Describing people: A poselet-based approach to attribute classification
Authors:
- 1 November 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1543-1550
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.Keywords
This publication has 16 references indexed in Scilit:
- Action recognition from a distributed representation of pose and appearance2011
- Attribute-centric recognition for cross-category generalization2010
- Attribute and simile classifiers for face verification2009
- Describing objects by their attributes2009
- Learning to detect unseen object classes by between-class attribute transfer2009
- Progressive search space reduction for human pose estimation2008
- Estimating age, gender, and identity using first name priors2008
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories2006
- A unified learning framework for real time face detection and classification2003
- Learning gender with support facesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002