Synergistic Face Detection and Pose Estimation with Energy-Based Models

We describe a novel method for real-time, simultaneous multi-view face detection and facial pose estimation. The method employs a convolutional network to map face images to points on a manifold, parametrized by pose, and non-face images to points far from that manifold. This network is trained by optimizing a loss function of three variables: image, pose, and face/non-face label. We test the resulting system, in a single configuration, on three standard data sets

• Type: Conference
• Year: 2006
• Where: CLOR
• Authors: Margarita Osadchy, Yann LeCun, Matthew L. Miller
• Keywords: CLOR 2006, Computer Vision, Facial Pose Estimation, Multi-view Face, Pose Estimation