Pose Embeddings: A Deep Architecture for Learning to Match Human Poses

07/01/2015
by   Greg Mori, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset