TrustAIRLab/Hateful_Memes_in_VLM download history

TrustAIRLab/Hateful_Memes_in_VLM is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 25 times (4 in the last 7 days), and 620 times in total. It ranks #316,899 among datasets by monthly downloads.

This dataset contains the response of VLMs (InstructBlip, ShareGPT4V, LLaVA and CogVLM) to hateful memes and the annotation to these responses. For more information, please refer to paper "From Meme to Threat: On the Hateful Meme Understanding and Induced Hateful Content Generation in Open-Source Vi

Open TrustAIRLab/Hateful_Memes_in_VLM on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.