Introduced in MemeCLIP: Leveraging CLIP Representations for Multimodal Meme Classification2024
PrideMM comprising 5,063 text-embedded images associated with the LGBTQ+ Pride movement
This study introduces a novel dataset PrideMM comprising 5,063 text-embedded images associated with the LGBTQ+ Pride movement, thereby addressing a serious gap in existing resources and proposes a novel framework MemeCLIP for efficient downstream learning while preserving the knowledge of the pre-trained CLIP model.
