In this paper we develop an algorithm for action recognition and localization in videos. The algorithm uses a figurecentric visual word representation. Different from previous ap...
Wikipedia despite having a very small budget has been among the top ten most visited websites for over half a decade. Being this visible also generated the problem of ill intended ...
It has recently been shown that only a small number of samples from a low-rank matrix are necessary to reconstruct the entire matrix. We bring this to bear on computer vision prob...
This paper advocates an implicit-surface representation of generic 3?D surfaces to take advantage of occluding edges in a very robust way. This lets us exploit silhouette constrai...
This paper discusses some of the methodological challenges that can be encountered when usability testing with visually impaired users. These include (1) the need for customized t...