Agreement function model for pose estimation. Issue 20 (1st September 2016)

• Record Type: Journal Article
• Authors: Zhang, Haopeng; Jiang, Zhiguo
• Is Part Of: Electronics letters. Volume 52:Issue 20(2016)
• Page Start: 1677
• Page End: 1679
• Publication Date: 2016-09-01
• Subjects: pose estimation -- object recognition -- statistical distributions; agreement function model -- pose estimation -- visual object recognition -- generative model -- joint probability distribution -- AF conditional maximisation; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2016.2338
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : 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.