Yoga-82: a new dataset for fine-grained classification of human poses

Abstract

Human pose estimation is a well-known problem in computer vision to locate joint positions. Existing datasets for the learning of poses are observed to be not challenging enough in terms of pose diversity, object occlusion, and viewpoints. This makes the pose annotation process relatively simple and restricts the application of the models that have been trained on them. To handle more variety in human poses, we propose the concept of fine-grained hierarchical pose classification, in which we formulate the pose estimation as a classification task, and propose a dataset, Yoga-82, for large-scale yoga pose recognition with 82 classes. Yoga-82 consists of complex poses where fine annotations may not be possible. To resolve this, we provide hierarchical labels for yoga poses based on the body configuration of the pose. The dataset contains a three-level hierarchy including body positions, variations in body positions, and the actual pose names. We present the classification accuracy of the state-of-the-art convolutional neural network architectures on Yoga-82. We also present several hierarchical variants of DenseNet in order to utilize the hierarchical labels.

Publication
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops
Manisha Verma
Manisha Verma
Specially-Appointed Researcher/Fellow

Manisha’s research interest broadly lies in computer vision and image processing. Currently, she is working on micro facial expression recognition using multi-model deep learning frameworks.

Sudhakar Kumawat
Sudhakar Kumawat
Specially-Appointed Researcher/Fellow

His research interests are privacy preservation in computer vision, transfer learning in computational photography, and action recognition.

Yuta Nakashima
Yuta Nakashima
Associate Professor

Yuta Nakashima is an associate professor with Institute for Datability Science, Osaka University. His research interests include computer vision, pattern recognition, natural langauge processing, and their applications.

Related