# DeepNAG: Deep Non-Adversarial Gesture Generation

arXiv: https://arxiv.org/abs/2011.09149 · HTML: https://mlsanity.com/paper/2011.09149/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2020.

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

- [Pixel-wise Agricultural Image Time Series Classification: Comparisons and a Deformable Prototype-based Approach](https://mlsanity.com/paper/2303.12533/) (2023)
- [Neural Latent Aligner: Cross-trial Alignment for Learning Representations of Complex, Naturalistic Neural Data](https://mlsanity.com/paper/2308.06443/) (2023)
- [Soft Dynamic Time Warping for Multi-Pitch Estimation and Beyond](https://mlsanity.com/paper/2304.05032/) (2023)
- [SCORE: Self-supervised Correspondence Fine-tuning for Improved Content Representations](https://mlsanity.com/paper/2403.06260/) (2024)
- [OTW: Optimal Transport Warping for Time Series](https://mlsanity.com/paper/2306.00620/) (2023)
- [LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related Tasks](https://mlsanity.com/paper/2406.09153/) (2024)
- [Improving the Security of Smartwatch Payment with Deep Learning](https://mlsanity.com/paper/2307.05437/) (2023)
- [hvEEGNet: exploiting hierarchical VAEs on EEG data for neuroscience applications](https://mlsanity.com/paper/2312.00799/) (2023)
- [Electric Vehicle Identification from Behind Smart Meter Data](https://mlsanity.com/paper/2509.19316/) (2025)

## Abstract (arXiv)

Synthetic data generation to improve classification performance (data augmentation) is a well-studied problem. Recently, generative adversarial networks (GAN) have shown superior image data augmentation performance, but their suitability in gesture synthesis has received inadequate attention. Further, GANs prohibitively require simultaneous generator and discriminator network training. We tackle both issues in this work. We first discuss a novel, device-agnostic GAN model for gesture synthesis called DeepGAN. Thereafter, we formulate DeepNAG by introducing a new differentiable loss function based on dynamic time warping and the average Hausdorff distance, which allows us to train DeepGAN's generator without requiring a discriminator. Through evaluations, we compare the utility of DeepGAN and DeepNAG against two alternative techniques for training five recognizers using data augmentation over six datasets. We further investigate the perceived quality of synthesized samples via an Amazon Mechanical Turk user study based on the HYPE benchmark. We find that DeepNAG outperforms DeepGAN in accuracy, training time (up to 17x faster), and realism, thereby opening the door to a new line of research in generator network design and training for gesture synthesis. Our source code is available at https://www.deepnag.com.