mlsanityData to 14 Oct 2026

MemeBLIP2: A novel lightweight multimodal system to detect harmful memes

arXiv 2504.21226 ↗First posted 29 Apr 2025cs.CV cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 10 of its 12 references that are in the map. First posted on arXiv 29 Apr 2025.

Builds on

10 of 12 references.

References · 10

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  5. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  6. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  7. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  8. 2020The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memescited by 490
  9. 2021MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targetscited by 86
  10. 2024MemeCLIP: Leveraging CLIP Representations for Multimodal Meme Classificationcited by 30

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 2.

8 papers.

  1. 2025From Points to Coalitions: Hierarchical Contrastive Shapley Values for Prioritizing Data Samplescited by 12
  2. 2025Cloud-Based AI Systems: Leveraging Large Language Models for Intelligent Fault Detection and Autonomous Self-Healingcited by 10
  3. 2025Does Bigger Mean Better? Comparitive Analysis of CNNs and Biomedical Vision Language Modles in Medical Diagnosiscited by 9
  4. 2025Rainbow Noise: Stress-Testing Multimodal Harmful-Meme Detectors on LGBTQ Contentcited by 6
  5. 2025Renaissance of RNNs in Streaming Clinical Time Series: Compact Recurrence Remains Competitive with Transformerscited by 5
  6. 2025Lightweight Baselines for Medical Abstract Classification: DistilBERT with Cross-Entropy as a Strong Defaultcited by 3
  7. 2026Physiologically Informed Deep Learning: A Multi-Scale Framework for Next-Generation PBPK Modelingcited by 0
  8. 2026Beyond Accuracy: A Qualitative Analysis of Vision-Language Models for Hate Speech Detection in Memescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025From Recognition to Reasoning: Advancing Multimodal Harmful Meme Detection via Chain-of-Thought Alignment
  2. 2023Mapping Memes to Words for Multimodal Hateful Meme Classification
  3. 2026GatedCLIP: Gated Multimodal Fusion for Hateful Memes Detection
  4. 2023Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models
  5. 2026Beyond a Joke: Multi-Angle Reasoning for Detecting and Explaining Harmful Humor in Memes
  6. 2025Demystifying Hateful Content: Leveraging Large Multimodal Models for Hateful Meme Detection with Explainable Decisions
  7. 2025Detecting and Understanding Hateful Contents in Memes Through Captioning and Visual Question-Answering
  8. 2025Detecting and Mitigating Hateful Content in Multimodal Memes with Vision-Language Models