Skeletonization algorithms typically decompose an object’s
silhouette into a set of symmetric parts, offering a
powerful representation for shape categorization. However,
havi...
Alex Levinshtein, Sven Dickinson, Cristian Sminchi...
A common design of an object recognition system has
two steps, a detection step followed by a foreground withinclass
classification step. For example, consider face detection
by...
In extended video sequences, individual frames are grouped into shots which are defined as a sequence taken by a single camera, and related shots are grouped into scenes which are...
Gait is a promising biometric cue which can facilitate the recognition of human beings, particularly when other biometrics are unavailable. Existing work for gait recognition, how...
Automatic annotation is an elegant alternative to explicit recognition in images. In annotation, the image is matched with keyword models, and the most relevant keywords are assig...