English

Discovering Useful Parts for Pose Estimation in Sparsely Annotated Datasets

Computer Vision and Pattern Recognition 2016-05-04 v1

Abstract

Our work introduces a novel way to increase pose estimation accuracy by discovering parts from unannotated regions of training images. Discovered parts are used to generate more accurate appearance likelihoods for traditional part-based models like Pictorial Structures [13] and its derivatives. Our experiments on images of a hawkmoth in flight show that our proposed approach significantly improves over existing work [27] for this application, while also being more generally applicable. Our proposed approach localizes landmarks at least twice as accurately as a baseline based on a Mixture of Pictorial Structures (MPS) model. Our unique High-Resolution Moth Flight (HRMF) dataset is made publicly available with annotations.

Keywords

Cite

@article{arxiv.1605.00707,
  title  = {Discovering Useful Parts for Pose Estimation in Sparsely Annotated Datasets},
  author = {Mikhail Breslav and Tyson L. Hedrick and Stan Sclaroff and Margrit Betke},
  journal= {arXiv preprint arXiv:1605.00707},
  year   = {2016}
}

Comments

Accepted at WACV 2016

R2 v1 2026-06-22T13:47:21.863Z