# Video2IMU: Realistic IMU features and signals from videos

arXiv: https://arxiv.org/abs/2202.06547 · HTML: https://mlsanity.com/paper/2202.06547/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 20 references that are in the map.
- First posted on arXiv 14 Feb 2022.

## Builds on (most cited first, 7 of 7)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [DeepPose: Human Pose Estimation via Deep Neural Networks](https://mlsanity.com/paper/1312.4659/) (2013)
- [Time Series Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2002.12478/) (2020)
- [Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation](https://mlsanity.com/paper/1805.09707/) (2018)
- [Improving Deep Learning using Generic Data Augmentation](https://mlsanity.com/paper/1708.06020/) (2017)

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

- [VSMP-IMU: Video-Grounded Semantic Motion Programs for Sensor-Aware Synthetic IMU Generation](https://mlsanity.com/paper/2608.05782/) (2026)

## Abstract (arXiv)

Human Activity Recognition (HAR) from wearable sensor data identifies movements or activities in unconstrained environments. HAR is a challenging problem as it presents great variability across subjects. Obtaining large amounts of labelled data is not straightforward, since wearable sensor signals are not easy to label upon simple human inspection. In our work, we propose the use of neural networks for the generation of realistic signals and features using human activity monocular videos. We show how these generated features and signals can be utilized, instead of their real counterparts, to train HAR models that can recognize activities using signals obtained with wearable sensors. To prove the validity of our methods, we perform experiments on an activity recognition dataset created for the improvement of industrial work safety. We show that our model is able to realistically generate virtual sensor signals and features usable to train a HAR classifier with comparable performance as the one trained using real sensor data. Our results enable the use of available, labelled video data for training HAR models to classify signals from wearable sensors.