— This work details the authors’ efforts to push the baseline of expression recognition performance on a realistic database. Both subject-dependent and subject-independent emot...
Usman Tariq, Kai-Hsiang Lin, Zhen Li, Xi Zhou, Zha...
In this paper, we present a method for human action recognition from multi-view image sequences that uses the combined motion and shape flow information with variability considera...
Variational methods are among the most accurate techniques for estimating the optic flow. They yield dense flow fields and can be designed such that they preserve discontinuities, ...
This paper presents an application of optic flow estimation to image metamorphosis. It uses a state of the art optical flow algorithm to do image metamorphosis, which is used in v...
We have designed and tested a single-chip analog VLSI sensor that detects imminent collisions by measuring radially expansive optic flow. The design of the chip is based on a mode...
Catadioptric omnidirectional sensors (catadioptric cameras) capture instantaneous images with panoramic 360 field of view. Entire surroundings are projected via a circularly symme...
Abstract. Rigidity and reflectance are key object properties, important in their own rights, and they are key properties that stratify motion reconstruction algorithms. However, th...
We test the hypothesis that: (1) Optic flow can be used to detect significant environmental features during locomotion in a biped, even given significant up and down movement and j...