Cascaded pose regression
2010
548 citations
Abstract
We present a fast and accurate algorithm for computing the 2D pose of objects in images called cascaded pose regression (CPR). CPR progressively refines a loosely specified initial guess, where each refinement is carried out by a different regressor. Each regressor performs simple image measurements that are dependent on the output of the previous regressors; the entire system is automatically learned from human annotated training examples. CPR is not restricted to rigid transformations: `pose' is any parameterized variation of the object's appearance such as the degrees of freedom of deformable and articulated objects. We compare CPR against both standard regression techniques and human performance (computed from redundant human annotations). Experiments on three diverse datasets (mice, faces, fish) suggest CPR is fast (2-3ms per pose estimate), accurate (approaching human performance), and easy to train from small amounts of labeled data.
Keywords
Computer scienceParameterized complexityArtificial intelligencePoseRegressionObject (grammar)Degrees of freedom (physics and chemistry)Computer visionPattern recognition (psychology)Variation (astronomy)3D pose estimationMachine learningAlgorithmMathematicsStatistics
Affiliated Institutions
Related Publications
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,...
DeepPose: Human Pose Estimation via Deep Neural Networks
We propose a method for human pose estimation based on Deep Neural Networks (DNNs). The pose estimation is formulated as a DNN-based regression problem towards body joints. We p...
Towards Pose Robust Face Recognition
Most existing pose robust methods are too computational complex to meet practical applications and their performance under unconstrained environments are rarely evaluated. In th...
Learn to Combine Multiple Hypotheses for Accurate Face Alignment
In this paper, we present the details of our method in attending the 300 Faces in-the-wild (300W) challenge. We build our method on cascade regression framework, where a series ...
Instance-Aware Semantic Segmentation via Multi-task Network Cascades
Semantic segmentation research has recently witnessed rapid progress, but many leading methods are unable to identify object instances. In this paper, we present Multitask Netwo...
Publication Info
- Year
- 2010
- Type
- article
- Pages
- 1078-1085
- Citations
- 548
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
548
OpenAlex
Cite This
Piotr Dollár,
Peter Welinder,
Pietro Perona
(2010).
Cascaded pose regression.
, 1078-1085.
https://doi.org/10.1109/cvpr.2010.5540094
Identifiers
- DOI
- 10.1109/cvpr.2010.5540094