| dc.rights.license | CC-BY-NC-ND | |
| dc.contributor.advisor | Önal Ertugrul, I. | |
| dc.contributor.author | Chen, Sylvia | |
| dc.date.accessioned | 2023-08-10T00:01:49Z | |
| dc.date.available | 2023-08-10T00:01:49Z | |
| dc.date.issued | 2023 | |
| dc.identifier.uri | https://studenttheses.uu.nl/handle/20.500.12932/44557 | |
| dc.description.abstract | Automatic Pain Assessment (APA) through facial expressions meets the challenge of limited pain expression data and imbalanced pain levels. Traditional data augmentation schemes do not contribute additional semantic information about the infrequent label. In this paper, we propose a novel data augmentation scheme using Generative Adversarial Networks (GANs). | |
| dc.description.sponsorship | Utrecht University | |
| dc.language.iso | EN | |
| dc.subject | AU-based Painful Dataset Augmentation Using GAN Network | |
| dc.title | Realistic Painful Expression Synthesis Using Generative Models | |
| dc.type.content | Master Thesis | |
| dc.rights.accessrights | Open Access | |
| dc.subject.keywords | Pain Expression; Data Augmentation; GAN; Action Units | |
| dc.subject.courseuu | Game and Media Technology | |
| dc.thesis.id | 21489 | |
