PGM-AUA V1.0 AIMs – Visual Salience Mapping

Function
Ref. Model
I/O Data
SubAIMs
JSON MData
Profiles
Ref. Software
Conformance
Performance

1 Functions

The Visual Salience Mapping (PGM‑VSM) AIM is a Sub‑AIM of Visual Scene Enhancement (PGM‑VSE). It determines the relative perceptual importance of Visual Objects with respect to user interaction and context, and produces the Salient Object Matrix.

Each Sub‑AIM of Visual Scene Enhancement independently generates a Visual CXT Response, a Visual Domain Request and a Visual Interaction History Request. Visual Enhancement Multiplexing multiplexes them into the corresponding external output signals of Visual Scene Enhancement.

[High‑level specification derived from the Visual Scene Enhancement page. To be completed.]

The PGM‑VSM AIM:

Receives	Visual Object Types	Identifiers of the semantic object types assigned to the Visual Objects, produced by Visual Instance Identification.
	Visual CXT Request	Contextual directive specifying scope, depth, and policy constraints for visual enhancement.
	Visual Scene Descriptors	The initial Visual Scene Descriptors constructed by Visual Scene Description.
	Visual Domain Response	Domain‑specific knowledge supporting visual object classification and semantic interpretation.
	Visual Interaction History Response	Interaction History response, providing temporal context for scene understanding.
	Affordance Tags	Tags describing the possible interactions with Visual Objects, produced by Visual Environment Analysis.
	Interaction Potential	The feasibility of the possible interactions with Visual Objects, produced by Visual Environment Analysis.
Produces	Salient Object Matrix	The Visual Objects ranked by perceptual importance and interaction relevance.
	Affordance Tags	Tags describing the possible interactions with Visual Objects, produced by Visual Environment Analysis.
	Visual CXT Response	Response reporting the processing outcome of this Sub‑AIM, multiplexed by Visual Enhancement Multiplexing into the Visual CXT Response of Visual Scene Enhancement.
	Visual Domain Request	Domain request issued by this Sub‑AIM, multiplexed by Visual Enhancement Multiplexing into the Visual Domain Request of Visual Scene Enhancement.
	Visual Interaction History Request	Interaction History request issued by this Sub‑AIM, multiplexed by Visual Enhancement Multiplexing into the Visual Interaction History Request of Visual Scene Enhancement.

2 Reference Model

Figure 1 depicts the Reference Model of the Visual Salience Mapping (PGM‑VSM) AIM.

[Figure 1 to be inserted.]

Figure 1 – Reference Model of the Visual Salience Mapping (PGM‑VSM) AIM

3 I/O Data

Table 1 specifies the Input and Output Data of the Visual Salience Mapping (PGM‑VSM) AIM.

Table 1 – Input and Output Data of the Visual Salience Mapping (PGM‑VSM) AIM

Input	Description
Visual Object Types	Identifiers of the semantic object types assigned to the Visual Objects, produced by Visual Instance Identification.
Visual CXT Request	Contextual directive specifying scope, depth, and policy constraints for visual enhancement.
Visual Scene Descriptors	The initial Visual Scene Descriptors constructed by Visual Scene Description.
Visual Domain Response	Domain‑specific knowledge supporting visual object classification and semantic interpretation.
Visual Interaction History Response	Interaction History response, providing temporal context for scene understanding.
Affordance Tags	Tags describing the possible interactions with Visual Objects, produced by Visual Environment Analysis.
Interaction Potential	The feasibility of the possible interactions with Visual Objects, produced by Visual Environment Analysis.
Output	Description
Salient Object Matrix	The Visual Objects ranked by perceptual importance and interaction relevance.
Affordance Tags	Tags describing the possible interactions with Visual Objects, produced by Visual Environment Analysis.
Visual CXT Response	Response reporting the processing outcome of this Sub‑AIM, multiplexed by Visual Enhancement Multiplexing into the Visual CXT Response of Visual Scene Enhancement.
Visual Domain Request	Domain request issued by this Sub‑AIM, multiplexed by Visual Enhancement Multiplexing into the Visual Domain Request of Visual Scene Enhancement.
Visual Interaction History Request	Interaction History request issued by this Sub‑AIM, multiplexed by Visual Enhancement Multiplexing into the Visual Interaction History Request of Visual Scene Enhancement.

4 SubAIMs

No SubAIMs.

5 JSON Metadata

https://schemas.mpai.community/PGM1/V1.0/AIMs/VisualSalienceMapping.json

6 Profiles

No Profiles.

7 Reference Software

Not part of this specification.

8 Conformance Testing

Table 2 provides the Conformance Testing Method for the Visual Salience Mapping (PGM‑VSM) AIM.
If a schema contains references to other schemas, conformance of data for the primary schema implies that any data referencing a secondary schema shall also validate against the relevant schema.

Table 2 – Conformance Testing Method for the Visual Salience Mapping (PGM‑VSM) AIM

Receives	Visual Object Types	Shall validate against Visual Object Types schema.
	Visual CXT Request	Shall validate against Visual CXT Request schema.
	Visual Scene Descriptors	Shall validate against Visual Scene Descriptors schema.
	Visual Domain Response	Shall validate against Visual Domain Response schema.
	Visual Interaction History Response	Shall validate against Visual Interaction History Response schema.
	Affordance Tags	Shall validate against Affordance Tags schema.
	Interaction Potential	Shall validate against Interaction Potential schema.
Produces	Salient Object Matrix	Shall validate against Salient Object Matrix schema.
	Affordance Tags	Shall validate against Affordance Tags schema.
	Visual CXT Response	Shall validate against Visual CXT Response schema.
	Visual Domain Request	Shall validate against Visual Domain Request schema.
	Visual Interaction History Request	Shall validate against Visual Interaction History Request schema.

9 Performance Assessment