Automatic Chinese Meme Generation using Deep Neural Networksopen access
- Authors
- Lin, W.; Qimeng, Z.; Kim, YoungBin; Wu, R.; Jin, H.; Deng, H.; Luo, P.; Kim, C.-H.
- Issue Date
- Nov-2021
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- Computer architecture; Computer Vision; Decoding; Deep Learning; Feature extraction; Image Captioning; Internet; Internet Meme; Meme Generation; Social networking (online); Task analysis; Transformers
- Citation
- IEEE Access, v.9, pp 152657 - 152667
- Pages
- 11
- Journal Title
- IEEE Access
- Volume
- 9
- Start Page
- 152657
- End Page
- 152667
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/52195
- DOI
- 10.1109/ACCESS.2021.3127324
- ISSN
- 2169-3536
- Abstract
- 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. Author
- Files in This Item
-
- Appears in
Collections - Graduate School of Advanced Imaging Sciences, Multimedia and Film > Department of Imaging Science and Arts > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/52195)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.