We present an approach for dictionary learning of action attributes via information maximization. We unify the class distribution and appearance information into an objective func...
Learning from streams of evolving and unbounded data is an important problem, for example in visual surveillance or internet scale data. For such large and evolving real-world data...
Chen Change Loy, Timothy M. Hospedales, Tao Xiang,...
Interactive navigation in image-based scenes requires random access to the compressed reference image data. When using state of the art block-based hybrid video coding techniques,...
We modify the multilevel successive elimination algorithm (MSEA) to make it compatible with the motion estimation required for the H.264/AVC video coding standard. The algorithm m...
This study used eye-tracking technology to assess where helpers look as they are providing assistance to a worker during collaborative physical tasks. Gaze direction was coded int...
Susan R. Fussell, Leslie D. Setlock, Elizabeth M. ...