mlsanityData to 7 Oct 2026

Disentangling Hate in Online Memes

arXiv 2108.06207 ↗First posted 9 Aug 2021cs.IR cs.CL cs.MMcited by 46

Not on the map. Why?

Abstract (arXiv)

Hateful and offensive content detection has been extensively explored in a single modality such as text. However, such toxic information could also be communicated via multimodal content such as online memes. Therefore, detecting multimodal hateful content has recently garnered much attention in academic and industry research communities. This paper aims to contribute to this emerging research topic by proposing DisMultiHate, which is a novel framework that performed the classification of multimodal hateful content. Specifically, DisMultiHate is designed to disentangle target entities in multimodal memes to improve hateful content classification and explainability. We conduct extensive experiments on two publicly available hateful and offensive memes datasets. Our experiment results show that DisMultiHate is able to outperform state-of-the-art unimodal and multimodal baselines in the hateful meme classification task. Empirical case studies were also conducted to demonstrate DisMultiHate's ability to disentangle target entities in memes and ultimately showcase DisMultiHate's explainability of the multimodal hateful content classification task.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). Builds on 38 of its 60 references that are in the map. First posted on arXiv 9 Aug 2021.

Builds on

38 of 60 references.

References · 38

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  7. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  8. 2017Decoupled Weight Decay Regularizationcited by 1,722
  9. 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,291
  10. 2019VL-BERT: Pre-training of Generic Visual-Linguistic Representationscited by 954
  11. 2017Automated Hate Speech Detection and the Problem of Offensive Languagecited by 724
  12. 2020The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memescited by 485
26 more
  1. 2018Understanding disentangling in β-VAEcited by 332
  2. 2020Large-Scale Adversarial Training for Vision-and-Language Representation Learningcited by 327
  3. 2020ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graphcited by 211
  4. 2017Deep Learning for Hate Speech Detection in Tweetscited by 180
  5. 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
  6. 2019Learning Disentangled Representations for Recommendationcited by 110
  7. 2019Exploring Hate Speech Detection in Multimodal Publicationscited by 103
  8. 2017Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observationscited by 100
  9. 2019FairFace: Face Attribute Dataset for Balanced Race, Gender, and Agecited by 87
  10. 2018Learning Disentangled Joint Continuous and Discrete Representationscited by 83
  11. 2018All You Need is "Love": Evading Hate-speech Detectioncited by 56
  12. 2019Learning Disentangled Representations via Mutual Information Estimationcited by 52
  13. 2020Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challengecited by 51
  14. 2020Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memescited by 50
  15. 2020A Multimodal Framework for the Detection of Hateful Memescited by 48
  16. 2017One-step and Two-step Classification for Abusive Language Detection on Twittercited by 46
  17. 2020Enhance Multimodal Transformer With External Label And In-Domain Pretrain: Hateful Meme Challenge Winning Solutioncited by 41
  18. 2020Detecting Hate Speech in Multi-modal Memescited by 38
  19. 2020Detecting Hateful Memes Using a Multimodal Deep Ensemblecited by 30
  20. 2017Mean Birds: Detecting Aggression and Bullying on Twittercited by 29
  21. 2020Multimodal Learning for Hateful Memes Detectioncited by 29
  22. 2021DeepHate: Hate Speech Detection via Multi-Faceted Text Representationscited by 29
  23. 2015Learning to Linearize Under Uncertaintycited by 25
  24. 2015Bayesian representation learning with oracle constraintscited by 16
  25. 2020Classification of Multimodal Hate Speech -- The Winning Solution of Hateful Memes Challengecited by 7
  26. 2020Hateful Memes Detection via Complementary Visual and Linguistic Networkscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 13; 2024: 15; 2025: 9; 2026: 6.

46 papers.

Sort:

By area:

  1. 2023Prompting for Multimodal Hateful Meme Classificationcited by 68
  2. 2022Detecting and Understanding Harmful Memes: A Surveycited by 58
  3. 2023Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detectioncited by 45
  4. 2023Decoding the Underlying Meaning of Multimodal Hateful Memescited by 38
  5. 2022On Explaining Multimodal Hateful Meme Detection Modelscited by 29
  6. 2024Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Modelscited by 26
  7. 2024Towards Low-Resource Harmful Meme Detection with LMM Agentscited by 23
  8. 2023Mapping Memes to Words for Multimodal Hateful Meme Classificationcited by 19
  9. 2023BanglaAbuseMeme: A Dataset for Bengali Abusive Meme Classificationcited by 18
  10. 2024Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Modelscited by 17
  11. 2024Modularized Networks for Few-shot Hateful Meme Detectioncited by 15
  12. 2025MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detectioncited by 14
34 more
  1. 2024Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicitiescited by 13
  2. 2025Demystifying Hateful Content: Leveraging Large Multimodal Models for Hateful Meme Detection with Explainable Decisionscited by 13
  3. 2023TotalDefMeme: A Multi-Attribute Meme dataset on Total Defence in Singaporecited by 12
  4. 2023Rethinking Multimodal Content Moderation from an Asymmetric Angle with Mixed-modalitycited by 9
  5. 2024MemeCraft: Contextual and Stance-Driven Multimodal Meme Generationcited by 9
  6. 2022Predicting Hate Intensity of Twitter Conversation Threadscited by 7
  7. 2024Deciphering Hate: Identifying Hateful Memes and Their Targetscited by 7
  8. 2024Hate Speech Detection with Generalizable Target-aware Fairnesscited by 7
  9. 2024Bridging Modalities: Enhancing Cross-Modality Hate Speech Detection with Few-Shot In-Context Learningcited by 7
  10. 2023MemeFier: Dual-stage Modality Fusion for Image Meme Classificationcited by 6
  11. 2023MemeGraphs: Linking Memes to Knowledge Graphscited by 6
  12. 2023PromptMTopic: Unsupervised Multimodal Topic Modeling of Memes using Large Language Modelscited by 5
  13. 2024LionGuard: Building a Contextualized Moderation Classifier to Tackle Localized Unsafe Contentcited by 5
  14. 2025Humor in Pixels: Benchmarking Large Multimodal Models Understanding of Online Comicscited by 5
  15. 2024Align before Attend: Aligning Visual and Textual Features for Multimodal Hateful Content Detectioncited by 4
  16. 2025Combatting Dimensional Collapse in LLM Pre-Training Data via Diversified File Selectioncited by 4
  17. 2025A Multimodal-Multitask Framework with Cross-modal Relation and Hierarchical Interactive Attention for Semantic Comprehensioncited by 4
  18. 2023TOT: Topology-Aware Optimal Transport For Multimodal Hate Detectioncited by 2
  19. 2023Causal Intersectionality and Dual Form of Gradient Descent for Multimodal Analysis: a Case Study on Hateful Memescited by 2
  20. 2024MHS-STMA: Multimodal Hate Speech Detection via Scalable Transformer-Based Multilevel Attention Frameworkcited by 2
  21. 2025Improving Multimodal Hateful Meme Detection Exploiting LMM-Generated Knowledgecited by 2
  22. 2024Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglementcited by 1
  23. 2024COT: A Generative Approach for Hate Speech Counter-Narratives via Contrastive Optimal Transportcited by 1
  24. 2024Prompt-enhanced Network for Hateful Meme Classificationcited by 1
  25. 2025From Shallow Humor to Metaphor: Towards Label-Free Harmful Meme Detection via LMM Agent Self-Improvementcited by 1
  26. 2026All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproductioncited by 1
  27. 2023MATK: The Meme Analytical Tool Kitcited by 0
  28. 2025Detecting Offensive Memes with Social Biases in Singapore Context Using Multimodal Large Language Modelscited by 0
  29. 2025Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrievalcited by 0
  30. 2026HateXScore: A Metric Suite for Evaluating Reasoning Quality in Hate Speech Explanationscited by 0
  31. 2026MuPHI: Learning Implicit Multimodal Harm Reasoning via Semantically Grounded Reward Optimizationcited by 0
  32. 2026I Know What You Meme, Even If it Emerged Today: Understanding Evolving Memes through Open-World Knowledge Acquisitioncited by 0
  33. 2026HCIG: A Hierarchical Cross-Modal Incongruity Graph Network for Multimodal Sarcasm and Cyberbullying Detectioncited by 0
  34. 2026Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challengescited by 0