We develop hierarchical, probabilistic models for objects, the parts composing them, and the visual scenes surrounding them. Our approach couples topic models originally developed...
Erik B. Sudderth, Antonio Torralba, William T. Fre...
The problem of reassembling an object from its parts or fragments has never been addressed with a unified computational approach, which depends on the pure geometric form of the pa...
The imprecise computation model provides the ability to cope with unpredictable workloads. However, there is no consistent way on how to terminate the computation in its early sta...
We describe a mid-level approach for action recognition. From an input video, we extract salient spatio-temporal structures by forming clusters of trajectories that serve as candi...
In a series of publications, we have proposed a foundational system of ontological categories which has been used to evaluate and improve the quality of conceptual modeling languag...