— This paper presents a new method based on Fourier and moments features to extract words and characters from a video text line in any direction for recognition. Unlike existing ...
We present a discriminative method for learning selectional preferences from unlabeled text. Positive examples are taken from observed predicate-argument pairs, while negatives ar...
We treat feature selection and basis selection in a unified framework by introducing the masking matrix. If one considers feature selection as finding a binary mask vector that de...
We present a shape based method for automatic people detection and counting without any assumption or knowledge of camera motion. The proposed method is applied to athletic videos...
Variable selection problems are typically addressed under a penalized optimization framework. Nonconvex penalties such as the minimax concave plus (MCP) and smoothly clipped absol...