DBScholar

Back to papers

Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics

Summary: Measurement study finds visual DNN analytics bottlenecked by preprocessing—not inference—on modern accelerators. SMOL exploits native low-resolution data and hardware-aware CPU/GPU co-scheduling, memory, and threading for up to 5.9× throughput at fixed accuracy. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID
h79aa3e04751657e7
Venue
VLDB
Year
2021
Pagerank
7.5207996e-05
Overall Rank
3,219 | 78.36%
DOI
10.14778/3425879.3425881

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{kang_vldb21,
        title = {{Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics}},
        author = {Kang, Daniel and Mathur, Ankit and Veeramacheneni, Teja and Bailis, Peter and Zaharia, Matei},
        journal = {PVLDB},
        series = {{VLDB} '21},
        volume = {14},
        number = {2},
        pages = {87--100},
        doi = {10.14778/3425879.3425881},
        url = {https://doi.org/10.14778/3425879.3425881},
        year = {2021}
}

Incoming Citations (Sorted by Pagerank)

Showing 15 of 15 citing papers.

Rank Citing Paper Year Venue Pagerank
2,053 tf.data: A Machine Learning Data Processing Framework 2021 VLDB 9.1140407e-05
2,662 End-to-end Optimization of Machine Learning Prediction Queries 2022 SIGMOD 8.1596229e-05
3,601 Where Is My Training Bottleneck? Hidden Trade-Offs in Deep Learning Preprocessing Pipelines 2022 SIGMOD 7.1757877e-05
3,650 TASTI: Semantic Indexes for Machine Learning-based Queries over Unstructured Data 2022 SIGMOD 7.1341771e-05
3,753 VSS: A Storage System for Video Analytics 2021 SIGMOD 7.0502734e-05
3,778 Optimizing Video Analytics with Declarative Model Relationships 2023 VLDB 7.0259119e-05
3,874 Accelerating Approximate Aggregation Queries with Expensive Predicates 2021 VLDB 6.953738e-05
4,287 VIVA: An End-to-End System for Interactive Video Analytics 2022 CIDR 6.6869736e-05
6,166 Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving 2025 SIGMOD 5.8631131e-05
7,801 Accelerating Aggregation Queries on Unstructured Streams of Data 2023 VLDB 5.4507311e-05
8,749 Optimizing Video Selection LIMIT Queries With Commonsense Knowledge 2024 VLDB 5.2852539e-05
10,043 The Image Calculator: 10x Faster Image-AI Inference by Replacing JPEG with Self-designing Storage Format 2024 SIGMOD 5.0921006e-05
10,107 TVM: A Tile-based Video Management Framework 2024 VLDB 5.0789354e-05
10,858 Sema: A High-performance System for LLM-based Semantic Query Processing 2026 VLDB 4.9793485e-05
11,509 Predictive and Near-Optimal Sampling for View Materialization in Video Databases 2024 SIGMOD 4.9793485e-05
Previous Page 1 / 1 Next

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.

Rank Cited Paper Year Venue Pagerank
271 NoScope: Optimizing Neural Network Queries over Video at Scale 2017 VLDB 0.00022560564
281 Accelerating Machine Learning Inference with Probabilistic Predicates 2018 SIGMOD 0.00022295232
541 BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics 2020 VLDB 0.00016657685
1,193 Weld: A Common Runtime for High Performance Data Analytics 2017 CIDR 0.0001158809
1,617 Challenges and Opportunities in DNN-Based Video Analytics: A Demonstration of the BlazeIt Video Query Engine 2019 CIDR 0.00010057464
2,776 Approximate Selection with Guarantees using Proxies 2020 VLDB 8.0309448e-05
Previous Page 1 / 1 Next

Semantically Similar Papers

# Overall Rank Paper Year Venue
1 3,811 FastFlow: Accelerating Deep Learning Model Training with Smart Offloading of Input Data Pipeline 2023 VLDB
2 9,934 Faster Visual Analytics through Pixel-Perfect Aggregation 2014 VLDB
3 10,013 ETO: Accelerating Optimization of DNN Operators by High-Performance Tensor Program Reuse 2022 VLDB
4 13,746 Using Deep Learning Models to Replace Large Materialized Views in Relational Database 2021 CIDR
5 3,630 VISTA: Optimized System for Declarative Feature Transfer from Deep CNNs at Scale 2020 SIGMOD
6 1,617 Challenges and Opportunities in DNN-Based Video Analytics: A Demonstration of the BlazeIt Video Query Engine 2019 CIDR
7 3,040 Incremental and Approximate Inference for Faster Occlusion-based Deep CNN Explanations 2019 SIGMOD
8 2,391 DeepLens: Towards a Visual Data Management System 2019 CIDR
9 1,475 Analyzing and Mitigating Data Stalls in DNN Training 2021 VLDB
10 3,601 Where Is My Training Bottleneck? Hidden Trade-Offs in Deep Learning Preprocessing Pipelines 2022 SIGMOD