Using k-Poselets for Detecting People and Localizing Their Keypoints

Abstract

A k-poselet is a deformable part model (DPM) with k parts, where each of the parts is a poselet, aligned to a specific configuration of keypoints based on ground-truth annotations. A separate template is used to learn the appearance of each part. The parts are allowed to move with respect to each other with a deformation cost that is learned at training time. This model is richer than both the traditional version of poselets and DPMs. It enables a unified approach to person detection and keypoint prediction which, barring contemporaneous approaches based on CNN features, achieves state-of-the-art keypoint prediction while maintaining competitive detection performance.

Keywords

Computer scienceArtificial intelligenceGround truthState (computer science)Pattern recognition (psychology)Computer visionAlgorithm

Affiliated Institutions

University of California, Berkeley US

Related Publications

Cascaded Pyramid Network for Multi-person Pose Estimation

Yilun Chen , Zhicheng Wang , Yuxiang Peng +3 more

The topic of multi-person pose estimation has been largely improved recently, especially with the development of convolutional neural network. However, there still exist a lot o...

2018 2018 IEEE/CVF Conference on Computer ... 1733 citations

Towards Accurate Multi-person Pose Estimation in the Wild

George Papandreou , Tyler Zhu , Nori Kanazawa +4 more

We propose a method for multi-person detection and 2-D pose estimation that achieves state-of-art results on the challenging COCO keypoints task. It is a simple, yet powerful, t...

2017 882 citations

Deformable Part Descriptors for Fine-Grained Recognition and Attribute Prediction

Ning Zhang , Ryan Farrell , Forrest Iandola +1 more

Recognizing objects in fine-grained domains can be extremely challenging due to the subtle differences between subcategories. Discriminative markings are often highly localized,...

2013 201 citations

Describing people: A poselet-based approach to attribute classification

Lubomir Bourdev , Subhransu Maji , Jitendra Malik

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 occlusio...

2011 337 citations

End-to-End Recovery of Human Shape and Pose

Angjoo Kanazawa , Michael J. Black , David W. Jacobs +1 more

We describe Human Mesh Recovery (HMR), an end-to-end framework for reconstructing a full 3D mesh of a human body from a single RGB image. In contrast to most current methods tha...

2018 2018 IEEE/CVF Conference on Computer ... 1811 citations

Publication Info

Year: 2014
Type: article
Citations: 172
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Using k-Poselets for Detecting People and Localizing Their Keypoints

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

172

OpenAlex

Cite This

APA Style

                            
                                    Georgia Gkioxari, 
                                
                                    Bharath Hariharan, 
                                
                                    Ross Girshick
                                
                                et al.
                            
                            (2014). 
                            Using k-Poselets for Detecting People and Localizing Their Keypoints. 
                            
                            .
                            https://doi.org/10.1109/cvpr.2014.458

Identifiers

DOI: 10.1109/cvpr.2014.458