Loading...
Please wait, while we are loading the content...
Similar Documents
Modec: Multimodal decomposable models for human pose estimation (2013)
| Content Provider | CiteSeerX |
|---|---|
| Author | Taskar, Ben |
| Description | We propose a multimodal, decomposable model for ar-ticulated human pose estimation in monocular images. A typical approach to this problem is to use a linear struc-tured model, which struggles to capture the wide range of appearance present in realistic, unconstrained images. In this paper, we instead propose a model of human pose that explicitly captures a variety of pose modes. Unlike other multimodal models, our approach includes both global and local pose cues and uses a convex objective and joint train-ing for mode selection and pose estimation. We also employ a cascaded mode selection step which controls the trade-off between speed and accuracy, yielding a 5x speedup in in-ference and learning. Our model outperforms state-of-the-art approaches across the accuracy-speed trade-off curve for several pose datasets. This includes our newly-collected dataset of people in movies, FLIC, which contains an or-der of magnitude more labeled data for training and testing than existing datasets. The new dataset and code are avail-able online. 1 1. In Computer Vision and Pattern Recognition (CVPR) |
| File Format | |
| Language | English |
| Publisher Date | 2013-01-01 |
| Access Restriction | Open |
| Subject Keyword | Local Pose Cue Typical Approach Unconstrained Image Joint Train-ing Labeled Data Cascaded Mode Selection Step Ar-ticulated Human Pose Estimation Newly-collected Dataset Pose Mode Convex Objective Several Pose Datasets New Dataset Pose Estimation Decomposable Model Monocular Image Wide Range Avail-able Online State-of-the-art Approach Mode Selection Multimodal Decomposable Model Multimodal Model Accuracy-speed Trade-off Curve Linear Struc-tured Model Human Pose Estimation Appearance Present |
| Content Type | Text |
| Resource Type | Article |
