Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlu...
We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor pri...
Many learning tasks for computer vision problems can be described by multiple views or multiple features. These views can be exploited in order to learn from unlabeled data, a.k.a....
Recent work in the field of machine translation (MT) evaluation suggests that sentence level evaluation based on machine learning (ML) can outperform the standard metrics such as B...
Antoine Veillard, Elvina Melissa, Cassandra Theodo...
We present an approach to visual object-class recognition and segmentation based on a pipeline that combines multiple, holistic figure-ground hypotheses generated in a bottom-up,...