Abstract
dc:descriptionIn this work, I will present our approach of using multi-modal data for recognizing human emotion and behavior in the wild. The study is divided into four tasks: group emotion recognition, driver gaze prediction, student engagement prediction, and emotion recognition using physiological signals. We explore multiple approaches including classical machine learning tools such as random forests, state-of-the-art deep neural networks, and multiple fusion and ensemble-based approaches. We also show that similar approaches can be used across tracks as many of the features generalize well to the different problems (e.g. facial features).
Degree
thesis:*- Name thesis:degree_name
- MS in Computer Science (M.S.C.S.)
- Level thesis:degree_level
- Thesis
- Discipline thesis:degree_discipline
- Computer Science and Engineering
- Grantor
- University of South Florida
- Year dc:date
- 2021
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Srivastava, Shivam
- Contributors dc:contributor
-
- Shaun Canavan, Ph.D.
- Dmitry B. Goldgof, Ph.D.
- Srinivas Katkoori, Ph.D.
Subjects
dc:subject × 4Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.usf.edu/etd/8873