# VI-Net: View-Invariant Quality of Human Movement Assessment

arXiv: https://arxiv.org/abs/2008.04999 · HTML: https://mlsanity.com/paper/2008.04999/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2020.

## Built on by (most cited first, 8 of 8)

- [Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment](https://mlsanity.com/paper/2202.14019/) (2022)
- [Piano Skills Assessment](https://mlsanity.com/paper/2101.04884/) (2021)
- [Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment](https://mlsanity.com/paper/2403.13798/) (2024)
- [Computer Vision for Clinical Gait Analysis: A Gait Abnormality Video Dataset](https://mlsanity.com/paper/2407.04190/) (2024)
- [A Decade of Action Quality Assessment: Largest Systematic Survey of Trends, Challenges, and Future Directions](https://mlsanity.com/paper/2502.02817/) (2025)
- [Unsupervised View-Invariant Human Posture Representation](https://mlsanity.com/paper/2109.08730/) (2021)
- [ExeChecker: Where Did I Go Wrong?](https://mlsanity.com/paper/2412.10573/) (2024)
- [MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and Coaching](https://mlsanity.com/paper/2608.26094/) (2026)

## Abstract (arXiv)

We propose a view-invariant method towards the assessment of the quality of human movements which does not rely on skeleton data. Our end-to-end convolutional neural network consists of two stages, where at first a view-invariant trajectory descriptor for each body joint is generated from RGB images, and then the collection of trajectories for all joints are processed by an adapted, pre-trained 2D CNN (e.g. VGG-19 or ResNeXt-50) to learn the relationship amongst the different body parts and deliver a score for the movement quality. We release the only publicly-available, multi-view, non-skeleton, non-mocap, rehabilitation movement dataset (QMAR), and provide results for both cross-subject and cross-view scenarios on this dataset. We show that VI-Net achieves average rank correlation of 0.66 on cross-subject and 0.65 on unseen views when trained on only two views. We also evaluate the proposed method on the single-view rehabilitation dataset KIMORE and obtain 0.66 rank correlation against a baseline of 0.62.