Thin-Slicing for Pose: Learning to Understand Pose Without Explicit Pose Estimation
Abstract
We address the problem of learning a pose-aware, compact embedding that projects images with similar human poses to be placed close-by in the embedding space. The embedding function is built on a deep convolutional network, and trained with triplet-based rank constraints on real image data. This architecture allows us to learn a robust representation that captures differences in human poses by effectively factoring out variations in clothing, background, and imaging conditions in the wild. For a variety of pose-related tasks, the proposed pose embedding provides a cost-efficient and natural alternative to explicit pose estimation, circumventing challenges of localizing body joints. We demonstrate the efficacy of the embedding on pose-based image retrieval and action recognition problems.
Cite
Text
Kwak et al. "Thin-Slicing for Pose: Learning to Understand Pose Without Explicit Pose Estimation." Conference on Computer Vision and Pattern Recognition, 2016. doi:10.1109/CVPR.2016.534Markdown
[Kwak et al. "Thin-Slicing for Pose: Learning to Understand Pose Without Explicit Pose Estimation." Conference on Computer Vision and Pattern Recognition, 2016.](https://mlanthology.org/cvpr/2016/kwak2016cvpr-thinslicing/) doi:10.1109/CVPR.2016.534BibTeX
@inproceedings{kwak2016cvpr-thinslicing,
title = {{Thin-Slicing for Pose: Learning to Understand Pose Without Explicit Pose Estimation}},
author = {Kwak, Suha and Cho, Minsu and Laptev, Ivan},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2016},
doi = {10.1109/CVPR.2016.534},
url = {https://mlanthology.org/cvpr/2016/kwak2016cvpr-thinslicing/}
}