Human Gesture and Micro-gesture Analysis: Datasets, Methods, and Applications

Thesis event information

Date and time of the thesis defence

Place of the thesis defence

L5, Linnanmaa Campus

Topic of the dissertation

Human Gesture and Micro-gesture Analysis: Datasets, Methods, and Applications

Doctoral candidate

Master of Science Haoyu Chen

Faculty and unit

University of Oulu Graduate School, Faculty of Information Technology and Electrical Engineering, Center for Machine Vision and Signal Analysis

Subject of study

Computer Science

Opponent

Professor Joni-Kristian Kämäräinen, Tampere University

Custos

Academy professor Guoying Zhao, Center for Machine Vision and Signal Analysis

Add event to calendar

Use subtle body gestures to read your hidden emotions and generate them

Using machines to achieve robust recognition, generation, and even further interpretation of body gestures (e.g., understanding emotion with micro-gestures) is an appealing topic and drives all the research work in this dissertation.

To facilitate the research on this topic with computer vision methods, this dissertation tries to approach it via four stages: regular gesture recognition, micro-gesture dataset and analysis, gesture generation, and specific applications.

Results show that we can achieve robust gesture cognition, realistic gesture generation, and also emotion recognition with gestures.
Last updated: 4.3.2022