# KP-RNN: A Deep Learning Pipeline for Human Motion Prediction and Synthesis of Performance Art

arXiv: https://arxiv.org/abs/2210.04366 · HTML: https://mlsanity.com/paper/2210.04366/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 9 Oct 2022.

## Builds on (most cited first, 8 of 8)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Everybody Dance Now](https://mlsanity.com/paper/1808.07371/) (2018)
- [Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction](https://mlsanity.com/paper/2204.11561/) (2022)
- [GlocalNet: Class-aware Long-term Human Motion Synthesis](https://mlsanity.com/paper/2012.10744/) (2020)
- [Application of Graph Convolutions in a Lightweight Model for Skeletal Human Motion Forecasting](https://mlsanity.com/paper/2110.04810/) (2021)
- [Smooth head tracking for virtual reality applications](https://mlsanity.com/paper/2110.14193/) (2021)
- [P4AI: Approaching AI Ethics through Principlism](https://mlsanity.com/paper/2111.14062/) (2021)

## Abstract (arXiv)

Digitally synthesizing human motion is an inherently complex process, which can create obstacles in application areas such as virtual reality. We offer a new approach for predicting human motion, KP-RNN, a neural network which can integrate easily with existing image processing and generation pipelines. We utilize a new human motion dataset of performance art, Take The Lead, as well as the motion generation pipeline, the Everybody Dance Now system, to demonstrate the effectiveness of KP-RNN's motion predictions. We have found that our neural network can predict human dance movements effectively, which serves as a baseline result for future works using the Take The Lead dataset. Since KP-RNN can work alongside a system such as Everybody Dance Now, we argue that our approach could inspire new methods for rendering human avatar animation. This work also serves to benefit the visualization of performance art in digital platforms by utilizing accessible neural networks.