paper-with-me

홈 › Papers

MemeBLIP2: A novel lightweight multimodal system to detect harmful memes

2025-04-29 · Jiaqi Liu, Ran Tong, Aowei Shen, Shuzheng Li, Changlin Yang, Lisha Xu

Memes often merge visuals with brief text to share humor or opinions, yet some memes contain harmful messages such as hate speech. In this paper, we introduces MemeBLIP2, a light weight multimodal system that detects harmful memes by combining image and text features effectively. We build on previous studies by adding modules that align image and text representations into a shared space and fuse them for better classification. Using BLIP-2 as the core vision-language model, our system is evaluated on the PrideMM datasets. The results show that MemeBLIP2 can capture subtle cues in both modalities, even in cases with ironic or culturally specific content, thereby improving the detection of harmful material.

📄 PDF Abstract BibTeX arXiv:2504.21226

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Rainbow Noise: Stress-Testing Multimodal Harmful-Meme Detectors on LGBTQ Content

2025-07-24 · Ran Tong, Songtao Wei, Jiaqi Liu, Lanruo Wang arxiv

Hateful memes aimed at LGBTQ\,+ communities often evade detection by tweaking either the caption, the image, or both. We build the first robustness benchmark for this setting, pairing four realistic caption attacks with …

Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models

2023-12-09 · Hongzhan Lin, Ziyang Luo, Jing Ma, Long Chen

The age of social media is rife with memes. Understanding and detecting harmful memes pose a significant challenge due to their implicit meaning that is not explicitly conveyed through the surface text and image. However…

Multimodal Reasoning

Ultra Low-Cost Two-Stage Multimodal System for Non-Normative Behavior Detection

2024-03-24 · Albert Lu, Stephen Cranefield

The online community has increasingly been inundated by a toxic wave of harmful comments. In response to this growing challenge, we introduce a two-stage ultra-low-cost multimodal harmful behavior detection method design…

Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models

2024-01-24 · Hongzhan Lin, Ziyang Luo, Wei Gao, Jing Ma 외

The age of social media is flooded with Internet memes, necessitating a clear grasp and effective identification of harmful ones. This task presents a significant challenge due to the implicit meaning embedded in memes, …

Hateful Meme ClassificationLanguage ModellingSmall Language ModelText Generation

MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets

2021-09-11 · Findings (EMNLP) 2021 11 · Shraman Pramanick, Shivam Sharma, Dimitar Dimitrov, Md Shad Akhtar 외

Internet memes have become powerful means to transmit political, psychological, and socio-cultural ideas. Although memes are typically humorous, recent days have witnessed an escalation of harmful memes used for trolling…