We introduce a novel set of features for robust object recognition. Each element of this set is a complex feature obtained by combining position- and scale-tolerant edgedetectors ...
— This paper presents a method to achieve visual servoing tasks when the shape of the object being observed as well as the final image are unknown. Therefore, a reconstruction p...
—Many visualization applications benefit from displaying content on real-world objects rather than on a traditional display (e.g., a monitor). This type of visualization display ...
We address the problem of multiclass object detection. Our aims are to enable models for new categories to benefit from the detectors built previously for other categories, and fo...
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...