Please use this identifier to cite or link to this item:
http://artemis.cslab.ece.ntua.gr:8080/jspui/handle/123456789/18000
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Παρέλλη, Μαρία | - |
dc.date.accessioned | 2021-07-13T17:44:46Z | - |
dc.date.available | 2021-07-13T17:44:46Z | - |
dc.date.issued | 2021-06-24 | - |
dc.identifier.uri | http://artemis.cslab.ece.ntua.gr:8080/jspui/handle/123456789/18000 | - |
dc.description.abstract | Sign Language constitutes the primary means of communication for the deaf and hard-of-hearing. Sign Language Recognition is a complex task, which lies at the intersection of computer vision and language modeling. Manual and non-manual cues such as expression, hand shape, and body orientation occur in parallel and play a meaningful role in the articulation of the sign. In this thesis, we study this problem extensively by leveraging recent deep learning approaches. In the first section, we focus on 3D Hand and Body Pose estimation and report quantitative and qualitative results. In the second section, we explore the task of continuous sign language recognition and how expressive 3D skeleton and parameterizations of the human body can be exploited in conjunction with graph convolutions in order to effectively solve our task. We also compare our results with successful architectures, such as transformers and LSTM attention encoder-decoders. We report competitive performance on the Phoenix 2014-T dataset. | en_US |
dc.language | en | en_US |
dc.subject | Sign Language | en_US |
dc.subject | Graphs | en_US |
dc.subject | 3D Pose | en_US |
dc.subject | ST-GCN | en_US |
dc.subject | 3D Mesh | en_US |
dc.subject | CNN | en_US |
dc.title | Deep Learning Based Sign Language Recognition | en_US |
dc.description.pages | 126 | en_US |
dc.contributor.supervisor | Μαραγκός Πέτρος | en_US |
dc.department | Τομέας Σημάτων, Ελέγχου και Ρομποτικής | en_US |
Appears in Collections: | Διπλωματικές Εργασίες - Theses |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Thesis_parelli.pdf | 9.32 MB | Adobe PDF | View/Open |
Items in Artemis are protected by copyright, with all rights reserved, unless otherwise indicated.