SOTAVerified

Meme Classification

Meme classification refers to the task of classifying internet memes.

Papers

Showing 1–10 of 59 papers

TitleStatusHype
Detecting Harmful Memes with Decoupled Understanding and Guided CoT ReasoningCode0
LLM-based Semantic Augmentation for Harmful Content Detection—0
Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme DetectionCode1
Demystifying Hateful Content: Leveraging Large Multimodal Models for Hateful Meme Detection with Explainable Decisions—0
Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme ClassificationCode0
Prompt-enhanced Network for Hateful Meme ClassificationCode0
MemeCLIP: Leveraging CLIP Representations for Multimodal Meme ClassificationCode1
What Makes a Meme a Meme? Identifying Memes for Memetics-Aware Dataset Creation—0
IITK at SemEval-2024 Task 4: Hierarchical Embeddings for Detection of Persuasion Techniques in MemesCode0
MATK: The Meme Analytical Tool KitCode1
Show:102550
← PrevPage 1 of 6Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RA-HMD (Qwen2-VL-7B)ROC-AUC0.91—Unverified
2RA-HMD (LLaVA-1.5-7B)ROC-AUC0.9—Unverified
3PaLI-X-VPDROC-AUC0.89—Unverified
4RA-HMD (Qwen2-VL-2B)ROC-AUC0.88—Unverified
5RGCL (CLIP)ROC-AUC0.87—Unverified
6Flamingo (fine-tuned)ROC-AUC0.87—Unverified
7Hate-CLIPper - AlignROC-AUC0.86—Unverified
8ISSUESROC-AUC0.86—Unverified
9Ron ZhuROC-AUC0.85—Unverified
10HumanROC-AUC0.83—Unverified