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
Discriminative modelArtificial intelligenceComputer sciencePattern recognition (psychology)Pyramid (geometry)ClothingKernel (algebra)Variation (astronomy)Support vector machineInvariant (physics)Face (sociological concept)Feature extractionMachine learningComputer visionMathematicsGeography
Affiliated Institutions
Related Publications
PANDA: Pose Aligned Networks for Deep Attribute Modeling
We propose a method for inferring human attributes (such as gender, hair style, clothes style, expression, action) from images of people under large variation of viewpoint, pose...
Deformable Part Descriptors for Fine-Grained Recognition and Attribute Prediction
Recognizing objects in fine-grained domains can be extremely challenging due to the subtle differences between subcategories. Discriminative markings are often highly localized,...
Attribute and simile classifiers for face verification
We present two novel methods for face verification. Our first method - "attribute" classifiers - uses binary classifiers trained to recognize the presence or absence of describa...
SUN attribute database: Discovering, annotating, and recognizing scene attributes
In this paper we present the first large-scale scene attribute database. First, we perform crowd-sourced human studies to find a taxonomy of 102 discriminative attributes. Next,...
Tom-vs-Pete Classifiers and Identity-Preserving Alignment for Face Verification
We propose a method of face verification that takes advantage of a reference set of faces, disjoint by identity from the test faces, labeled with identity and face part location...
Publication Info
- Year
- 2011
- Type
- article
- Pages
- 1543-1550
- Citations
- 337
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
337
OpenAlex
Cite This
Lubomir Bourdev,
Subhransu Maji,
Jitendra Malik
(2011).
Describing people: A poselet-based approach to attribute classification.
, 1543-1550.
https://doi.org/10.1109/iccv.2011.6126413
Identifiers
- DOI
- 10.1109/iccv.2011.6126413