Adversarial Attention for Human Motion Synthesis
This addresses the challenge of high inter-subject variability and limited datasets in fields like healthcare, enabling better generalization for human motion analysis models.
The paper tackles the problem of generating synthetic human motion to address limited specialized datasets, presenting a method using adversarial attention that can synthesize motion over short- and long-time horizons and improve classification performance by supplementing real data with synthetic motions.
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.