# Yoga-82: A New Dataset for Fine-grained Classification of Human Poses

arXiv: https://arxiv.org/abs/2004.10362 · HTML: https://mlsanity.com/paper/2004.10362/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2020.

## Built on by (most cited first, 25 of 25)

- [3D Human Pose Estimation via Intuitive Physics](https://mlsanity.com/paper/2303.18246/) (2023)
- [FLAG3D: A 3D Fitness Activity Dataset with Language Instruction](https://mlsanity.com/paper/2212.04638/) (2022)
- [Video Action Differencing](https://mlsanity.com/paper/2503.07860/) (2025)
- [FixMyPose: Pose Correctional Captioning and Retrieval](https://mlsanity.com/paper/2104.01703/) (2021)
- [Fine-Grained Sports, Yoga, and Dance Postures Recognition: A Benchmark Analysis](https://mlsanity.com/paper/2308.00323/) (2023)
- [InfiniteForm: A synthetic, minimal bias dataset for fitness applications](https://mlsanity.com/paper/2110.01330/) (2021)
- [Representation Learning by Detecting Incorrect Location Embeddings](https://mlsanity.com/paper/2204.04788/) (2022)
- [Pose Prior Learner: Unsupervised Categorical Prior Learning for Pose Estimation](https://mlsanity.com/paper/2410.03858/) (2024)
- [Joint Learning On The Hierarchy Representation for Fine-Grained Human Action Recognition](https://mlsanity.com/paper/2110.05853/) (2021)
- [Encoding Hierarchical Information in Neural Networks helps in Subpopulation Shift](https://mlsanity.com/paper/2112.10844/) (2021)
- [3DYoga90: A Hierarchical Video Dataset for Yoga Pose Understanding](https://mlsanity.com/paper/2310.10131/) (2023)
- [A Computer Vision-Based Approach for Driver Distraction Recognition using Deep Learning and Genetic Algorithm Based Ensemble](https://mlsanity.com/paper/2107.13355/) (2021)
- [A View Independent Classification Framework for Yoga Postures](https://mlsanity.com/paper/2206.13577/) (2022)
- [MuJo: Multimodal Joint Feature Space Learning for Human Activity Recognition](https://mlsanity.com/paper/2406.03857/) (2024)
- [Informed deep hierarchical classification: a non-standard analysis inspired approach](https://mlsanity.com/paper/2409.16956/) (2024)
- [PointT2I: LLM-based text-to-image generation via keypoints](https://mlsanity.com/paper/2506.01370/) (2025)
- [TaiChi Action Capture and Performance Analysis with Multi-view RGB Cameras](https://mlsanity.com/paper/2306.14490/) (2023)
- [Real-Time Feedback and Benchmark Dataset for Isometric Pose Evaluation](https://mlsanity.com/paper/2506.11774/) (2025)
- [An Efficient Deep Convolutional Neural Network Model For Yoga Pose Recognition Using Single Images](https://mlsanity.com/paper/2306.15768/) (2023)
- [Yoga Pose Classification Using Transfer Learning](https://mlsanity.com/paper/2411.00833/) (2024)
- [Exploring the Use of Contrastive Language-Image Pre-Training for Human Posture Classification: Insights from Yoga Pose Analysis](https://mlsanity.com/paper/2501.07221/) (2025)
- [PosePilot: An Edge-AI Solution for Posture Correction in Physical Exercises](https://mlsanity.com/paper/2505.19186/) (2025)
- [Integrating Skeleton Based Representations for Robust Yoga Pose Classification Using Deep Learning Models](https://mlsanity.com/paper/2512.00572/) (2025)
- [MotionHalluc: Diagnosing Kinematic Hallucinations in Fine-Grained Motion Reasoning](https://mlsanity.com/paper/2606.23061/) (2026)
- [SAGE-Yoga: Multi-Cue Learning for Yoga Pose Classification and Joint-Level Correction](https://mlsanity.com/paper/2609.20245/) (2026)

## Abstract (arXiv)

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.