Ever tried asking your AI assistant, or even a robot having cameras, “is there a free seat in the waiting room”? Probably not, because you know it won’t be able to answer. This is actually a non-trivial issue of automated fusion of different sources of information, such as for example video and sound. Furthermore, making sense of the fused media is also non trivial! Let’s learn why in this SPRING Technical Seminar #1, entitled “Audio Visual Machine Perception for Human-Robot Interaction”, by Dr. Radu Horaud from Inria on 27 May 2020.

For privacy reasons YouTube needs your permission to be loaded. For more details, please see our Privacy policy.
I Accept