# Real-Time Feedback and Benchmark Dataset for Isometric Pose Evaluation

arXiv: https://arxiv.org/abs/2506.11774 · HTML: https://mlsanity.com/paper/2506.11774/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 46 references that are in the map.
- First posted on arXiv 13 Jun 2025.

## Builds on (most cited first, 12 of 12)

- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [Human Action Recognition from Various Data Modalities: A Review](https://mlsanity.com/paper/2012.11866/) (2020)
- [PYSKL: Towards Good Practices for Skeleton Action Recognition](https://mlsanity.com/paper/2205.09443/) (2022)
- [Yoga-82: A New Dataset for Fine-grained Classification of Human Poses](https://mlsanity.com/paper/2004.10362/) (2020)
- [Pose Trainer: Correcting Exercise Posture using Pose Estimation](https://mlsanity.com/paper/2006.11718/) (2020)
- [3D Pose Based Feedback for Physical Exercises](https://mlsanity.com/paper/2208.03257/) (2022)
- [Spatio-Temporal Pyramid Graph Convolutions for Human Action Recognition and Postural Assessment](https://mlsanity.com/paper/1912.03442/) (2019)
- [Using Learnable Physics for Real-Time Exercise Form Recommendations](https://mlsanity.com/paper/2310.07221/) (2023)
- [Benchmarking Reliability of Deep Learning Models for Pathological Gait Classification](https://mlsanity.com/paper/2409.13643/) (2024)
- [3DYoga90: A Hierarchical Video Dataset for Yoga Pose Understanding](https://mlsanity.com/paper/2310.10131/) (2023)
- [Validation of Human Pose Estimation and Human Mesh Recovery for Extracting Clinically Relevant Motion Data from Videos](https://mlsanity.com/paper/2503.14760/) (2025)

## Built on by (most cited first, 1 of 1)

- [FitAQA: A Benchmark of Fitness Action Quality Assessment for Multimodal Large Language Models](https://mlsanity.com/paper/2608.08736/) (2026)

## Abstract (arXiv)

Isometric exercises appeal to individuals seeking convenience, privacy, and minimal dependence on equipments. However, such fitness training is often overdependent on unreliable digital media content instead of expert supervision, introducing serious risks, including incorrect posture, injury, and disengagement due to lack of corrective feedback. To address these challenges, we present a real-time feedback system for assessing isometric poses. Our contributions include the release of the largest multiclass isometric exercise video dataset to date, comprising over 3,600 clips across six poses with correct and incorrect variations. To support robust evaluation, we benchmark state-of-the-art models-including graph-based networks-on this dataset and introduce a novel three-part metric that captures classification accuracy, mistake localization, and model confidence. Our results enhance the feasibility of intelligent and personalized exercise training systems for home workouts. This expert-level diagnosis, delivered directly to the users, also expands the potential applications of these systems to rehabilitation, physiotherapy, and various other fitness disciplines that involve physical motion.