Pose Embeddings: A Deep Architecture for Learning to Match Human Poses
Venue
arXiv (2015)
Publication Year
2015
Authors
Greg Mori, Caroline Pantofaru, Nisarg Kothari, Thomas Leung, George Toderici, Alexander Toshev, Weilong Yang
BibTeX
Abstract
We present a method for learning an embedding that places images of humans in
similar poses nearby. This embedding can be used as a direct method of comparing
images based on human pose, avoiding potential challenges of estimating body joint
positions. Pose embedding learning is formulated under a triplet-based distance
criterion. A deep architecture is used to allow learning of a representation
capable of making distinctions between different poses. Experiments on human pose
matching and retrieval from video data demonstrate the potential of the method.
