Presto: Hybrid CPU-GPU Preprocessing Framework for Video-based AI Inference System
The growing adoption of video-based AI models has created a pressing demand for high throughput, low latency inference systems. However, existing preprocessing frameworks—whether CPU or GPU based—struggle to keep up with the computational burdens of video decoding and data augmentation, resulting in suboptimal GPU utilization and degraded inference system performance.
Authors
- Jihyuk Lee (ORCID: https://orcid.org/0009-0008-0986-213X)
- Dongsu Han (ORCID: https://orcid.org/0000-0001-6922-7244)
- Jaehong Kim (ORCID: https://orcid.org/0000-0002-9111-9976)
Institutions
- Korea Advanced Institute of Science and Technology (KR)
- Chung-Ang University (KR)
- Carnegie Mellon University (US)
Publication Details
- Published
- 2025-06-23
- DOI
- https://doi.org/10.1145/3711875.3736688
- Primary Topic
- Human Pose and Action Recognition
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Research Foundation
- National Research Foundation of Korea
- Ministry of Science and ICT, South Korea
- Samsung