Abstract: FindingEmo - An Image Dataset for Emotion Recognition in the Wild

Laurent Mertens, Elahe Yargholi, Jan Van den Stock, Hans Op de Beeck, Joost Vennekens

Track: Type B (Encore Abstracts)

Keywords: Computer Vision, Dataset, Image Dataset, Emotion Recognition, Affective Computing, Social Cognition, Artificial Intelligence

Abstract: We present FindingEmo, a new image dataset containing annotations for 25,869 images, specifically tailored to Emotion Recognition. Contrary to existing datasets, it focuses on complex scenes depicting multiple people in various naturalistic, social settings, with images being annotated as a whole, thereby going beyond the traditional focus on faces or single individuals.

Serve As Reviewer: ~Laurent_Mertens1

Submission Number: 3