Most existing techniques for analyzing face images assume that the faces are at near-frontal poses. Generalizing to non-frontal faces is often difficult, due to a dearth of groun...
We present a method to track and recognize shape-changing hand gestures simultaneously. The switching linear model using active contour model well corresponds to temporal shapes a...
Mun Ho Jeong, Yoshinori Kuno, Nobutaka Shimada, Yo...
In this work we present a new crowd analysis algorithm powered by behavior priors that are learned on a large database of crowd videos gathered from the Internet. The algorithm wo...
Mikel Rodriguez, Josef Sivic, Ivan Laptev, Jean-Yv...
Wikis are currently in high demand in a large variety of fields, due to their simplicity and flexible nature. Documentation, reporting, project management, online glossaries and d...
—Motion information is an important cue for a robot to separate foreground moving objects from the static background world. Based on the observation that the motion of the backgr...