论文标题
HYSIA：在云中提供基于DNN的视频到零售应用程序
Hysia: Serving DNN-Based Video-to-Retail Applications in Cloud
论文作者
论文摘要
将\下划线{V} IDEO流和在线\下划线{r} Etailing（V2R）结合起来一直是一个增长的趋势。在本文中，我们为多媒体的从业者和研究人员提供了一个基于云的平台，名为Hysia，可轻松开发和部署V2R应用程序。该系统包括：1）提供优化的V2R服务的后端基础架构，包括数据引擎，模型存储库，模型服务和内容匹配； 2）一个应用程序层，该应用程序可以实现快速的V2R应用程序原型制作。 Hysia通过以下大规模多媒体解决了行业和学术需求：1）无缝整合包括NVIDIA视频SDK，Facebook Faiss和Grpc在内的最先进的图书馆； 2）有效利用GPU计算； 3）允许开发人员轻松绑定新模型，以满足快速变化的深度学习（DL）技术。最重要的是，我们实施了一个编排，以进一步优化DL模型服务性能。 Hysia已在Github上作为开源项目发行，并引起了很大的关注。我们已经发表了Hysia将DockerHub作为当前云环境中无缝集成和部署的官方形象。
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.
