AI has many techniques and tools at its disposal, yet seems to be lacking some special "juice" needed to create a true being. We propose that the missing ingredients are ...
In this paper, we present a novel approach for automatically learning a compact and yet discriminative appearance-based human action model. A video sequence is represented by a ba...
Abstract As a matter of fact, humans continuously delegate and distribute cognitive functions to the environment to lessen their limits. They build models, representations, and oth...
In this work, homomorphic image modeling is used to make the exhaustive block-matching algorithm (EBMA) more human vision system (HVS) aware, thus yielding visually pleasing seque...
We designed an activity-based prototyping process realized in the ActivityDesigner system that combines the theoretical framework of Activity-Centered Design with traditional iter...