Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

11-2023

Abstract

Hateful meme detection is a challenging multimodal task that requires comprehension of both vision and language, as well as cross-modal interactions. Recent studies have tried to fine-tune pre-trained vision-language models (PVLMs) for this task. However, with increasing model sizes, it becomes important to leverage powerful PVLMs more efficiently, rather than simply fine-tuning them. Recently, researchers have attempted to convert meme images into textual captions and prompt language models for predictions. This approach has shown good performance but suffers from non-informative image captions. Considering the two factors mentioned above, we propose a probing-based captioning approach to leverage PVLMs in a zero-shot visual question answering (VQA) manner. 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 detection. The good performance of models with Pro-Cap on three benchmarks validates the effectiveness and generalization of the proposed method 1.

Keywords

Memes, multimodal, semantic extraction

Discipline

Databases and Information Systems | Graphic Communications | Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering

Publication

MM '23: Proceedings of the 31st ACM International Conference on Multimedia, Ottawa, October 29 - November 3

First Page

5244

Last Page

5252

ISBN

9798400701085

Identifier

10.1145/3581783.3612498

Publisher

ACM

City or Country

New York

Copyright Owner and License

Authors

Creative Commons License

Creative Commons Attribution 3.0 License
This work is licensed under a Creative Commons Attribution 3.0 License.

Additional URL

https://doi.org/10.1145/3581783.3612498

Share

COinS