We present a discriminative part-based approach for the recognition of object classes from unsegmented cluttered scenes. Objects are modeled as flexible constellations of parts co...
Generative topic models such as LDA are limited by their inability to utilize nontrivial input features to enhance their performance, and many topic models assume that topic assig...
Conditional random fields (CRF) are widely used for predicting output variables that have some internal structure. Most of the CRF research has been done on structured classificati...
We present a navigation algorithm, which integrates virtual obstacle concept with a potential-field-based method to maneuver cylindrical mobile robots in unknown or unstructured e...
Liu Chengqing, Marcelo H. Ang, Hariharan Krishnan,...
We describe techniques to establish local frames over point-sampled manifold surfaces. The tangential alignment of local frames is determined using a wave front algorithm starting...