We tackle the problem of learning a rotation invariant latent factor model when the training data is comprised of lower-dimensional projections of the original feature space. The main goal is the discovery of a set of 3-D bases poses that can characterize the manifold of primitive human motions, or movemes, from a training set of 2-D projected poses obtained from still images taken at various camera angles. The proposed technique for basis discovery is data-driven rather than hand-designed. The learned representation is rotation invariant, and can reconstruct any training instance from multiple viewing angles. We apply our method to modeling human poses in sports (via the Leeds Sports Dataset), and demonstrate the effectiveness of the learned bases in a range of applications such as activity classification, inference of dynamics from a single frame, and synthetic representation of movements.
@article{arxiv.1609.07495,
title = {A Rotation Invariant Latent Factor Model for Moveme Discovery from Static Poses},
author = {Matteo Ruggero Ronchi and Joon Sik Kim and Yisong Yue},
journal= {arXiv preprint arXiv:1609.07495},
year = {2016}
}
Comments
Long version of the paper accepted at the IEEE ICDM 2016 conference. 10 pages, 9 figures, 1 table. Project page: http://www.vision.caltech.edu/~mronchi/projects/RotationInvariantMovemes/