We describe a novel video player that uses Temporal Semantic Compression (TSC) to present a compressed summary of a movie. Compression is based on tempo which is derived from film...
— In communication networks, such as the Internet or mobile ad-hoc networks, the actions taken by intermediate nodes or links are typically hidden from the communicating endpoint...
Michal Feldman, John Chuang, Ion Stoica, Scott She...
This paper presents a robust and accurate method for joint head pose and facial actions tracking, even under challenging conditions such as varying lighting, large head movements,...
In multi-agent planning environments, action models for each agent must be given as input. However, creating such action models by hand is difficult and time-consuming, because i...
In this paper, we present a novel approach for human action recognition with histograms of 3D joint locations (HOJ3D) as a compact representation of postures. We extract the 3D sk...