HS-Coriander/

SA-VLM-HarmImages

This dataset is the dataset for Malicious Image Analysis via Vision-Language Segmentation Fusion: Detection, Element, and Location in One-shot.

The dataset contains various categories of harmful images, such as:

Violence Illegal Activities Extremism and Discrimination

Each image is provided with corresponding annotation files for segmentation and classification tasks.

Due to legal… See the full description on the dataset page: https://huggingface.co/datasets/HS-Coriander/SA-VLM-HarmImages.