|
Work item:
|
F.CEC-MDG
|
|
Subject/title:
|
Requirements and framework of AI based multimedia data generation systems using core cloud and edge cloud
|
|
Status:
|
[Carried to next study period]
|
|
Approval process:
|
AAP
|
|
Type of work item:
|
Recommendation
|
|
Version:
|
New
|
|
Equivalent number:
|
-
|
|
Timing:
|
-
|
|
Liaison:
|
-
|
|
Supporting members:
|
-
|
|
Summary:
|
AI-based multimedia data generation systems require robust cloud computing capabilities for large scale model training but can exhibit high latency due to the remote nature of the cloud. A promising solution to this latency issue is to deploy interaction-intensive AI-based multimedia data generation services on edge networks. Despite their resource limitations, edge servers can offer lightweight model training, fine tuning and real-time inference services, which are less computationally and storage intensive. Therefore, this Recommendation identifies a reference framework and requirements of AI-based multimedia data generation systems using core cloud and edge cloud. The use cases are also provided in an appendix.
|
|
Comment:
|
-
|
|
Reference(s):
|
|
|
Historic references:
|
|
Contact(s):
|
|
| ITU-T A.5 justification(s): |
|
|
|
|
First registration in the WP:
2023-08-22 14:18:53
|
|
Last update:
2024-09-20 10:29:41
|
