# Few-shot human motion prediction for heterogeneous sensors

arXiv: https://arxiv.org/abs/2212.11771 · HTML: https://mlsanity.com/paper/2212.11771/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 27 references that are in the map.
- First posted on arXiv 22 Dec 2022.

## Builds on (most cited first, 16 of 16)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [On human motion prediction using recurrent neural networks](https://mlsanity.com/paper/1705.02445/) (2017)
- [History Repeats Itself: Human Motion Prediction via Motion Attention](https://mlsanity.com/paper/2007.11755/) (2020)
- [Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction](https://mlsanity.com/paper/2003.08802/) (2020)
- [Deep representation learning for human motion prediction and classification](https://mlsanity.com/paper/1702.07486/) (2017)
- [TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning](https://mlsanity.com/paper/1905.06549/) (2019)
- [The Kolmogorov-Arnold representation theorem revisited](https://mlsanity.com/paper/2007.15884/) (2020)
- [Multi-level Motion Attention for Human Motion Prediction](https://mlsanity.com/paper/2106.09300/) (2021)
- [An Intelligent Non-Invasive Real Time Human Activity Recognition System for Next-Generation Healthcare](https://mlsanity.com/paper/2008.02567/) (2020)
- [Few-Shot Forecasting of Time-Series with Heterogeneous Channels](https://mlsanity.com/paper/2204.03456/) (2022)
- [Chameleon: Learning Model Initializations Across Tasks With Different Schemas](https://mlsanity.com/paper/1909.13576/) (2019)
- [HIDRA: Head Initialization across Dynamic targets for Robust Architectures](https://mlsanity.com/paper/1910.12749/) (2019)

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

- [Off-the-shelf ChatGPT is a Good Few-shot Human Motion Predictor](https://mlsanity.com/paper/2405.15267/) (2024)
- [Personalized Pose Forecasting](https://mlsanity.com/paper/2312.03528/) (2023)

## Abstract (arXiv)

Human motion prediction is a complex task as it involves forecasting variables over time on a graph of connected sensors. This is especially true in the case of few-shot learning, where we strive to forecast motion sequences for previously unseen actions based on only a few examples. Despite this, almost all related approaches for few-shot motion prediction do not incorporate the underlying graph, while it is a common component in classical motion prediction. Furthermore, state-of-the-art methods for few-shot motion prediction are restricted to motion tasks with a fixed output space meaning these tasks are all limited to the same sensor graph. In this work, we propose to extend recent works on few-shot time-series forecasting with heterogeneous attributes with graph neural networks to introduce the first few-shot motion approach that explicitly incorporates the spatial graph while also generalizing across motion tasks with heterogeneous sensors. In our experiments on motion tasks with heterogeneous sensors, we demonstrate significant performance improvements with lifts from 10.4% up to 39.3% compared to best state-of-the-art models. Moreover, we show that our model can perform on par with the best approach so far when evaluating on tasks with a fixed output space while maintaining two magnitudes fewer parameters.