Adversarial Attention for Human Motion Synthesis

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)

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

• Organisation

Project Code	Award No	Project Name	Principal Investigator	Funder's Name	Funder Ref	Lead Dept
315206		Privacy-Preserved Human Motion Analysis for Healthcare Applications	Fani Deligianni	Engineering and Physical Sciences Research Council (EPSRC)	EP/W01212X/1	Computing Science