# Learning Deep and Compact Models for Gesture Recognition

arXiv: https://arxiv.org/abs/1712.10136 · HTML: https://mlsanity.com/paper/1712.10136/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Dec 2017.

## Built on by (most cited first, 2 of 2)

- [How do Foundation Models Compare to Skeleton-Based Approaches for Gesture Recognition in Human-Robot Interaction?](https://mlsanity.com/paper/2506.20795/) (2025)
- [GesSure- A Robust Face-Authentication enabled Dynamic Gesture Recognition GUI Application](https://mlsanity.com/paper/2207.11033/) (2022)

## Abstract (arXiv)

We look at the problem of developing a compact and accurate model for gesture recognition from videos in a deep-learning framework. Towards this we propose a joint 3DCNN-LSTM model that is end-to-end trainable and is shown to be better suited to capture the dynamic information in actions. The solution achieves close to state-of-the-art accuracy on the ChaLearn dataset, with only half the model size. We also explore ways to derive a much more compact representation in a knowledge distillation framework followed by model compression. The final model is less than 1~MB in size, which is less than one hundredth of our initial model, with a drop of 7% in accuracy, and is suitable for real-time gesture recognition on mobile devices.