Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark

TL;DR

This paper introduces the novel task of Pairwise Emotional Relationship Recognition in videos, presents a large multi-modal dataset called ERATO, and proposes a baseline model with a specialized attention mechanism to advance multi-modal video understanding.

Contribution

The paper defines a new PERR task, creates ERATO, a large-scale multi-modal dataset, and develops the SMTA baseline model to improve multi-modal fusion in emotional relationship recognition.

Findings

ERATO contains 31,182 clips and 203 hours of video data.

SMTA improves multi-modal fusion performance by about 1%.

The dataset and model facilitate research in multi-modal emotion and relationship recognition.

Abstract

Recognizing the emotional state of people is a basic but challenging task in video understanding. In this paper, we propose a new task in this field, named Pairwise Emotional Relationship Recognition (PERR). This task aims to recognize the emotional relationship between the two interactive characters in a given video clip. It is different from the traditional emotion and social relation recognition task. Varieties of information, consisting of character appearance, behaviors, facial emotions, dialogues, background music as well as subtitles contribute differently to the final results, which makes the task more challenging but meaningful in developing more advanced multi-modal models. To facilitate the task, we develop a new dataset called Emotional RelAtionship of inTeractiOn (ERATO) based on dramas and movies. ERATO is a large-scale multi-modal dataset for PERR task, which has 31,182 video clips, lasting about 203 video hours. Different from the existing datasets, ERATO contains interaction-centric videos with multi-shots, varied video length, and multiple modalities including visual, audio and text. As a minor contribution, we propose a baseline model composed of Synchronous Modal-Temporal Attention (SMTA) unit to fuse the multi-modal information for the PERR task. In contrast to other prevailing attention mechanisms, our proposed SMTA can steadily improve the performance by about 1\%. We expect the ERATO as well as our proposed SMTA to open up a new way for PERR task in video understanding and further improve the research of multi-modal fusion methodology.