Automatic Chinese Meme Generation Using Deep Neural Networks

Internet memes have become widely used by people for online communication and interaction, particularly through social media. Interest in meme-generation research has been increasing rapidly. In this study, we address the problem of meme generation as an image captioning task, which uses an encoder&...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Lin Wang, Qimeng Zhang, Youngbin Kim, Ruizheng Wu, Hongyu Jin, Haoke Deng, Pengchu Luo, Chang-Hun Kim
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Deep learning computer vision image captioning meme generation internet meme Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/2d90e3c311a84b9f9e40afd641a880ae
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2d90e3c311a84b9f9e40afd641a880ae
record_format	dspace
spelling	oai:doaj.org-article:2d90e3c311a84b9f9e40afd641a880ae2021-11-26T00:00:21ZAutomatic Chinese Meme Generation Using Deep Neural Networks2169-353610.1109/ACCESS.2021.3127324https://doaj.org/article/2d90e3c311a84b9f9e40afd641a880ae2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9611242/https://doaj.org/toc/2169-3536Internet memes have become widely used by people for online communication and interaction, particularly through social media. Interest in meme-generation research has been increasing rapidly. In this study, we address the problem of meme generation as an image captioning task, which uses an encoder–decoder architecture to generate Chinese meme texts that match image content. First, to train the model on the characteristics of Chinese memes, we collected a dataset of 3,000 meme images with 30,000 corresponding humorous Chinese meme texts. Second, we introduced a Chinese meme generation system that can generate humorous and relevant texts from any given image. Our system used a pre-trained ResNet-50 for image feature extraction and a state-of-the-art transformer-based GPT-2 model to generate Chinese meme texts. Finally, we combined the generated text and images to form common image memes. We performed qualitative evaluations of the generated Chinese meme texts through different user studies. The evaluation results revealed that the Chinese memes generated by our model were indistinguishable from real ones.Lin WangQimeng ZhangYoungbin KimRuizheng WuHongyu JinHaoke DengPengchu LuoChang-Hun KimIEEEarticleDeep learningcomputer visionimage captioningmeme generationinternet memeElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 152657-152667 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Deep learning computer vision image captioning meme generation internet meme Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Deep learning computer vision image captioning meme generation internet meme Electrical engineering. Electronics. Nuclear engineering TK1-9971 Lin Wang Qimeng Zhang Youngbin Kim Ruizheng Wu Hongyu Jin Haoke Deng Pengchu Luo Chang-Hun Kim Automatic Chinese Meme Generation Using Deep Neural Networks
description	Internet memes have become widely used by people for online communication and interaction, particularly through social media. Interest in meme-generation research has been increasing rapidly. In this study, we address the problem of meme generation as an image captioning task, which uses an encoder–decoder architecture to generate Chinese meme texts that match image content. First, to train the model on the characteristics of Chinese memes, we collected a dataset of 3,000 meme images with 30,000 corresponding humorous Chinese meme texts. Second, we introduced a Chinese meme generation system that can generate humorous and relevant texts from any given image. Our system used a pre-trained ResNet-50 for image feature extraction and a state-of-the-art transformer-based GPT-2 model to generate Chinese meme texts. Finally, we combined the generated text and images to form common image memes. We performed qualitative evaluations of the generated Chinese meme texts through different user studies. The evaluation results revealed that the Chinese memes generated by our model were indistinguishable from real ones.
format	article
author	Lin Wang Qimeng Zhang Youngbin Kim Ruizheng Wu Hongyu Jin Haoke Deng Pengchu Luo Chang-Hun Kim
author_facet	Lin Wang Qimeng Zhang Youngbin Kim Ruizheng Wu Hongyu Jin Haoke Deng Pengchu Luo Chang-Hun Kim
author_sort	Lin Wang
title	Automatic Chinese Meme Generation Using Deep Neural Networks
title_short	Automatic Chinese Meme Generation Using Deep Neural Networks
title_full	Automatic Chinese Meme Generation Using Deep Neural Networks
title_fullStr	Automatic Chinese Meme Generation Using Deep Neural Networks
title_full_unstemmed	Automatic Chinese Meme Generation Using Deep Neural Networks
title_sort	automatic chinese meme generation using deep neural networks
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/2d90e3c311a84b9f9e40afd641a880ae
work_keys_str_mv	AT linwang automaticchinesememegenerationusingdeepneuralnetworks AT qimengzhang automaticchinesememegenerationusingdeepneuralnetworks AT youngbinkim automaticchinesememegenerationusingdeepneuralnetworks AT ruizhengwu automaticchinesememegenerationusingdeepneuralnetworks AT hongyujin automaticchinesememegenerationusingdeepneuralnetworks AT haokedeng automaticchinesememegenerationusingdeepneuralnetworks AT pengchuluo automaticchinesememegenerationusingdeepneuralnetworks AT changhunkim automaticchinesememegenerationusingdeepneuralnetworks
_version_	1718409958363496448

Automatic Chinese Meme Generation Using Deep Neural Networks

Ejemplares similares