Pro-Cap: Leveraging a frozen vision-language model for hateful meme detection
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 impo...
Saved in:
Main Authors: | CAO, Rui, HEE, Ming Shan, KUEK, Adriel, CHONG, Wen Haw, LEE, Roy Ka-Wei, JIANG, Jing |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8477 https://ink.library.smu.edu.sg/context/sis_research/article/9480/viewcontent/Pro_Cap_pvoa_cc_by.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
MERMAID: A dataset and framework for multimodal meme semantic understanding
by: TOH, Shaun, et al.
Published: (2023) -
Multimodal zero-shot hateful meme detection
by: ZHU, Jiawen, et al.
Published: (2022) -
On explaining multimodal hateful meme detection models
by: HEE, Ming Shan, et al.
Published: (2022) -
Disentangling hate in online memes
by: LEE, Ka Wei, Roy, et al.
Published: (2021) -
MATK: The Meme Analytical Tool Kit
by: HEE, Ming Shan, et al.
Published: (2023)