Detecting and Understanding Hateful Contents in Memes Through Captioning and Visual Question-Answering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Anaissi, Ali, Akram, Junaid, Chaturvedi, Kunal, Braytee, Ali
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909590084386816
author Anaissi, Ali
Akram, Junaid
Chaturvedi, Kunal
Braytee, Ali
author_facet Anaissi, Ali
Akram, Junaid
Chaturvedi, Kunal
Braytee, Ali
contents Memes are widely used for humor and cultural commentary, but they are increasingly exploited to spread hateful content. Due to their multimodal nature, hateful memes often evade traditional text-only or image-only detection systems, particularly when they employ subtle or coded references. To address these challenges, we propose a multimodal hate detection framework that integrates key components: OCR to extract embedded text, captioning to describe visual content neutrally, sub-label classification for granular categorization of hateful content, RAG for contextually relevant retrieval, and VQA for iterative analysis of symbolic and contextual cues. This enables the framework to uncover latent signals that simpler pipelines fail to detect. Experimental results on the Facebook Hateful Memes dataset reveal that the proposed framework exceeds the performance of unimodal and conventional multimodal models in both accuracy and AUC-ROC.
format Preprint
id arxiv_https___arxiv_org_abs_2504_16723
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Detecting and Understanding Hateful Contents in Memes Through Captioning and Visual Question-Answering
Anaissi, Ali
Akram, Junaid
Chaturvedi, Kunal
Braytee, Ali
Computer Vision and Pattern Recognition
Artificial Intelligence
Memes are widely used for humor and cultural commentary, but they are increasingly exploited to spread hateful content. Due to their multimodal nature, hateful memes often evade traditional text-only or image-only detection systems, particularly when they employ subtle or coded references. To address these challenges, we propose a multimodal hate detection framework that integrates key components: OCR to extract embedded text, captioning to describe visual content neutrally, sub-label classification for granular categorization of hateful content, RAG for contextually relevant retrieval, and VQA for iterative analysis of symbolic and contextual cues. This enables the framework to uncover latent signals that simpler pipelines fail to detect. Experimental results on the Facebook Hateful Memes dataset reveal that the proposed framework exceeds the performance of unimodal and conventional multimodal models in both accuracy and AUC-ROC.
title Detecting and Understanding Hateful Contents in Memes Through Captioning and Visual Question-Answering
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2504.16723