hateclipper

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Meme ClassificationonHarm-P
Accuracy· 2022-10-12
87.6
best: 91.6 (RA-HMD (Qwen2-VL-7B))
SOTA
Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features arXiv:2210.05916
Meme ClassificationonHarm-P
F1· 2022-10-12
86.9
best: 91.1 (RA-HMD (Qwen2-VL-7B))
SOTA
Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features arXiv:2210.05916