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

arXiv: https://arxiv.org/abs/1507.00302 · HTML: https://mlsanity.com/paper/1507.00302/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2015.

## Built on by (most cited first, 3 of 3)

- [Context-Aware Sequence Alignment using 4D Skeletal Augmentation](https://mlsanity.com/paper/2204.12223/) (2022)
- [Generalizing GradCAM for Embedding Networks](https://mlsanity.com/paper/2402.00909/) (2024)
- [AutoComPose: Automatic Generation of Pose Transition Descriptions for Composed Pose Retrieval Using Multimodal LLMs](https://mlsanity.com/paper/2503.22884/) (2025)

## Abstract (arXiv)

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.