Bourached, A;
Griffiths, R-R;
Gray, R;
Jha, A;
Nachev, P;
(2022)
Generative Model-Enhanced Human Motion Prediction.
Applied AI Letters
, 3
(2)
, Article e63. 10.1002/ail2.63.
Preview |
Text
Nachev_Generative model-enhanced human motion prediction.pdf Download (4MB) | Preview |
Abstract
The task of predicting human motion is complicated by the natural heterogeneity and compositionality of actions, necessitating robustness to distributional shifts as far as out-of-distribution (OoD). Here, we formulate a new OoD benchmark based on the Human3.6M and Carnegie Mellon University (CMU) motion capture datasets, and introduce a hybrid framework for hardening discriminative architectures to OoD failure by augmenting them with a generative model. When applied to current state-of-the-art discriminative models, we show that the proposed approach improves OoD robustness without sacrificing in-distribution performance, and can theoretically facilitate model interpretability. We suggest human motion predictors ought to be constructed with OoD challenges in mind, and provide an extensible general framework for hardening diverse discriminative architectures to extreme distributional shift. The code is available at: https://github.com/bouracha/OoDMotion.
| Type: | Article |
|---|---|
| Title: | Generative Model-Enhanced Human Motion Prediction |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1002/ail2.63 |
| Publisher version: | https://doi.org/10.1002/ail2.63 |
| Language: | English |
| Additional information: | © 2022 The Authors. Applied AI Letters published by John Wiley & Sons Ltd. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. |
| Keywords: | deep learning; generative models; human motion prediction; variational autoencoders |
| UCL classification: | UCL 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 Brain Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences > UCL Queen Square Institute of Neurology UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences > UCL Queen Square Institute of Neurology > Brain Repair and Rehabilitation |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10114109 |
Archive Staff Only
 |
View Item |
