Yoga-82: A New Dataset for Fine-grained Classification of Human Poses
This addresses the problem of limited pose variety for computer vision researchers, but it is incremental as it focuses on a specific domain.
The authors tackled the lack of pose diversity in existing human pose datasets by proposing Yoga-82, a large-scale dataset for fine-grained yoga pose classification with 82 classes, and reported classification accuracy using state-of-the-art convolutional neural networks.
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.