Hysia: Serving DNN-Based Video-to-Retail Applications in Cloud
This provides a practical solution for practitioners and researchers in multimedia to handle large-scale video-to-retail applications, though it is incremental as it builds on existing technologies.
The paper tackles the challenge of developing and deploying video-to-retail applications by introducing Hysia, a cloud-based platform that integrates optimized services and libraries, resulting in an open-source system that has gained attention and been published on DockerHub for easy deployment.
Combining \underline{v}ideo streaming and online \underline{r}etailing (V2R) has been a growing trend recently. In this paper, we provide practitioners and researchers in multimedia with a cloud-based platform named Hysia for easy development and deployment of V2R applications. The system consists of: 1) a back-end infrastructure providing optimized V2R related services including data engine, model repository, model serving and content matching; and 2) an application layer which enables rapid V2R application prototyping. Hysia addresses industry and academic needs in large-scale multimedia by: 1) seamlessly integrating state-of-the-art libraries including NVIDIA video SDK, Facebook faiss, and gRPC; 2) efficiently utilizing GPU computation; and 3) allowing developers to bind new models easily to meet the rapidly changing deep learning (DL) techniques. On top of that, we implement an orchestrator for further optimizing DL model serving performance. Hysia has been released as an open source project on GitHub, and attracted considerable attention. We have published Hysia to DockerHub as an official image for seamless integration and deployment in current cloud environments.