Go to MPAI-CVE AI Modules

1 Function 2 Reference Model 3 Input/Output Data
4 SubAIMs 5 JSON Metadata 6 Profiles
7 Reference Software 8 Conformance Texting 9 Performance Assessment

1 Function

The Visual Object Identification (CVE-VOI) AIM produces the Identifier, based on a Taxonomy, of a Visual Object of a Visual Scene, described by its Basic Visual Scene Descriptors, that is crossed by a Point of View:

Receives Basic Visual Scene Descriptors The Descriptors of the Visual Scene.
Visual Objects The Objects in the Scene.
Body Descriptors Descriptors of the Body indicating the object.
Produces Visual Instance ID Identifying a Visual Object in the Scene that belongs to some level in a taxonomy.

2 Reference Model

Figure 1 specifies the Reference Model of the Visual Object Identification (CVE-VOI) AIM.

[Figure 1 – The Visual Object Identification (CVE-VOI) AIM Reference Model: to be inserted from the CVE Reference Models deck]

3 Input/Output Data

Table 1 specifies the Input and Output Data of the Visual Object Identification (CVE-VOI) AIM.

Table 1 – I/O Data of the Visual Object Identification (CVE-VOI) AIM

Input Description
Body Descriptors The Descriptors of the Body Objects of Entities in the Visual Scene.
Basic Visual Scene Descriptors The Descriptors of the Visual Scene, including the Visual Objects and their Space-Time.
Visual Object The Visual Objects in the Visual Scene that are not Entities.
Output Description
Visual Instance Identifier The Identifier of the specific Visual Object belonging to a level in the taxonomy.

4 SubAIMs

Visual Object Identification (CVE-VOI) is a Composite AIM specified by Figure 2.
Figure 2 – The Visual Object Identification (CVE-VOI) Composite AIM Reference Model

Figure 2 – The Visual Object Identification (CVE-VOI) Composite AIM Reference Model

Note that Visual Direction Identification and Visual Object Extraction receive the Basic Visual Scene Descriptors (they also accept Basic Multimodal Scene Descriptors). The AIMs composing the Visual Object Identification (CVE-VOI) Composite AIM are:

Table 2 – AIMs of the Visual Object Identification (CVE-VOI) Composite AIM

AIM AIMs Names JSON
CVE-VOI Visual Object Identification Link
CVE-VDI Visual Direction Identification Link
OSD-VOE Visual Object Extraction Link
CVE-VII Visual Instance Identification Link

5 JSON Metadata

https://schemas.mpai.community/CVE/V1.0/AIMs/VisualObjectIdentification.json

6 Profiles

No Profiles.

7 Reference Software

8 Conformance Testing

Table 3 provides the Conformance Testing Method for the CVE-VOI AIM. Conformance Testing of the individual AIMs of the CVE-VOI Composite AIM are given by the individual AIM Specification. Note that a schema may contain references to other schemas. In this case, validation of data for the primary schema implies that any data that refers to a secondary schema shall also validate.

Table 3 – Conformance Testing Method for the CVE-VOI AIM

Receives Basic Visual Scene Descriptors Shall validate against the Basic Visual Scene Descriptors schema.
Visual Objects Shall validate against the Visual Objects schema. Visual Data shall conform with Qualifier.
Body Descriptors Shall validate against the Body Descriptors XML schema.
Produces Visual Instance ID Shall validate against the Instance ID schema.

9 Performance Assessment