In this paper we introduce a template-based method for recognizing human actions called Action MACH. Our approach is based on a Maximum Average Correlation Height (MACH) filter. A...
Recent approaches to action classification in videos have used sparse spatio-temporal words encoding local appearance around interesting movements. Most of these approaches use a ...
Multimedia streaming is one of the most attractive services over the Internet, for which bandwidth is a primary constraint. For live streaming, however, the computational resource ...
Meng-Ting Lu, Chang-Kuan Lin, Jason Yao, Homer H. ...
In this paper, we propose a novel technique for modelbased recognition of complex object motion trajectories using Hidden Markov Models (HMM). We build our models on Principal Com...
Faisal I. Bashir, Wei Qu, Ashfaq A. Khokhar, Dan S...
We present two user interfaces for the interactive control of dynamically-simulated characters. The first interface uses an ‘action palette’ and targets sports prototyping ap...