Agreement function model for pose estimation

Pose estimation is a critical problem in the challenge of visual object recognition. An alternative model, agreement function (AF), is proposed to solve this problem, which is essentially a generative model since it is learned to represent the joint probability distribution of the inputs and their poses. Estimated poses of unseen samples can be obtained by maximising the AF conditional on the given samples. Extensive experiments are performed on several challenging datasets to validate the authors' model, and achieved state-of-the-art experimental results.