Enhance Multimodal Transformer With External Label And In-Domain Pretrain: Hateful Meme Challenge Winning Solution
Not on the map. Why?
Abstract (arXiv)
Hateful meme detection is a new research area recently brought out that requires both visual, linguistic understanding of the meme and some background knowledge to performing well on the task. This technical report summarises the first place solution of the Hateful Meme Detection Challenge 2020, which extending state-of-the-art visual-linguistic transformers to tackle this problem. At the end of the report, we also point out the shortcomings and possible directions for improving the current methodology.
Key facts. Cited by 41 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Dec 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 6; 2022: 10; 2023: 16; 2024: 5; 2025: 4.
41 papers.
Sort:
By area:
- 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
- 2023Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Modelscited by 175
- 2021Detecting Harmful Memes and Their Targetscited by 78
- 2023Prompting for Multimodal Hateful Meme Classificationcited by 69
- 2022Detecting and Understanding Harmful Memes: A Surveycited by 58
- 2022Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Featurescited by 56
- 2023Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detectioncited by 47
- 2021Disentangling Hate in Online Memescited by 46
- 2021Detecting Harmful Content On Online Platforms: What Platforms Need Vs. Where Research Efforts Gocited by 33
- 2022On Explaining Multimodal Hateful Meme Detection Modelscited by 29
- 2022On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learningcited by 26
- 2024Towards Low-Resource Harmful Meme Detection with LMM Agentscited by 24
29 more
- 2023Mapping Memes to Words for Multimodal Hateful Meme Classificationcited by 20
- 2022Emotion Based Hate Speech Detection using Multimodal Learningcited by 18
- 2024Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Modelscited by 18
- 2023Model Sketching: Centering Concepts in Early-Stage Machine Learning Model Designcited by 15
- 2023Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Modelscited by 15
- 2024Modularized Networks for Few-shot Hateful Meme Detectioncited by 15
- 2025MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detectioncited by 15
- 2024Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicitiescited by 13
- 2023Detecting and Correcting Hate Speech in Multimodal Memes with Large Visual Language Modelcited by 12
- 2023Rethinking Multimodal Content Moderation from an Asymmetric Angle with Mixed-modalitycited by 9
- 2023MemeFier: Dual-stage Modality Fusion for Image Meme Classificationcited by 6
- 2023MemeGraphs: Linking Memes to Knowledge Graphscited by 6
- 2023PromptMTopic: Unsupervised Multimodal Topic Modeling of Memes using Large Language Modelscited by 5
- 2021An Interpretable Approach to Hateful Meme Detectioncited by 3
- 2021Towards A Multi-agent System for Online Hate Speech Detectioncited by 2
- 2023TOT: Topology-Aware Optimal Transport For Multimodal Hate Detectioncited by 2
- 2023ARC-NLP at Multimodal Hate Speech Event Detection 2023: Multimodal Methods Boosted by Ensemble Learning, Syntactical and Entity Featurescited by 2
- 2025Detecting and Mitigating Hateful Content in Multimodal Memes with Vision-Language Modelscited by 2
- 2022Feels Bad Man: Dissecting Automated Hateful Meme Detection Through the Lens of Facebook's Challengecited by 1
- 2022Multimodal Transformer for Parallel Concatenated Variational Autoencoderscited by 1
- 2022The Hateful Memes Challenge Next Movecited by 1
- 2023Meme Sentiment Analysis Enhanced with Multimodal Spatial Encoding and Facial Embeddingcited by 1
- 2023A Review of Vision-Language Models and their Performance on the Hateful Memes Challengecited by 1
- 2023Unimodal Intermediate Training for Multimodal Meme Sentiment Classificationcited by 1
- 2024Prompt-enhanced Network for Hateful Meme Classificationcited by 1
- 2021What is Multimodality?cited by 0
- 2022RubCSG at SemEval-2022 Task 5: Ensemble learning for identifying misogynous MEMEscited by 0
- 2025What's Pulling the Strings? Evaluating Integrity and Attribution in AI Training and Inference through Concept Shiftcited by 0
- 2025Unpacking Hateful Memes: Presupposed Context and False Claimscited by 0
- 2025Unpacking Hateful Memes: Presupposed Context and False Claims11 Oct 2025
- 2025MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection9 Jul 2025
- 2025Detecting and Mitigating Hateful Content in Multimodal Memes with Vision-Language Models30 Apr 2025
- 2025What's Pulling the Strings? Evaluating Integrity and Attribution in AI Training and Inference through Concept Shift28 Apr 2025
- 2024Prompt-enhanced Network for Hateful Meme Classification12 Nov 2024
- 2024Towards Low-Resource Harmful Meme Detection with LMM Agents8 Nov 2024
- 2024Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities11 Jun 2024
- 2024Modularized Networks for Few-shot Hateful Meme Detection19 Feb 2024
- 2024Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models24 Jan 2024
- 2023PromptMTopic: Unsupervised Multimodal Topic Modeling of Memes using Large Language Models11 Dec 2023
- 2023Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models9 Dec 2023
- 2023Detecting and Correcting Hate Speech in Multimodal Memes with Large Visual Language Model12 Nov 2023
29 more
- 2023Mapping Memes to Words for Multimodal Hateful Meme Classification12 Oct 2023
- 2023Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection16 Aug 2023
- 2023Unimodal Intermediate Training for Multimodal Meme Sentiment Classification1 Aug 2023
- 2023ARC-NLP at Multimodal Hate Speech Event Detection 2023: Multimodal Methods Boosted by Ensemble Learning, Syntactical and Entity Features25 Jul 2023
- 2023MemeGraphs: Linking Memes to Knowledge Graphs28 May 2023
- 2023Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models23 May 2023
- 2023Rethinking Multimodal Content Moderation from an Asymmetric Angle with Mixed-modality17 May 2023
- 2023A Review of Vision-Language Models and their Performance on the Hateful Memes Challenge9 May 2023
- 2023MemeFier: Dual-stage Modality Fusion for Image Meme Classification6 Apr 2023
- 2023Model Sketching: Centering Concepts in Early-Stage Machine Learning Model Design6 Mar 2023
- 2023Meme Sentiment Analysis Enhanced with Multimodal Spatial Encoding and Facial Embedding3 Mar 2023
- 2023TOT: Topology-Aware Optimal Transport For Multimodal Hate Detection27 Feb 2023
- 2023Prompting for Multimodal Hateful Meme Classification8 Feb 2023
- 2022The Hateful Memes Challenge Next Move13 Dec 2022
- 2022On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning13 Dec 2022
- 2022Multimodal Transformer for Parallel Concatenated Variational Autoencoders28 Oct 2022
- 2022Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features12 Oct 2022
- 2022Detecting and Understanding Harmful Memes: A Survey9 May 2022
- 2022Flamingo: a Visual Language Model for Few-Shot Learning29 Apr 2022
- 2022RubCSG at SemEval-2022 Task 5: Ensemble learning for identifying misogynous MEMEs8 Apr 2022
- 2022On Explaining Multimodal Hateful Meme Detection Models4 Apr 2022
- 2022Feels Bad Man: Dissecting Automated Hateful Meme Detection Through the Lens of Facebook's Challenge17 Feb 2022
- 2022Emotion Based Hate Speech Detection using Multimodal Learning13 Feb 2022
- 2021Detecting Harmful Memes and Their Targets24 Sep 2021
- 2021An Interpretable Approach to Hateful Meme Detection9 Aug 2021
- 2021Disentangling Hate in Online Memes9 Aug 2021
- 2021Towards A Multi-agent System for Online Hate Speech Detection3 May 2021
- 2021What is Multimodality?10 Mar 2021
- 2021Detecting Harmful Content On Online Platforms: What Platforms Need Vs. Where Research Efforts Go27 Feb 2021
- 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
- 2023Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detectioncited by 47
- 2023Detecting and Correcting Hate Speech in Multimodal Memes with Large Visual Language Modelcited by 12
- 2025Detecting and Mitigating Hateful Content in Multimodal Memes with Vision-Language Modelscited by 2
- 2023A Review of Vision-Language Models and their Performance on the Hateful Memes Challengecited by 1
- 2025Detecting and Mitigating Hateful Content in Multimodal Memes with Vision-Language Models30 Apr 2025
- 2023Detecting and Correcting Hate Speech in Multimodal Memes with Large Visual Language Model12 Nov 2023
- 2023Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection16 Aug 2023
- 2023A Review of Vision-Language Models and their Performance on the Hateful Memes Challenge9 May 2023
- 2022Flamingo: a Visual Language Model for Few-Shot Learning29 Apr 2022
- 2021Detecting Harmful Memes and Their Targetscited by 78
- 2023Prompting for Multimodal Hateful Meme Classificationcited by 69
- 2022Detecting and Understanding Harmful Memes: A Surveycited by 58
- 2022Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Featurescited by 56
- 2021Disentangling Hate in Online Memescited by 46
- 2021Detecting Harmful Content On Online Platforms: What Platforms Need Vs. Where Research Efforts Gocited by 33
- 2022On Explaining Multimodal Hateful Meme Detection Modelscited by 29
- 2022On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learningcited by 26
- 2024Towards Low-Resource Harmful Meme Detection with LMM Agentscited by 24
- 2023Mapping Memes to Words for Multimodal Hateful Meme Classificationcited by 20
- 2022Emotion Based Hate Speech Detection using Multimodal Learningcited by 18
- 2024Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Modelscited by 18
12 most cited of 31 All 31 (JSON)
- 2025Unpacking Hateful Memes: Presupposed Context and False Claims11 Oct 2025
- 2024Prompt-enhanced Network for Hateful Meme Classification12 Nov 2024
- 2024Towards Low-Resource Harmful Meme Detection with LMM Agents8 Nov 2024
- 2024Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities11 Jun 2024
- 2024Modularized Networks for Few-shot Hateful Meme Detection19 Feb 2024
- 2024Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models24 Jan 2024
- 2023PromptMTopic: Unsupervised Multimodal Topic Modeling of Memes using Large Language Models11 Dec 2023
- 2023Mapping Memes to Words for Multimodal Hateful Meme Classification12 Oct 2023
- 2023Unimodal Intermediate Training for Multimodal Meme Sentiment Classification1 Aug 2023
- 2023ARC-NLP at Multimodal Hate Speech Event Detection 2023: Multimodal Methods Boosted by Ensemble Learning, Syntactical and Entity Features25 Jul 2023
- 2023MemeGraphs: Linking Memes to Knowledge Graphs28 May 2023
- 2023Rethinking Multimodal Content Moderation from an Asymmetric Angle with Mixed-modality17 May 2023
12 newest of 31 All 31 (JSON)