Frequency-Store: Scaling Image AI by A Column-Store for Images
Summary: Frequency-Store: a column-store for images that splits images into frequency-based columns and stores batches column-wise to share I/O across concurrent training and inference pipelines. Column-wise layout enables tighter encodings, better compression and up to 11× speedups and 2.2× compression gains over prior image-AI storage. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Utku Sirin (Harvard University)
- 2. Victoria Kauffman (Harvard University)
- 3. Aadit Saluja (Harvard University)
- 4. Florian Klein (Harvard University)
- 5. Jeremy Hsu (Harvard University)
- 6. Stratos Idreos (Harvard University)
BibTeX Citation
@inproceedings{sirin_cidr25,
address = {Amsterdam, Netherlands},
series = {{CIDR} '25},
title = {{Frequency-Store: Scaling Image AI by A Column-Store for Images}},
booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
author = {Sirin, Utku and Kauffman, Victoria and Saluja, Aadit and Klein, Florian and Hsu, Jeremy and Idreos, Stratos},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,277 | F3: The Open-Source Data File Format for the Future | 2026 | SIGMOD | 5.2937431e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 14 | MonetDB/X100: Hyper-Pipelining Query Execution | 2005 | CIDR | 0.0006312782 |
| 9,881 | The Image Calculator: 10x Faster Image-AI Inference by Replacing JPEG with Self-designing Storage Format | 2024 | SIGMOD | 5.2040783e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 7,285 | Bullion: A Column Store for Machine Learning | 2025 | CIDR |
| 2 | 885 | Finding Frequent Items in Data Streams | 2008 | VLDB |
| 3 | 1,507 | Column Imprints: A Secondary Index Structure | 2013 | SIGMOD |
| 4 | 60 | Integrating Compression and Execution in Column-Oriented Database Systems | 2006 | SIGMOD |
| 5 | 1,395 | Column-oriented Database Systems | 2009 | VLDB |
| 6 | 11,768 | Workload-Aware Column Imprints | 2020 | SIGMOD |
| 7 | 10,584 | QStore: Quantization-Aware Compressed Model Storage | 2026 | VLDB |
| 8 | 11,381 | Grouping Time Series for Efficient Columnar Storage | 2023 | SIGMOD |
| 9 | 6,143 | ColumnML: Column-Store Machine Learning with On-The-Fly Data Transformation | 2019 | VLDB |
| 10 | 9,881 | The Image Calculator: 10x Faster Image-AI Inference by Replacing JPEG with Self-designing Storage Format | 2024 | SIGMOD |