Finding fiducial facial points in any frame of a video showing rich naturalistic facial behaviour is an unsolved problem. Yet this is a crucial step for geometric-featurebased fa...
Michel Valstar, Brais Martinez, Xavier Binefa, Maj...
Electronic theses and dissertations (ETDs) are a unique genre that is emerging in part as a result of the work to build the Networked Digital Library of Theses and Dissertations (...
Ranking large scale image and video collections usually expects higher accuracy on top ranked data, while tolerates lower accuracy on bottom ranked ones. In view of this, we propo...
Object recognition and detection represent a relevant component in cognitive computer vision systems, such as in robot vision, intelligent video surveillance systems, or multi-mod...
Gerald Fritz, Christin Seifert, Lucas Paletta, Hor...
We consider a class of learning problems that involve a structured sparsityinducing norm defined as the sum of -norms over groups of variables. Whereas a lot of effort has been pu...