Yoga-82: A New Dataset for Fine-grained Classification of Human Poses (arXiv)


Human pose estimation is a well-known problem in computer vision to locate joint positions. Existing datasets for learning of poses are observed to be not challenging enough in terms of pose diversity, object occlusion and view points. 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.

Sample images from dataset for each of class-6 (root class) and class-20 (subclass 1)


Standing pose






Note: Images published here are under different creative common licenses. We do not own the rights of these images. Following are the links for above images.

All images of the Yoga-82 dataset are obtained from the Internet which are not property of Osaka University, Japan and IIT Gandhinagar, India. Both of these organization are not responsible for the content nor the meaning of these images. We provide web links of images used in making of this dataset along with train and test splits. Please check ReadMe.txt file after download.

Terms and Conditions:

  1. The Yoga-82 dataset is available for non-commercial research and educational purposes only.

  2. If researcher reproduce images in electronic or print media, kindly check individual image copyright for reproduction.

  3. Researcher is allowed to redistribute the dataset (in original form only that available on this webpage), if third party agrees to these conditions.

  4. If Researcher is employed by a for-profit, commercial entity, Researcher's employer shall also be bound by these terms and conditions, and Researcher hereby represents that he or she is fully authorized to enter into this agreement on behalf of such employer.


  • Pose classification baseline and hierarchical models evaluated in paper are available here.

  • Yoga pose classification tutorial on Yoga-82 dataset using Monk AI toolkit, by Tessellate Imaging Team.

Please cite the following paper if you use the dataset.

@inproceedings{verma2020yoga, title={Yoga-82: A New Dataset for Fine-grained Classification of Human Poses}, author={Verma, Manisha and Kumawat, Sudhakar and Nakashima, Yuta and Raman, Shanmuganathan}, booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)}, pages={4472-4479}, year={2020}}

Kindly mail at if you find any issue.