DSpace Repository

Action Recognition in Generalized Zero-Shot Learning Setting Using the Conditional Generative Adversarial Network

Show simple item record

dc.contributor.advisor Dailey, Matthew
dc.contributor.author Tirumalasetty, Gayatri
dc.contributor.other Phan Minh, Dung
dc.contributor.other Anutariya, Chutiporn
dc.date.accessioned 2020-01-17T06:38:10Z
dc.date.available 2020-01-17T06:38:10Z
dc.date.issued 2020-01-17
dc.identifier.other AIT
dc.identifier.uri http://www.cs.ait.ac.th/xmlui/handle/123456789/962
dc.description 37 p. en_US
dc.description.abstract Human action recognition is an interesting area of research that has found applications in security surveillance systems, robotics, human-computer interaction and so on. Human actions can be classified into usual (mundane) events and unusual (peculiar) events. The traditional supervised learning models that discriminate between classes are helpful in classifying mundane actions of which the data is available during training. But in case of unusual events, we do not generally possess the example data during training. This now becomes a problem of zero-shot learning. In this study, I explore generative models to produce instances of peculiar action events with the help of semantic meaning related to the action classes. The data from different places at AIT has been combined with benchmark UCF101 dataset to carry out the experiment. I have achieved an accuracy of 96.7\% on the usual event classification and 60.94\% on unusual event classification tasks during test time. en_US
dc.description.sponsorship AIT Fellowship en_US
dc.language.iso en_US en_US
dc.publisher AIT en_US
dc.subject Action recognition en_US
dc.subject Generative adversarial networks en_US
dc.subject Conditional GAN en_US
dc.subject Zero-shot learnig en_US
dc.subject Generalized zero-shot learning en_US
dc.subject Computer vision en_US
dc.subject Deep learning en_US
dc.title Action Recognition in Generalized Zero-Shot Learning Setting Using the Conditional Generative Adversarial Network en_US
dc.type Research report en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account