 |
VLDB |
0.0003404384 |
| 316 |
NoScope: Optimizing Neural Network Queries over Video at Scale |
2017 |
VLDB |
0.00027988668 |
| 696 |
BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics |
2020 |
VLDB |
0.00018048935 |
| 1,388 |
MIRIS: Fast Object Track Queries in Video |
2020 |
SIGMOD |
0.00012260926 |
| 2,064 |
Chimp: Efficient Lossless Floating Point Compression for Time Series Databases |
2022 |
VLDB |
9.6418929e-05 |
| 3,206 |
Panorama: A Data System for Unbounded Vocabulary Querying over Video |
2020 |
VLDB |
7.3826363e-05 |
| 3,606 |
EVA: A Symbolic Approach to Accelerating Exploratory Video Analytics with Materialized Views |
2022 |
SIGMOD |
6.9260354e-05 |
| 4,269 |
VSS: A Storage System for Video Analytics |
2021 |
SIGMOD |
6.306798e-05 |
| 4,392 |
Elf: Erasing-based Lossless Floating-Point Compression |
2023 |
VLDB |
6.2257087e-05 |
| 4,641 |
VIVA: An End-to-End System for Interactive Video Analytics |
2022 |
CIDR |
6.027004e-05 |
| 4,751 |
ODIN: Automated Drift Detection and Recovery in Video Analytics |
2020 |
VLDB |
5.9485403e-05 |
| 4,865 |
OTIF: Efficient Tracker Pre-processing over Large Video Datasets |
2022 |
SIGMOD |
5.8684353e-05 |
| 5,173 |
FiGO: Fine-Grained Query Optimization in Video Analytics |
2022 |
SIGMOD |
5.6447253e-05 |
| 6,315 |
Seiden: Revisiting Query Processing in Video Database Systems |
2023 |
VLDB |
5.1142298e-05 |
| 7,338 |
Aero: Adaptive Query Processing of ML Queries |
2025 |
SIGMOD |
4.7584583e-05 |
| 7,928 |
Accelerating Aggregation Queries on Unstructured Streams of Data |
2023 |
VLDB |
4.613455e-05 |
| 8,700 |
SeeSaw: Interactive Ad-hoc Search Over Image Databases |
2023 |
SIGMOD |
4.4656647e-05 |
| 9,129 |
Spatialyze: A Geospatial Video Analytics System with Spatial-Aware Optimizations |
2024 |
VLDB |
4.3903093e-05 |
| 9,341 |
SketchQL: Video Moment Querying with a Visual Query Interface |
2024 |
SIGMOD |
4.3554097e-05 |
| 9,765 |
TVM: A Tile-based Video Management Framework |
2024 |
VLDB |
4.2856106e-05 |
| 9,768 |
DoveDB: A Declarative and Low-Latency Video Database |
2023 |
VLDB |
4.2856106e-05 |
| 9,769 |
VOCALExplore: Pay-as-You-Go Video Data Exploration and Model Building |
2023 |
VLDB |
4.2856106e-05 |
| 9,770 |
Everest: A Top-K Deep Video Analytics System |
2022 |
SIGMOD |
4.2856106e-05 |
Semantically Similar Papers
| Overall Rank |
Paper |
Year |
Venue |
Pagerank |
| 4,567 |
Optimizing Video Analytics with Declarative Model Relationships |
2023 |
VLDB |
6.080526e-05 |
| 7,922 |
Video-zilla: An Indexing Layer for Large-Scale Video Analytics |
2022 |
SIGMOD |
4.615892e-05 |
| 10,518 |
High-Throughput Ingestion for Video Warehouse: Comprehensive Configuration and Effective Exploration |
2025 |
SIGMOD |
4.1945683e-05 |
| 3,604 |
Spatial and Temporal Constrained Ranked Retrieval over Videos |
2022 |
VLDB |
6.9301368e-05 |
| 10,944 |
Predictive and Near-Optimal Sampling for View Materialization in Video Databases |
2024 |
SIGMOD |
4.1945683e-05 |
| 5,173 |
FiGO: Fine-Grained Query Optimization in Video Analytics |
2022 |
SIGMOD |
5.6447253e-05 |
| 4,950 |
Evaluating Temporal Queries Over Video Feeds |
2021 |
SIGMOD |
5.8104133e-05 |
| 9,765 |
TVM: A Tile-based Video Management Framework |
2024 |
VLDB |
4.2856106e-05 |
| 10,503 |
Self-Enhancing Video Data Management System for Compositional Events with Large Language Models |
2025 |
SIGMOD |
4.1945683e-05 |
| 11,061 |
Optimizing Video Queries with Declarative Clues |
2024 |
VLDB |
4.1945683e-05 |