Adversarial Attention for Human Motion Synthesis

TL;DR

This paper introduces an adversarial attention-based deep learning method for controllable human motion synthesis, enabling generation of realistic motions and improving classification with synthetic data, addressing data scarcity and variability issues.

Contribution

The paper proposes a novel adversarial attention mechanism for human motion synthesis that enhances controllability and data augmentation capabilities in deep learning models.

Findings

Generated realistic human motions over various time horizons.

Improved classification performance with synthetic motion data.

Demonstrated effectiveness of adversarial attention in motion synthesis.

Abstract

Analysing human motions is a core topic of interest for many disciplines, from Human-Computer Interaction, to entertainment, Virtual Reality and healthcare. Deep learning has achieved impressive results in capturing human pose in real-time. On the other hand, due to high inter-subject variability, human motion analysis models often suffer from not being able to generalise to data from unseen subjects due to very limited specialised datasets available in fields such as healthcare. However, acquiring human motion datasets is highly time-consuming, challenging, and expensive. Hence, human motion synthesis is a crucial research problem within deep learning and computer vision. We present a novel method for controllable human motion synthesis by applying attention-based probabilistic deep adversarial models with end-to-end training. We show that we can generate synthetic human motion over both short- and long-time horizons through the use of adversarial attention. Furthermore, we show that we can improve the classification performance of deep learning models in cases where there is inadequate real data, by supplementing existing datasets with synthetic motions.