We present a framework for the automatic recognition of complex multi-agent events in settings where structure is imposed by rules that agents must follow while performing activit...
The extracted low resolution video from a motion compensated 3-D subband/wavelet scalable video coder is unnecessarily sharp and sometimes contains significant aliasing, compared ...
We propose a new Bayesian approach to object-based image retrieval with relevance feedback. Although estimating the object posterior probability density from few examples seems in...
Derek Hoiem, Rahul Sukthankar, Henry Schneiderman,...
We propose a novel classification approach for automatically detecting pulmonary embolism (PE) from computedtomography-angiography images. Unlike most existing approaches that req...
The paper has two main contributions: The rst is a set of methods for computing structure and motion for m 3 views of 6 points. It is shown that a geometric image error can be mini...
Frederik Schaffalitzky, Andrew Zisserman, Richard ...