Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Huertas-Tato, Javier, Koutlis, Christos, Papadopoulos, Symeon, Camacho, David, Kompatsiaris, Ioannis
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2409.05772
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917771796807680
author Huertas-Tato, Javier
Koutlis, Christos
Papadopoulos, Symeon
Camacho, David
Kompatsiaris, Ioannis
author_facet Huertas-Tato, Javier
Koutlis, Christos
Papadopoulos, Symeon
Camacho, David
Kompatsiaris, Ioannis
contents Memes are an increasingly prevalent element of online discourse in social networks, especially among young audiences. They carry ideas and messages that range from humorous to hateful, and are widely consumed. Their potentially high impact requires adequate means of control to moderate their use in large scale. In this work, we propose SimCLIP a deep learning-based architecture for cross-modal understanding of memes, leveraging a pre-trained CLIP encoder to produce context-aware embeddings and a Siamese fusion technique to capture the interactions between text and image. We perform an extensive experimentation on seven meme classification tasks across six datasets. We establish a new state of the art in Memotion7k with a 7.25% relative F1-score improvement, and achieve super-human performance on Harm-P with 13.73% F1-Score improvement. Our approach demonstrates the potential for compact meme classification models, enabling accurate and efficient meme monitoring. We share our code at https://github.com/jahuerta92/meme-classification-simclip
format Preprint
id arxiv_https___arxiv_org_abs_2409_05772
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A CLIP-based siamese approach for meme classification
Huertas-Tato, Javier
Koutlis, Christos
Papadopoulos, Symeon
Camacho, David
Kompatsiaris, Ioannis
Multimedia
Memes are an increasingly prevalent element of online discourse in social networks, especially among young audiences. They carry ideas and messages that range from humorous to hateful, and are widely consumed. Their potentially high impact requires adequate means of control to moderate their use in large scale. In this work, we propose SimCLIP a deep learning-based architecture for cross-modal understanding of memes, leveraging a pre-trained CLIP encoder to produce context-aware embeddings and a Siamese fusion technique to capture the interactions between text and image. We perform an extensive experimentation on seven meme classification tasks across six datasets. We establish a new state of the art in Memotion7k with a 7.25% relative F1-score improvement, and achieve super-human performance on Harm-P with 13.73% F1-Score improvement. Our approach demonstrates the potential for compact meme classification models, enabling accurate and efficient meme monitoring. We share our code at https://github.com/jahuerta92/meme-classification-simclip
title A CLIP-based siamese approach for meme classification
topic Multimedia
url https://arxiv.org/abs/2409.05772