Action recognition is one of the most active research fields in computer vision. In this paper, we propose a novel method for classifying human actions in a series of image seque...
An encoder based rate smoothing scheme which uses explicit slicebased mode selection has been proposed recently. The algorithm provides significantly smoother bitstream from a va...
We introduce a novel and inexpensive approach for the temporal alignment of speech to highly imperfect transcripts from automatic speech recognition (ASR). Transcripts are generat...
Successes and failures during rescue operations after hurricane Katrina and the Twin Towers attack demonstrated the importance of supporting first responders with adequate means t...
Marco Roccetti, Mario Gerla, Claudio E. Palazzi, S...
— In an effort to ease the burden of programming motor commands for humanoid robots, a computer vision technique is developed for converting a monocular video sequence of human p...
Jeffrey B. Cole, David B. Grimes, Rajesh P. N. Rao