Poselets and Their Applications in High-Level Computer Vision

Part detectors are a common way to handle the variability in appearance in high-level computer vision problems, such as detection and semantic segmentation. Identifying good parts, however, remains an open question. Anatomical parts, such as arms and legs, are difficult to detect reliably because parallel lines are common in natural images. In contrast, a visual conjunction such as "half of a frontal face and a left shoulder" may be a perfectly good discriminative visual pattern. We propose a new computer vision part, called a poselet, which is trained to respond to a given part of the object at a given viewpoint and pose regardless of the variation in appearance.

High-level computer vision is challenging because the image is a function of multiple somewhat independent factors, such as the appearance model of the object, its pose, and the camera viewpoint. Poselets allow us to "untangle the knot" because they decouple the pose from the appearance. We show that this property helps in a variety of high-level computer vision tasks -- our poselet-based method is currently the leading approach on detection and segmentation of people on the PASCAL competitions and performs well in other visual categories. We report competitive performance for pose and action recognition and we are the first method to do attribute classification for people under any viewpoint and pose. On gender recognition we outperform Cognitec, a leading commercial face recognition engine.

Speaker: Lubomir Bourdev, UC Berkeley

Room 508-20