This paper develops a theory of frequency domain invariants in computer vision. We derive novel identities using spherical harmonics, which are the angular frequency domain analog ...
Suppose a set of arbitrary (unlabeled) images contains frequent occurrences of 2D objects from an unknown category. This paper is aimed at simultaneously solving the following rel...
We propose a new and powerful tool for the analysis of trajectories, which in particular allows for more temporally aware analyses. Time plays an important role in the analysis of ...
The Hough transform provides an efficient way to detect objects. Various methods have been proposed to achieve discriminative learning of the Hough transform, but they have usuall...
This paper addresses the problem of simultaneous tracking of multiple targets in a video. We first apply object detectors to every video frame. Pairs of detection responses from ...