We explore an approach to 3D people tracking with learned motion models and deterministic optimization. The tracking problem is formulated as the minimization of a differentiable ...
Abstract. In a previous work, a new probabilistic context-free grammar (PCFG) model for natural language parsing derived from a tree bank corpus has been introduced. The model esti...
Although publicly-available, ground-truthed corpora have proven useful for training, evaluating, and comparing recognition systems in many domains, the availability of such corpor...
Scott MacLean, George Labahn, Edward Lank, Mirette...
This paper proposes an incremental multiple-object recognition and localization (IMORL) method. The objective of IMORL is to adaptively learn multiple interesting objects in an ima...
Conventional remote sensing classification techniques that model the data in each class with a multivariate Gaussian distribution are inefficient, as this assumption is generally ...
Chintan A. Shah, Manoj K. Arora, Stefan A. Robila,...