Unpaired Image Captioning by Language Pivoting
Abstract
Image captioning is a multimodal task involving computer vision and natural language processing, where the goal is to learn a mapping from the image to its natural language description. In general, the mapping function is learned from a training set of image-caption pairs. However, for some language, large scale image-caption paired corpus might not be available. We present an approach to this unpaired image captioning problem by language pivoting. Our method can effectively capture the characteristics of an image captioner from the pivot language (Chinese) and align it to the target language (English) using another pivot-target (Chinese-English) parallel corpus. We evaluate our method on two image-to-English benchmark datasets: MSCOCO and Flickr30K. Quantitative comparisons against several baseline approaches demonstrate the effectiveness of our method.
Cite
Text
Gu et al. "Unpaired Image Captioning by Language Pivoting." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01246-5_31Markdown
[Gu et al. "Unpaired Image Captioning by Language Pivoting." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/gu2018eccv-unpaired/) doi:10.1007/978-3-030-01246-5_31BibTeX
@inproceedings{gu2018eccv-unpaired,
title = {{Unpaired Image Captioning by Language Pivoting}},
author = {Gu, Jiuxiang and Joty, Shafiq and Cai, Jianfei and Wang, Gang},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2018},
doi = {10.1007/978-3-030-01246-5_31},
url = {https://mlanthology.org/eccv/2018/gu2018eccv-unpaired/}
}