We address the problem of understanding an indoor scene from a single image in terms of recovering the layouts of the faces (floor, ceiling, walls) and furniture. A major challeng...
We explore the striking mathematical connections that exist between market scoring rules, cost function based prediction markets, and no-regret learning. We first show that any c...
This paper investigates the problem ofautomatically learning declarative models of information sources available on the Internet. We report on ILA, a domain-independent program th...
How humans infer probable information from the limited observed data? How they are able to build on little knowledge about the context in hand? Is the human memory repeatedly const...
This paper describes, compares, and evaluates three different approaches for learning a semantic classification of library titles: 1) syntactically condensed titles, 2) complete t...