Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person ...
This paper describes a novel approach to the semantic relation detection problem. Instead of relying only on the training instances for a new relation, we leverage the knowledge l...
Chang Wang, James Fan, Aditya Kalyanpur, David Gon...
Current mainstream Evolutionary Algorithms (EA) are based on the concept of selection, encapsulated in the definition of a fitness function. Besides selection, however, the natur...
We present a novel algorithm aiming to estimate the 3D shape, the texture of a human face, along with the 3D pose and the light direction from a single photograph by recovering th...
This paper gives an overview of works done in our group on 3D and appearance modeling of objects, from images. The backbone of our approach is to use what we consider as the princi...