# Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation

arXiv: https://arxiv.org/abs/2507.12292 · HTML: https://mlsanity.com/paper/2507.12292/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 16 Jul 2025.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose](https://mlsanity.com/paper/2303.07399/) (2023)
- [An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1902.09130/) (2019)
- [Learning To Score Olympic Events](https://mlsanity.com/paper/1611.05125/) (2016)
- [Action Quality Assessment Across Multiple Actions](https://mlsanity.com/paper/1812.06367/) (2018)
- [Fine-grained Visual Classification with High-temperature Refinement and Background Suppression](https://mlsanity.com/paper/2303.06442/) (2023)
- [Masking Strategies for Background Bias Removal in Computer Vision Models](https://mlsanity.com/paper/2308.12127/) (2023)
- [Towards cumulative race time regression in sports: I3D ConvNet transfer learning in ultra-distance running events](https://mlsanity.com/paper/2208.11191/) (2022)
- [CLAD: A Contrastive Learning based Approach for Background Debiasing](https://mlsanity.com/paper/2210.02748/) (2022)
- [Mitigating the Effect of Incidental Correlations on Part-based Learning](https://mlsanity.com/paper/2310.00377/) (2023)
- [Classifying Soccer Ball-on-Goal Position Through Kicker Shooting Action](https://mlsanity.com/paper/2312.15236/) (2023)
- [A Large-Scale Re-identification Analysis in Sporting Scenarios: the Betrayal of Reaching a Critical Point](https://mlsanity.com/paper/2401.00080/) (2023)

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

- [Can Vision-Language Models Judge Olympic Diving? From Reasoning to Scores in Zero-Shot Action Quality Assessment](https://mlsanity.com/paper/2609.19354/) (2026)

## Abstract (arXiv)

Calisthenics skill classification is the computer vision task of inferring the skill performed by an athlete from images, enabling automatic performance assessment and personalized analytics. Traditional methods for calisthenics skill recognition are based on pose estimation methods to determine the position of skeletal data from images, which is later fed to a classification algorithm to infer the performed skill. Despite the progress in human pose estimation algorithms, they still involve high computational costs, long inference times, and complex setups, which limit the applicability of such approaches in real-time applications or mobile devices. This work proposes a direct approach to calisthenics skill recognition, which leverages depth estimation and athlete patch retrieval to avoid the computationally expensive human pose estimation module. Using Depth Anything V2 for depth estimation and YOLOv10 for athlete localization, we segment the subject from the background rather than relying on traditional pose estimation techniques. This strategy increases efficiency, reduces inference time, and improves classification accuracy. Our approach significantly outperforms skeleton-based methods, achieving 38.3x faster inference with RGB image patches and improved classification accuracy with depth patches (0.837 vs. 0.815). Beyond these performance gains, the modular design of our pipeline allows for flexible replacement of components, enabling future enhancements and adaptation to real-world applications.