Meme Classification

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

6 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 30 papers with code (59 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Learning Transferable Visual Models From Natural Language Supervision
  26 Feb 2021 82 repositories listed Syntology ran 16 of 20 samples · 4 unverified · 16 pointer-only (licence)
  State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories.
• Flamingo: a Visual Language Model for Few-Shot Learning
  29 Apr 2022 5 repositories listed Syntology ran 18 of 24 samples · 6 unverified · 7 pointer-only (licence)
  Building models that can be rapidly adapted to novel tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research.
• The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes
  10 May 2020 4 repositories listed Syntology ran 0 of 4 samples · 4 unverified
  This work proposes a new challenge set for multimodal classification, focusing on detecting hate speech in multimodal memes.
• Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection
  16 Aug 2023 2 repositories listed Syntology ran 1 of 4 samples · 3 unverified · 4 pointer-only (licence)
  Specifically, we prompt a frozen PVLM by asking hateful content-related questions and use the answers as image captions (which we call Pro-Cap), so that the captions contain information critical for hateful content…
• Detecting Harmful Memes with Decoupled Understanding and Guided CoT Reasoning
  10 Jun 2025 1 repository listed Syntology ran 1 of 5 samples · 4 unverified
  Building on these textual descriptions, we further incorporate targeted, interpretable human-crafted guidelines to guide models' reasoning under zero-shot CoT prompting.
• Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection
  18 Feb 2025 1 repository listed Syntology ran 2 of 4 samples · 2 unverified
  Hateful memes have become a significant concern on the Internet, necessitating robust automated detection systems.
• Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification
  25 Jan 2025 1 repository listed
  Next, we propose a commonsense and domain-enriched framework, M3H, to enhance MLMs' ability to interpret figurative language and commonsense knowledge.
• Prompt-enhanced Network for Hateful Meme Classification
  12 Nov 2024 1 repository listed Syntology ran 5 of 5 samples · 0 unverified · 5 pointer-only (licence)
  Specifically, after constructing the sequence through the prompt method and encoding it with a language model, we performed region information global extraction on the encoded sequence for multi-view perception.
• MemeCLIP: Leveraging CLIP Representations for Multimodal Meme Classification
  23 Sep 2024 1 repository listed
  We further compare the performance of MemeCLIP and zero-shot GPT-4 on the hate classification task.
• IITK at SemEval-2024 Task 4: Hierarchical Embeddings for Detection of Persuasion Techniques in Memes
  6 Apr 2024 1 repository listed
  Memes are one of the most popular types of content used in an online disinformation campaign.
• MATK: The Meme Analytical Tool Kit
  11 Dec 2023 1 repository listed
  The rise of social media platforms has brought about a new digital culture called memes.
• Improving Hateful Meme Detection through Retrieval-Guided Contrastive Learning
  14 Nov 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  Hateful memes have emerged as a significant concern on the Internet.
• BanglaAbuseMeme: A Dataset for Bengali Abusive Meme Classification
  18 Oct 2023 1 repository listed
  Finally, we perform a qualitative error analysis of the misclassified memes of the best-performing text-based, image-based and multimodal models.
• Mapping Memes to Words for Multimodal Hateful Meme Classification
  12 Oct 2023 1 repository listed Syntology ran 2 of 3 samples · 1 unverified
  Multimodal image-text memes are prevalent on the internet, serving as a unique form of communication that combines visual and textual elements to convey humor, ideas, or emotions.
• Decoding the Underlying Meaning of Multimodal Hateful Memes
  28 May 2023 1 repository listed
  Recent studies have proposed models that yielded promising performance for the hateful meme classification task.
• MemeGraphs: Linking Memes to Knowledge Graphs
  28 May 2023 1 repository listed
  In this work, we propose to use scene graphs, that express images in terms of objects and their visual relations, and knowledge graphs as structured representations for meme classification with a Transformer-based…
• MemeFier: Dual-stage Modality Fusion for Image Meme Classification
  6 Apr 2023 1 repository listed
  Hate speech is a societal problem that has significantly grown through the Internet.
• Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features
  12 Oct 2022 1 repository listed Syntology ran 0 of 5 samples · 5 unverified
  A simple classifier based on the FIM representation is able to achieve state-of-the-art performance on the Hateful Memes Challenge (HMC) dataset with an AUROC of 85.
• MUTE: A Multimodal Dataset for Detecting Hateful Memes
  10 Oct 2022 1 repository listed
  The exponential surge of social media has enabled information propagation at an unprecedented rate.
• AIDA-UPM at SemEval-2022 Task 5: Exploring Multimodal Late Information Fusion for Multimedia Automatic Misogyny Identification
  1 Jul 2022 1 repository listed
  The main contribution of this paper is the exploration of different late fusion methods to boost the performance of the combination based on the Transformer-based model and Convolutional Neural Networks (CNN) for text…
• Codec at SemEval-2022 Task 5: Multi-Modal Multi-Transformer Misogynous Meme Classification Framework
  14 Jun 2022 1 repository listed
  In this paper we describe our work towards building a generic framework for both multi-modal embedding and multi-label binary classification tasks, while participating in task 5 (Multimedia Automatic Misogyny…
• Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
  16 Feb 2022 1 repository listed
  Discriminative self-supervised learning allows training models on any random group of internet images, and possibly recover salient information that helps differentiate between the images.
• Do Images really do the Talking? Analysing the significance of Images in Tamil Troll meme classification
  9 Aug 2021 1 repository listed
  Our work illustrates different textual analysis methods and contrasting multimodal methods ranging from simple merging to cross attention to utilising both worlds' - best visual and textual features.
• UVCE-IIITT@DravidianLangTech-EACL2021: Tamil Troll Meme Classification: You need to Pay more Attention
  19 Apr 2021 1 repository listed
  We propose an ingenious model comprising of a transformer-transformer architecture that tries to attain state-of-the-art by using attention as its main component.
• IIITK@DravidianLangTech-EACL2021: Offensive Language Identification and Meme Classification in Tamil, Malayalam and Kannada
  17 Apr 2021 1 repository listed
  This paper describes the IIITK team’s submissions to the offensive language identification, and troll memes classification shared tasks for Dravidian languages at DravidianLangTech 2021 workshop@EACL 2021.
• Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge
  23 Dec 2020 1 repository listed
  Memes on the Internet are often harmless and sometimes amusing.
• Enhance Multimodal Transformer With External Label And In-Domain Pretrain: Hateful Meme Challenge Winning Solution
  15 Dec 2020 1 repository listed
  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.
• Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memes
  14 Dec 2020 1 repository listed
  This work presents Vilio, an implementation of state-of-the-art visio-linguistic models and their application to the Hateful Memes Dataset.
• KAFK at SemEval-2020 Task 8: Extracting Features from Pre-trained Neural Networks to Classify Internet Memes
  1 Dec 2020 1 repository listed
  This paper presents two approaches for the internet meme classification challenge of SemEval-2020 Task 8 by Team KAFK (cosec).
• Multimodal Meme Dataset (MultiOFF) for Identifying Offensive Content in Image and Text
  1 May 2020 1 repository listed
  Since there was no publicly available dataset for multimodal offensive meme content detection, we leveraged the memes related to the 2016 U.

Syntology lines on 10 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.