Hysia : serving DNN-based video-to-retail applications in cloud
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 consist...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/152998 |
| _version_ | 1811683435366842368 |
|---|---|
| author | Zhang, Huaizheng Li, Yuanming Ai, Qiming Luo, Yong Wen, Yonggang Jin, Yichao Ta, Nguyen Binh Duong |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Zhang, Huaizheng Li, Yuanming Ai, Qiming Luo, Yong Wen, Yonggang Jin, Yichao Ta, Nguyen Binh Duong |
| author_sort | Zhang, Huaizheng |
| collection | NTU |
| description | 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. |
| first_indexed | 2024-10-01T04:12:41Z |
| format | Conference Paper |
| id | ntu-10356/152998 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:12:41Z |
| publishDate | 2021 |
| record_format | dspace |
| spelling | ntu-10356/1529982021-10-28T05:09:44Z Hysia : serving DNN-based video-to-retail applications in cloud Zhang, Huaizheng Li, Yuanming Ai, Qiming Luo, Yong Wen, Yonggang Jin, Yichao Ta, Nguyen Binh Duong School of Computer Science and Engineering 28th ACM International Conference on Multimedia Engineering::Computer science and engineering::Information systems Engineering::Computer science and engineering::Computer applications Multimedia System Video Analysis 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. Energy Market Authority (EMA) Nanyang Technological University National Research Foundation (NRF) This research is supported in part and jointly by the National Research Foundation, Singapore, and the Energy Market Authority, under its Energy Programme (EP Award Ref. NRF2017EWT-EP003- 023) and a project fund from NTU (Ref. NTU–ACE2020-01). 2021-10-28T05:09:43Z 2021-10-28T05:09:43Z 2020 Conference Paper Zhang, H., Li, Y., Ai, Q., Luo, Y., Wen, Y., Jin, Y. & Ta, N. B. D. (2020). Hysia : serving DNN-based video-to-retail applications in cloud. 28th ACM International Conference on Multimedia, 4457-4460. https://dx.doi.org/10.1145/3394171.3414536 9781450379885 https://hdl.handle.net/10356/152998 10.1145/3394171.3414536 2-s2.0-85106918700 4457 4460 en NRF2017EWT-EP003- 023 NTU–ACE2020-01 © 2020 Association for Computing Machinery. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering::Information systems Engineering::Computer science and engineering::Computer applications Multimedia System Video Analysis Zhang, Huaizheng Li, Yuanming Ai, Qiming Luo, Yong Wen, Yonggang Jin, Yichao Ta, Nguyen Binh Duong Hysia : serving DNN-based video-to-retail applications in cloud |
| title | Hysia : serving DNN-based video-to-retail applications in cloud |
| title_full | Hysia : serving DNN-based video-to-retail applications in cloud |
| title_fullStr | Hysia : serving DNN-based video-to-retail applications in cloud |
| title_full_unstemmed | Hysia : serving DNN-based video-to-retail applications in cloud |
| title_short | Hysia : serving DNN-based video-to-retail applications in cloud |
| title_sort | hysia serving dnn based video to retail applications in cloud |
| topic | Engineering::Computer science and engineering::Information systems Engineering::Computer science and engineering::Computer applications Multimedia System Video Analysis |
| url | https://hdl.handle.net/10356/152998 |
| work_keys_str_mv | AT zhanghuaizheng hysiaservingdnnbasedvideotoretailapplicationsincloud AT liyuanming hysiaservingdnnbasedvideotoretailapplicationsincloud AT aiqiming hysiaservingdnnbasedvideotoretailapplicationsincloud AT luoyong hysiaservingdnnbasedvideotoretailapplicationsincloud AT wenyonggang hysiaservingdnnbasedvideotoretailapplicationsincloud AT jinyichao hysiaservingdnnbasedvideotoretailapplicationsincloud AT tanguyenbinhduong hysiaservingdnnbasedvideotoretailapplicationsincloud |