A Rotation Invariant Latent Factor Model for Moveme Discovery from Static Poses
This work addresses the challenge of modeling human poses from static images for applications in sports and movement analysis, representing an incremental improvement in domain-specific methods.
The paper tackles the problem of learning a rotation invariant latent factor model from 2-D projected poses to discover 3-D bases for human movemes, demonstrating effectiveness in applications like activity classification and inference of dynamics from a single frame.
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.