EXAONE-Atelier
Jupyter notebook examples for EXAONE Atelier Image to Text in AWS Marketplace.
EXAONE Atelier Image to Text is the latest version of the LG AI Research's image captioning model based on L-Verse (Kim et al., CVPR 2022) and BITTERS (Kim et al., Arxiv 2022).
Please contact opensource@lgresearch.ai for any questions regarding EXAONE Atelier.
Open Source Software Notice
Ⓒ 2023 LG AI Research. All rights reserved.
This software contains source code provided by NVIDIA Corporation. Also, this application uses Open Source Software (OSS). You can find the source code of these open source projects, along with applicable license information here.
How to cite
@InProceedings{Kim_2022_CVPR,
author = {Kim, Taehoon and Song, Gwangmo and Lee, Sihaeng and Kim, Sangyun and Seo, Yewon and Lee, Soonyoung and Kim, Seung Hwan and Lee, Honglak and Bae, Kyunghoon},
title = {L-Verse: Bidirectional Generation Between Image and Text},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2022},
pages = {16526-16536}
}
@misc{kim2022bitters,
title = {Large-Scale Bidirectional Training for Zero-Shot Image Captioning},
author = {Kim, Taehoon and Marsden, Mark and Ahn, Pyunghwan and Kim, Sangyun and Lee, Sihaeng and Sala, Alessandra and Kim, Seung Hwan},
publisher = {arXiv},
year = {2022},
doi = {10.48550/ARXIV.2211.06774},
url = {https://arxiv.org/abs/2211.06774},
keywords = {Computer Vision and Pattern Recognition (cs.CV), Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
}