CS Other Presentations

Department of Computer Science - University of Cyprus

Besides Colloquiums, the Department of Computer Science at the University of Cyprus also holds Other Presentations (Research Seminars, PhD Defenses, Short Term Courses, Demonstrations, etc.). These presentations are given by scientists who aim to present preliminary results of their research work and/or other technical material. Other Presentations serve as a forum for educating Computer Science students and related announcements are disseminated to the Department of Computer Science (i.e., the csall list):
rss RSS Directions Directions

Presentations Coordinator: Demetris Zeinalipour

PhD Defense: Automatic Emotion Recognition from Body Movements, Mr. Haris Zacharatos (University of Cyprus, Cyprus), Friday, August 27, 2021, 10:00-11:00 EET.


The Department of Computer Science at the University of Cyprus cordially invites you to the PhD Defense entitled:

Automatic Emotion Recognition from Body Movements

Speaker: Mr. Haris Zacharatos
Affiliation: University of Cyprus, Cyprus
Category: PhD Defense
Location: Zoom (with Registration), https://ucy.zoom.us/meeting/register/tJYlduGurzgtGdU18HaJFEkL-LZ9pK0Qj-cK (directions)
Date: Friday, August 27, 2021
Time: 10:00-11:00 EET
Host: Prof. Constantinos Pattichis (pattichi-AT-cs.ucy.ac.cy)
URL: https://www.cs.ucy.ac.cy/colloquium/presentations.php?speaker=cs.ucy.pres.2021.zacharatos

Abstract:
Humans are emotional beings and their feelings influence the way they perform and interact with computers. Emotion recognition is important in a variety of applications such as intelligent tutoring systems, computer games, robotics, medical and human computer interaction. The most expressive modalities for humans is body posture and movement and it has lately started to receive attention from researchers in the use for emotion recognition. Despite these advances there is a significant gap in low recognition rates on emotion derived from body modality. This thesis is addressing some of this shortcomings in emotion recognition and it proposing various methods towards an automatic emotion recognition system. A first method is proposed using body postures to detect emotions in a game environment with no temporal information available which resulted to satisfactory levels of recognition. Then a second method is proposed adding temporal information with high level notational systems inspired by several temporal techniques and the theory of Laban, we have created a model that achieved an 89% recognition rates, showing that temporal information along with high level notation systems can increase the results. A third method of automatic segmentation of body movements is presented, proposing symmetry for automatic segmentation, which can be used as an input for fully automated systems of recognising emotions. Finally a method to classify emotions using deep CNN models on the 3D raw data is presented resulting to a high recognition rates of 81% for binary classification that shows a very promising path for future research.

Short Bio:
Haris Zacharatos is a Ph.D. candidate at the Compute Science Department under the supervision of Dr Yiorgos Chrysanthou. He has received his M.Sc and B.Sc degrees in Computer Science from the University of Cyprus. His research interests include affective computing and artificial emotional intelligence, VR/XR/AR systems using wearable devices and robotics. He is a member of the Association for the Advancement of Affective Computing (AAAC).

  Other Presentations Web: https://www.cs.ucy.ac.cy/colloquium/presentations.php
  Colloquia Web: https://www.cs.ucy.ac.cy/colloquium/
  Calendar: https://www.cs.ucy.ac.cy/colloquium/schedule/cs.ucy.pres.2021.zacharatos.ics