Recognizing Emotions evoked by Movies using Multitask Learning

TL;DR

This paper introduces a multi-task learning approach to recognize emotions evoked by movies, modeling individual viewer emotions alongside aggregated annotations, leading to improved accuracy over existing methods.

Contribution

The paper proposes a novel multi-task deep learning architecture that jointly models individual and aggregated viewer emotions, outperforming traditional single-task models and state-of-the-art benchmarks.

Findings

Multi-task approach more accurately models individual and aggregated emotions.

Outperforms state-of-the-art on COGNIMUSE benchmark.

Demonstrates the effectiveness of joint modeling for affective movie analysis.

Abstract

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 experienced while watching the videos. Then, the common practice is to aggregate the different annotations, by computing average scores or majority voting, and train and test models on these aggregated annotations. With this procedure a single aggregated evoked emotion annotation is obtained per each video. However, emotions experienced while watching a video are subjective: different individuals might experience different emotions. In this paper, we model the emotions evoked by videos in a different manner: instead of modeling the aggregated value we jointly model the emotions experienced by each viewer and the aggregated value using a multi-task learning approach. Concretely, we propose two deep learning architectures: a Single-Task (ST) architecture and a Multi-Task (MT) architecture. Our results show that the MT approach can more accurately model each viewer and the aggregated annotation when compared to methods that are directly trained on the aggregated annotations. Furthermore, our approach outperforms the current state-of-the-art results on the COGNIMUSE benchmark.