Changrong Xiao, Sean Xin Xu, Kunpeng Zhang. Multimodal Data Augmentation for Image Captioning using Diffusion Models. In Zheng Wang, Cheng Long, Shihao Xu, Bingzheng Gan, Wei Shi, Zhao Cao, Tat-Seng Chua, editors, Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal Applications, LGM3A 2023, Ottawa ON, Canada, 2 November 2023. pages 23-33, ACM, 2023. [doi]
@inproceedings{XiaoXZ23-0,
title = {Multimodal Data Augmentation for Image Captioning using Diffusion Models},
author = {Changrong Xiao and Sean Xin Xu and Kunpeng Zhang},
year = {2023},
doi = {10.1145/3607827.3616839},
url = {https://doi.org/10.1145/3607827.3616839},
researchr = {https://researchr.org/publication/XiaoXZ23-0},
cites = {0},
citedby = {0},
pages = {23-33},
booktitle = {Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal Applications, LGM3A 2023, Ottawa ON, Canada, 2 November 2023},
editor = {Zheng Wang and Cheng Long and Shihao Xu and Bingzheng Gan and Wei Shi and Zhao Cao and Tat-Seng Chua},
publisher = {ACM},
}