|This is a great idea.† But what are the current limitations?† Current models used in probabilistic
perception are at the surface level.
|This idea arises in many
perception tasks. In vision, we can have high-level models of activities, and
of how people interact with each other, giving us much better models for
visual tracking.† However, I donít have
much time left, so† Iíll spend just a
couple of slides talking
|about it in the context of
natural language processing.