In real-world applications of visual recognition, many factors—such as pose, illumination, or image quality—can cause a significant mismatch between the source domain on whic...
The literature currently provides two ways to establish
point correspondences between images with moving objects.
On one side, there are energy minimization methods
that yield v...
Thomas Brox (University of California, Berkeley), ...
This paper proposes a new approach for video stabilization.
Most existing video stabilization methods adopt
a framework of three steps, motion estimation, motion compensation
an...
Ken-Yi Lee, Yung-Yu, Chuang Bing-Yu, Chen Ming Ouh...
We present an unsupervised technique for detecting unusual activity in a large video set using many simple features. No complex activity models and no supervised feature selection...
We investigate to what extent `bag of visual words' models can be used to distinguish categories which have significant visual similarity. To this end we develop and optimize...