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

Add code
Jul 01, 2015
Greg Mori, Caroline Pantofaru, Nisarg Kothari, Thomas Leung, George Toderici, Alexander Toshev, Weilong Yang

Figure 1 for Pose Embeddings: A Deep Architecture for Learning to Match Human Poses
Figure 2 for Pose Embeddings: A Deep Architecture for Learning to Match Human Poses
Figure 3 for Pose Embeddings: A Deep Architecture for Learning to Match Human Poses
Figure 4 for Pose Embeddings: A Deep Architecture for Learning to Match Human Poses

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

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.

View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon