"Energetic shaping through time"
Gestures relate sound and image ...
change of energy in sound can be related to change of energy of cause.
When a lot of visual activity is going on you can create a hierarchy by having some sound gestures more closely coupled with image gestures which highlights their importance.
Filters which can be laid over streams of, say, note information to add "gesture" eg. energy, dialogue, embelishment.
Maybe train a neural network to recognize opportunities and apply gesture masks to them.