# Activity-conditioned continuous human pose estimation for performance analysis of athletes using the example of swimming

arXiv: https://arxiv.org/abs/1802.00634 · HTML: https://mlsanity.com/paper/1802.00634/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Feb 2018.

## Built on by (most cited first, 9 of 9)

- [MEGA: Masked Generative Autoencoder for Human Mesh Recovery](https://mlsanity.com/paper/2405.18839/) (2024)
- [VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space](https://mlsanity.com/paper/2312.08291/) (2023)
- [Detecting Arbitrary Keypoints on Limbs and Skis with Sparse Partly Correct Segmentation Masks](https://mlsanity.com/paper/2211.09446/) (2022)
- [Three-Stream 3D/1D CNN for Fine-Grained Action Classification and Segmentation in Table Tennis](https://mlsanity.com/paper/2109.14306/) (2021)
- [Recognition of Freely Selected Keypoints on Human Limbs](https://mlsanity.com/paper/2204.06326/) (2022)
- [Towards Learning Monocular 3D Object Localization From 2D Labels using the Physical Laws of Motion](https://mlsanity.com/paper/2310.17462/) (2023)
- [Sports Video: Fine-Grained Action Detection and Classification of Table Tennis Strokes from Videos for MediaEval 2021](https://mlsanity.com/paper/2112.11384/) (2021)
- [Motion-DVAE: Unsupervised learning for fast human motion denoising](https://mlsanity.com/paper/2306.05846/) (2023)
- [SwimXYZ: A large-scale dataset of synthetic swimming motions and videos](https://mlsanity.com/paper/2310.04360/) (2023)

## Abstract (arXiv)

In this paper we consider the problem of human pose estimation in real-world videos of swimmers. Swimming channels allow filming swimmers simultaneously above and below the water surface with a single stationary camera. These recordings can be used to quantitatively assess the athletes' performance. The quantitative evaluation, so far, requires manual annotations of body parts in each video frame. We therefore apply the concept of CNNs in order to automatically infer the required pose information. Starting with an off-the-shelf architecture, we develop extensions to leverage activity information - in our case the swimming style of an athlete - and the continuous nature of the video recordings. Our main contributions are threefold: (a) We apply and evaluate a fine-tuned Convolutional Pose Machine architecture as a baseline in our very challenging aquatic environment and discuss its error modes, (b) we propose an extension to input swimming style information into the fully convolutional architecture and (c) modify the architecture for continuous pose estimation in videos. With these additions we achieve reliable pose estimates with up to +16% more correct body joint detections compared to the baseline architecture.