Bourached, Anthony;
(2023)
Deep Generative Modelling of Human Behaviour.
Doctoral thesis (Ph.D), UCL (University College London).
Preview |
Text
PhD.pdf - Other Download (34MB) | Preview |
Abstract
Human action is naturally intelligible as a time-varying graph of connected joints constrained by locomotor anatomy and physiology. Its prediction allows the anticipation of actions with applications across healthcare, physical rehabilitation and training, robotics, navigation, manufacture, entertainment, and security. In this thesis we investigate deep generative approaches to the problem of understanding human action. We show that the learning of generative qualities of the distribution may render discriminative tasks more robust to distributional shift and real-world variations in data quality. We further build, from the bottom-up, a novel stochastically deep generative modelling model taylored to the problem of human motion and demonstrate many of it’s state-of-the-art properties such as anomaly detection, imputation in the face of incomplete examples, as well as synthesis—and conditional synthesis—of new samples on massive open source human motion datasets compared to multiple baselines derived from the most relevant pieces of literature.
| Type: | Thesis (Doctoral) |
|---|---|
| Qualification: | Ph.D |
| Title: | Deep Generative Modelling of Human Behaviour |
| Open access status: | An open access version is available from UCL Discovery |
| Language: | English |
| Additional information: | Copyright © The Author 2023. Original content in this thesis is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) Licence (https://creativecommons.org/licenses/by-nc/4.0/). Any third-party copyright material present remains the property of its respective owner(s) and is licensed under its existing terms. Access may initially be restricted at the author’s request. |
| UCL classification: | UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Population Health Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Population Health Sciences > Institute of Health Informatics UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10170723 |
Archive Staff Only
 |
View Item |
