Learning Dynamic Action Units for Three-dimensional Facial Expression Recognition
Pablo Arbelaez$^{1}$
$^{1}$Universidad de Los Andes. Bogotá Colombia
email: pa.arbelaez@uniandes.edu.co

Schedule:Thu 22st@10:15, Room: C

Automated understanding of facial expressions is a fundamental step towards high-level human-computer interaction. The goal of this proposal is to develop a solution to this problem by taking advantage of the color, depth and temporal information provided by an RGB-D video feed. We plan to model human facial expressions through the analysis of temporal variations in the pattern of activations of their natural constituents, three-dimensional Action Units. As starting point for algorithm development, we propose to build on our prior experience developing convolutional neural network architectures for fine-grained localization, RGB-D scene understanding and video analysis.

BibTex

@InProceedings{CLEI-2015:GoogleCharla1,
	author 		= {Pablo Arbelaez},
	title 		= {Learning Dynamic Action Units for Three-dimensional Facial Expression Recognition},
	booktitle 	= {2015 XLI Latin American Computing Conference (CLEI), Special Edition},
	pages 		= {188--188},
	year 		= {2015},
	editor 		= {Universidad Católica San Pablo},
	address 	= {Arequipa-Peru},
	month 		= {October},
	organization 	= {CLEI},
	publisher 	= {CLEI},
	url 		= {http://clei.org/clei2015/GoogleCharla1},
	isbn 		= {978-9972-825-91-0},
	}