Disturbing Image Detection Using LMM-Elicited Emotion Embeddings

Disturbing Image Detection (DID) refers to the task of detecting content in images that can cause trauma to the viewers. It may include images that depict violence, pornography, animal cruelty, disasters. Such content elicits anxiety or/and fear to viewers, while it is noted that viewers who are systematically exposed to such content are at risk of experiencing severe psychological distress.