We present an extension of Isomap nonlinear dimension reduction (Tenenbaum et al., 2000) for data with both spatial and temporal relationships. Our method, ST-Isomap, augments the...
We introduce a generative model of dense flow fields within a layered representation of 3-dimensional scenes. Using probabilistic inference and learning techniques (namely, varia...
This paper describes the CMUnited-99 small-size robot team. The team builds on our previous RoboCup champion teams (’97 and ’98). The team reuses much of the hardware, percepti...
Manuela M. Veloso, Michael H. Bowling, Sorin Achim
This paper investigates the task of identifying frequently-used pathways from video sequences of natural outdoor scenes. Path models are adaptively learnt from the accumulation of...
This paper presents a theory that supports commonsense, qualitative reasoning about the flow of liquid around slowly moving solid objects; specifically, inferring that liquid can ...