The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

Open paper
Benchmark Model Rank Results
meme-classification-on-hateful-memesHuman#9ROC-AUC: 0.8265Accuracy: 0.847
meme-classification-on-hateful-memesVisual BERT COCO#15ROC-AUC: 0.754Accuracy: 0.695

Rank counts only results with a code link.