Describing People: A Poselet-Based Approach to Attribute Classification
Abstract
We propose a method for recognizing attributes, such as the gender, hair style and types of clothes of people under large variation in viewpoint, pose, articulation and occlusion typical of personal photo album images. Robust attribute classifiers under such conditions must be invariant to pose, but inferring the pose in itself is a challenging problem. We use a part-based approach based on poselets. Our parts implicitly decompose the aspect (the pose and viewpoint). We train attribute classifiers for each such aspect and we combine them together in a discriminative model. We propose a new dataset of 8000 people with annotated attributes. Our method performs very well on this dataset, significantly outperforming a baseline built on the spatial pyramid match kernel method. On gender recognition we outperform a commercial face recognition system.
Cite
Text
Bourdev et al. "Describing People: A Poselet-Based Approach to Attribute Classification." IEEE/CVF International Conference on Computer Vision, 2011. doi:10.1109/ICCV.2011.6126413Markdown
[Bourdev et al. "Describing People: A Poselet-Based Approach to Attribute Classification." IEEE/CVF International Conference on Computer Vision, 2011.](https://mlanthology.org/iccv/2011/bourdev2011iccv-describing/) doi:10.1109/ICCV.2011.6126413BibTeX
@inproceedings{bourdev2011iccv-describing,
title = {{Describing People: A Poselet-Based Approach to Attribute Classification}},
author = {Bourdev, Lubomir D. and Maji, Subhransu and Malik, Jitendra},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2011},
pages = {1543-1550},
doi = {10.1109/ICCV.2011.6126413},
url = {https://mlanthology.org/iccv/2011/bourdev2011iccv-describing/}
}