Pose pooling kernels for sub-category recognition

TL;DR: This work develops representations for poselet-based pose normalization using both explicit warping and implicit pooling as mechanisms and defines a pose normalized similarity or kernel function that is suitable for nearest-neighbor or kernel-based learning methods.

Abstract: The ability to normalize pose based on super-category landmarks can significantly improve models of individual categories when training data are limited. Previous methods have considered the use of volumetric or morphable models for faces and for certain classes of articulated objects. We consider methods which impose fewer representational assumptions on categories of interest, and exploit contemporary detection schemes which consider the ensemble of responses of detectors trained for specific posekeypoint configurations. We develop representations for poselet-based pose normalization using both explicit warping and implicit pooling as mechanisms. Our method defines a pose normalized similarity or kernel function that is suitable for nearest-neighbor or kernel-based learning methods.