Improving Multimodal Hateful Meme Detection Exploiting LMM-Generated Knowledge
Open paper
Benchmark
Model
Rank
Results
hateful-meme-classification-on-pridemm
LMM-CLIP
#2
Accuracy: 76.31
hateful-meme-classification-on-harmeme
LMM-LongCLIP
#6
Accuracy: 87.23
Rank counts only results with a code link.