This paper presents a new method to extract a network of vessels centerlines from a medical
image. The network is composed of local geodesics over a four-dimensional space that in...
This paper proposes a generic method for action recognition
in uncontrolled videos. The idea is to use images
collected from the Web to learn representations of actions
and use ...
Nazli Ikizler-Cinbis, R. Gokberk Cinbis, Stan Scla...
Fitting of the chin is an essential part of facial model fitting systems. Many previous approaches to chin fitting have used active contour models or snakes. However, achieving su...
This paper presents a probabilistic algorithm for segmenting and recognizing text embedded in video sequences. The algorithm approximates the posterior distribution of segmentatio...
In this paper we evaluate the effectiveness of two likelihood normalization techniques, the Background Model Set (BMS) and the Universal Background Model (UBM), for improving perf...