Video Violence Rating: A Large-Scale Public Database and A Multimodal Rating Model

Recognizing violence in videos is significant for the automatic identification and assessment of violence content to restrict the access to violence for specific audiences such as children. Existing methods focus on violence detection, which is only able to recognize whether there exists violence or not. Differently, this paper handles the problem of video violence rating, which provides a more granular classification of violence levels. However, there is no publicly available database for video violence rating since it asks for fine-grained violence level annotations. Therefore, this paper introduces a large-scale violence rating database, which will be publicly released. Furthermore, we propose a multimodal violence rating model. Different from existing models, our model makes use of the token-based interaction and contrastive learning techniques. The token-based interaction is able to strengthen the feature representations and make full use of multimodal features. The contrastive learning can improve the performance of the model. To evaluate our model, a wide range of experiments are conducted, and experiment results show that our model outperforms existing methods.

I. Introduction

With the increasing prevalence of streaming service subscriptions (e.g. Netflix) and video sharing platforms (e.g. YouTube, TikTok), online media such as short videos and movies make people quickly consume all kinds of videos, including some with violence contents. Existing researches [1], [2], [3], [4] shows that there is a correlation between youth violence and the media they are exposed to, which means youth violence increases with more violence contents in media. Therefore, with the increase of works [5], [6], [7] in media access control, video violence rating is highly significant as it enables automatic identification and assessment of violence contents for specific audiences.