"Gross!": Personalized Video Content Moderation Using Generative Image Overlays for Aversive Videos

초록

As the number of videos available online continues to increase rapidly, effective content filtering technologies have become essential. However, existing approaches lack personalization and struggle to preserve contextual understanding of the video. In this study, we propose a personalized content filtering method capable of understanding contextual information within videos. To evaluate the effectiveness of our approach, we conducted a user study with 18 participants. The results demonstrated a improvement in discomfort reduction and contextual understanding.

키워드