Memes are popular in the modern world and are distributed primarily for entertainment. However, harmful ideologies such as misogyny can be propagated through innocent-looking memes. The detection and understanding of why a meme is misogynistic is a research challenge due to its multimodal nature (image and text) and its nuanced manifestations across different societal contexts. We introduce a novel multimodal approach, namely, MM-Misogyny, to detect, categorize, and explain misogynistic content in memes. MM-Misogyny processes text and image modalities separately and unifies them into a multimodal context through a cross-attention mechanism. The resulting multimodal context is then easily processed for labeling, categorization, and explanation via a classifier and Large Language Model (LLM). The evaluation of the proposed model is performed on a newly curated dataset, What's Beneath Misogynous Stereotyping (WBMS), created by collecting misogynous memes from cyberspace and categorizing them into four categories, namely, Kitchen, Leadership, Working, and Shopping. The model not only detects and classifies misogyny, but also provides a granular understanding of how misogyny operates in domains of life. The results demonstrate the superiority of our approach compared to existing methods.

This work is being further extended in the direction of explainability by adding a neuro-symbolic reasoning module. The objective of this extension is to enhance the credibility of the classification decision and instill confidence in the architecture's ability to perform well on unseen data.