Axel Sauer

This is not planned, but I'd be happy about contributions :)

The reason was already given in #6, resetting templates during a sequence destroys the purpose of a long-term module. In the evaluation procedure of VOT, the resetting is done by...

I am not quite sure what you mean? The CAL networks take a sequence of images and high-level inputs and predict the affordances based on these inputs.

It won't stay unreleased; I'm aiming for the end of March :)