@inproceedings{jiang2019tiger,
author = {Jiang, Ming and Huang, Qiuyuan and Zhang, Lei and Wang, Xin and Zhang, Pengchuan and Gan, Zhe and Diesner, Jana and Gao, Jianfeng},
title = {TIGEr: Text-to-Image Grounding for Image Caption Evaluation},
booktitle = {EMNLP 2019},
year = {2019},
month = {November},
abstract = {This paper presents a new metric called TIGEr for the automatic evaluation of image captioning systems. Popular metrics, such as BLEU and CIDEr, are based solely on text matching between reference captions and machine-generated captions, potentially leading to biased evaluations because references may not fully cover the image content and natural language is inherently ambiguous. Building upon a machine-learned text-image grounding model, TIGEr allows to evaluate caption quality not only based on how well a caption represents image content, but also on how well machine-generated captions match human-generated captions. Our empirical tests show that TIGEr has a higher consistency with human judgments than alternative existing metrics. We also comprehensively assess the metric's effectiveness in caption evaluation by measuring the correlation between human judgments and metric scores.},
url = {http://approjects.co.za/?big=en-us/research/publication/tiger-text-to-image-grounding-for-image-caption-evaluation/},
}