— To close the loop between motion and vision, tracked visual features must remain in the camera field of view (visibility constraint). To overcome the visibility constraint, vi...
Hicham Hadj-Abdelkader, Youcef Mezouar, Nicolas An...
In this paper, we propose a multimodal system for detecting human activity and interaction patterns in a nursing home. Activities of groups of people are firstly treated as intera...
— In this paper we propose a method that exploits 3D motion-based features between frames of 3D facial geometry sequences for dynamic facial expression recognition. An expressive...
Georgia Sandbach, Stefanos Zafeiriou, Maja Pantic,...
This paper considers projective reconstruction with a hierarchical computational structure of trifocal tensors that integrates feature tracking and geometrical validation of the f...
This paper presents a new model of human attention that allows salient areas to be extracted from video frames. As automatic understanding of video semantic content is still far fr...