We consider the fully automated recognition of actions in uncontrolled environment. Most existing work relies on domain knowledge to construct complex handcrafted features from in...
Real-time three-dimensional (RT3D) echocardiography is the newest generation of three-dimensional (3-D) echocardiography. Segmentation of RT3D echocardiographic images is essential...
Yun Zhu, Xenophon Papademetris, Albert J. Sinusas,...
We present a method of recovering high dynamic range radiance maps from photographs taken with conventional imaging equipment. In our method, multiple photographs of the scene are...
We present a novel model for human action categorization. A video sequence is represented as a collection of spatial and spatial-temporal features by extracting static and dynamic...
Where does one attend when viewing dynamic scenes? Research into the factors influencing gaze location during static scene viewing have reported that low-level visual features con...
Parag K. Mital, Tim J. Smith, Robin L. Hill, John ...