Back to papers
Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics
Summary: End-to-end DNN for visual analytics; preprocessing bottlenecks. SMOL: using native low-res data and a runtime that pipelines preprocessing and inference with CPU/GPU placement, memory threading, delivering up to 5.9× throughput at fixed accuracy.
(summarized by gpt-5-nano on Feb 09 2026)
- Paper ID
- 12602
- Venue
- VLDB
- Year
- 2021
- Pagerank
- 7.2629834e-05
- Overall Rank
- 3,293 | 77.10%
- DOI
-
10.14778/3425879.3425881
Incoming Non-self Citations Over Time
Incoming Citations (Sorted by Pagerank)
Showing 14 of 14 citing papers.
| Rank |
Citing Paper |
Year |
Venue |
Pagerank |
| 2,170 |
tf.data: A Machine Learning Data Processing Framework |
2021 |
VLDB |
9.3821603e-05 |
| 3,407 |
End-to-end Optimization of Machine Learning Prediction Queries |
2022 |
SIGMOD |
7.1295646e-05 |
| 3,698 |
Where Is My Training Bottleneck? Hidden Trade-Offs in Deep Learning Preprocessing Pipelines |
2022 |
SIGMOD |
6.8340435e-05 |
| 4,269 |
VSS: A Storage System for Video Analytics |
2021 |
SIGMOD |
6.306798e-05 |
| 4,501 |
TASTI: Semantic Indexes for Machine Learning-based Queries over Unstructured Data |
2022 |
SIGMOD |
6.137686e-05 |
| 4,567 |
Optimizing Video Analytics with Declarative Model Relationships |
2023 |
VLDB |
6.080526e-05 |
| 4,641 |
VIVA: An End-to-End System for Interactive Video Analytics |
2022 |
CIDR |
6.027004e-05 |
| 4,712 |
Accelerating Approximate Aggregation Queries with Expensive Predicates |
2021 |
VLDB |
5.9787986e-05 |
| 7,928 |
Accelerating Aggregation Queries on Unstructured Streams of Data |
2023 |
VLDB |
4.613455e-05 |
| 8,672 |
Optimizing Video Selection LIMIT Queries With Commonsense Knowledge |
2024 |
VLDB |
4.4710897e-05 |
| 9,677 |
Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving |
2025 |
SIGMOD |
4.3047774e-05 |
| 9,765 |
TVM: A Tile-based Video Management Framework |
2024 |
VLDB |
4.2856106e-05 |
| 9,806 |
The Image Calculator: 10x Faster Image-AI Inference by Replacing JPEG with Self-designing Storage Format |
2024 |
SIGMOD |
4.2805224e-05 |
| 10,944 |
Predictive and Near-Optimal Sampling for View Materialization in Video Databases |
2024 |
SIGMOD |
4.1945683e-05 |
Outgoing Citations (Sorted by Pagerank)
Showing 6 of 6 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Semantically Similar Papers
| Overall Rank |
Paper |
Year |
Venue |
Pagerank |
| 4,180 |
FastFlow: Accelerating Deep Learning Model Training with Smart Offloading of Input Data Pipeline |
2023 |
VLDB |
6.3793352e-05 |
| 9,619 |
Faster Visual Analytics through Pixel-Perfect Aggregation |
2014 |
VLDB |
4.3170809e-05 |
| 9,705 |
ETO: Accelerating Optimization of DNN Operators by High-Performance Tensor Program Reuse |
2022 |
VLDB |
4.2994163e-05 |
| 13,229 |
Using Deep Learning Models to Replace Large Materialized Views in Relational Database |
2021 |
CIDR |
- |
| 2,886 |
VISTA: Optimized System for Declarative Feature Transfer from Deep CNNs at Scale |
2020 |
SIGMOD |
7.9612767e-05 |
| 2,863 |
Incremental and Approximate Inference for Faster Occlusion-based Deep CNN Explanations |
2019 |
SIGMOD |
7.9877991e-05 |
| 1,657 |
Challenges and Opportunities in DNN-Based Video Analytics: A Demonstration of the BlazeIt Video Query Engine |
2019 |
CIDR |
0.00010987105 |
| 2,533 |
DeepLens: Towards a Visual Data Management System |
2019 |
CIDR |
8.5899934e-05 |
| 1,504 |
Analyzing and Mitigating Data Stalls in DNN Training |
2021 |
VLDB |
0.00011642333 |
| 3,698 |
Where Is My Training Bottleneck? Hidden Trade-Offs in Deep Learning Preprocessing Pipelines |
2022 |
SIGMOD |
6.8340435e-05 |