no code implementations • 8 Feb 2017 • Ehsan Jahangiri, Alan L. Yuille
We propose a method to generate multiple diverse and valid human pose hypotheses in 3D all consistent with the 2D detection of joints in a monocular RGB image.
no code implementations • 9 Jan 2017 • Ehsan Jahangiri, Erdem Yoruk, Rene Vidal, Laurent Younes, Donald Geman
Despite enormous progress in object detection and classification, the problem of incorporating expected contextual relationships among object instances into modern recognition systems remains a key challenge.