DMCA
Describing People: A Poselet-Based Approach to Attribute Classification ∗
Cached
Download Links
| Citations: | 43 - 4 self |
BibTeX
@MISC{Bourdev_describingpeople:,
author = {Lubomir Bourdev and Subhransu Maji and Jitendra Malik},
title = {Describing People: A Poselet-Based Approach to Attribute Classification ∗},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
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. Figure 1. People can easily infer the gender based on the face, the hair style, the body proportions and the types of clothes. A robust gender classifier should take into account all such available cues. 1.
Keyphrases
attribute classification poselet-based approach hair style available cue attribute classifier challenging problem body proportion personal photo album image method performs part-based approach robust attribute classifier commercial face recognition system discriminative model annotated attribute robust gender classifier occlusion typical gender recognition large variation spatial pyramid match kernel method new dataset
