Appropriate selection of the kernel function, which implicitly defines the feature space of an algorithm, has a crucial role in the success of kernel methods. In this paper, we co...
This paper proposes a generic method for action recognition
in uncontrolled videos. The idea is to use images
collected from the Web to learn representations of actions
and use ...
Nazli Ikizler-Cinbis, R. Gokberk Cinbis, Stan Scla...
This paper presents a system for fully automatic recognition and reconstruction of 3D objects in image databases. We pose the object recognition problem as one of finding consist...
A novel scheme is proposed for achieving motion segmentation in low-frame rate videos, with application to temporal super resolution. Probabilistic generative models are commonly ...
Human activity analysis is an important problem in computer
vision with applications in surveillance and summarization
and indexing of consumer content. Complex human
activities...