We describe a mid-level approach for action recognition. From an input video, we extract salient spatio-temporal structures by forming clusters of trajectories that serve as candi...
A new computational model for active visual attention is introduced in this paper. The method extracts motion and shape features from video image sequences, and integrates these f...
This paper1 describes a method for tracking regions in image sequences. Regions segmented from each frame by a motion segmentation technique are matched by using a relaxation proc...
We consider the problem of estimating the relative orientation of a number of individual photocells -or pixels- that hold fixed relative positions. The photocells measure the inte...
Abstract— We study the problem of registering local relative pose estimates to produce a global consistent trajectory of a moving robot. Traditionally, this problem has been stud...