Malek-Podjaski, M. and Deligianni, F. (2024) Adversarial Attention for Human Motion Synthesis. In: 2023 IEEE Symposium Series on Computational Intelligence (SSCI 2023), Mexico City, Mexico, 5-8 Dec 2023, pp. 69-74. (doi: 10.1109/SSCI52147.2023.10371870) (Early Online Publication)
Text
307484.pdf - Accepted Version Available under License Creative Commons Attribution. 859kB |
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. 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.
Item Type: | Conference Proceedings |
---|---|
Additional Information: | The authors would like to acknowledge funding from The Royal Society (RGS/R2/212199) and EPSRC (EP/W01212X/1). |
Status: | Early Online Publication |
Refereed: | Yes |
Glasgow Author(s) Enlighten ID: | Deligianni, Dr Fani |
Authors: | Malek-Podjaski, M., and Deligianni, F. |
College/School: | College of Science and Engineering > School of Computing Science |
Published Online: | 01 January 2024 |
Related URLs: |
University Staff: Request a correction | Enlighten Editors: Update this record