This work addresses the problem of human action recognition by introducing a representation of a human action as a collection of short trajectories that are extracted in areas of ...
Antonios Oikonomopoulos, Ioannis Patras, Maja Pant...
A great need exists in many fields of eye-tracking research for a robust and general method for scanpath comparisons. Current measures either quantize scanpaths in space (string e...
Halszka Jarodzka, Kenneth Holmqvist, Marcus Nystr&...
Transparency can be a useful device for simultaneously depicting multiple superimposed layers of information in a single image. However, in computer-generated pictures -as in phot...
Victoria Interrante, Henry Fuchs, Stephen M. Pizer
Shape is an important cue for generic object recognition but can be insufficient without other cues such as object appearance. We explore a number of ways in which the geometric a...
Multiple observation improves the performance of 3D object classification. However, since the distribution of feature vectors obtained from multiple view points have strong nonlin...