Recognizing Emotions evoked by Movies using Multitask Learning

• Published in: International Conference on Affective Computing and Intelligent Interaction and workshops pp. 1 - 8
• Main Authors: Hayat, Hassan, Ventura, Carles, Lapedriza, Agata
• Format: Conference Proceeding
• Language: English
• Published: IEEE 28.09.2021
• Subjects: Affective computing; Annotations; Computational modeling; Computer architecture; Deep learning; Emotion recognition; Evoked emotion recognition; Motion pictures; Multi-modality; Multi-task Learning; Visualization

Understanding the emotional impact of movies has become important for affective movie analysis, ranking, and indexing. Methods for recognizing evoked emotions are usually trained on human annotated data. Concretely, viewers watch video clips and have to manually annotate the emotions they experience...