VEATIC: Video-based Emotion and Affect Tracking in Context Dataset

TL;DR

VEATIC is a comprehensive video dataset with continuous affect annotations from diverse sources, enabling better understanding and modeling of human emotions in context, surpassing limitations of facial-expression-only datasets.

Contribution

The paper introduces VEATIC, a large, context-rich video dataset with real-time affect annotations, and proposes a new computer vision task and benchmark for affect recognition.

Findings

Pretrained models on VEATIC outperform those on previous datasets.

VEATIC demonstrates improved generalizability in affect recognition tasks.

The dataset enables modeling of affect using both context and character information.

Abstract

Human affect recognition has been a significant topic in psychophysics and computer vision. However, the currently published datasets have many limitations. For example, most datasets contain frames that contain only information about facial expressions. Due to the limitations of previous datasets, it is very hard to either understand the mechanisms for affect recognition of humans or generalize well on common cases for computer vision models trained on those datasets. In this work, we introduce a brand new large dataset, the Video-based Emotion and Affect Tracking in Context Dataset (VEATIC), that can conquer the limitations of the previous datasets. VEATIC has 124 video clips from Hollywood movies, documentaries, and home videos with continuous valence and arousal ratings of each frame via real-time annotation. Along with the dataset, we propose a new computer vision task to infer the affect of the selected character via both context and character information in each video frame. Additionally, we propose a simple model to benchmark this new computer vision task. We also compare the performance of the pretrained model using our dataset with other similar datasets. Experiments show the competing results of our pretrained model via VEATIC, indicating the generalizability of VEATIC. Our dataset is available at https://veatic.github.io.