We present a novel method for recovering the 3D structure and scene flow from calibrated multi-view sequences. We propose a 3D point cloud parametrization of the 3D structure and ...
In this paper, we present a novel method, the first to date to our knowledge, which is capable of directly and automatically producing a concise and idealized 3D representation f...
Anne-Laure Chauve, Patrick Labatut, Jean-Philippe ...
In order for recognition systems to scale to a larger number of object categories building visual class taxonomies is important to achieve running times logarithmic in the number o...
The ability for an agent to reason under uncertainty is crucial for many planning applications, since an agent rarely has access to complete, error-free information about its envi...
We present a method for unsupervised learning of event classes from videos in which multiple actions might occur simultaneously. It is assumed that all such activities are produce...
Muralikrishna Sridhar, Anthony G. Cohn, David C. H...