|
Work item:
|
F.RFVFMP
|
|
Subject/title:
|
Requirements and framework for the vision foundation models platform
|
|
Status:
|
Under study [Issued from previous study period]
|
|
Approval process:
|
AAP
|
|
Type of work item:
|
Recommendation
|
|
Version:
|
New
|
|
Equivalent number:
|
-
|
|
Timing:
|
2026-Q4 (Medium priority)
|
|
Liaison:
|
ISO/IEC JTC1 SC42
|
|
Supporting members:
|
China Telecom, China Unicom, Zhejiang Dahua Technology, MIIT
|
|
Summary:
|
Vision foundation models provide capabilities for visual perception, visual understanding and cross-modal reasoning based on images, videos and other visual data. To support the development and use of such models, a vision foundation models platform provides common functions for data management, model development, model selection, model delivery and task support.
This Recommendation specifies requirements and a functional framework for a vision foundation models platform, and describes the workflows for model training and model inference supported by the platform. This Recommendation is intended to guide the construction and operation of vision foundation models platform.
|
|
Comment:
|
-
|
|
Reference(s):
|
|
|
Historic references:
|
|
Contact(s):
|
|
| ITU-T A.5 justification(s): |
|
|
|
|
First registration in the WP:
2024-02-02 15:50:40
|
|
Last update:
2026-09-04 17:05:37
|
