Murdoch University Research Repository

Welcome to the Murdoch University Research Repository

The Murdoch University Research Repository is an open access digital collection of research
created by Murdoch University staff, researchers and postgraduate students.

Learn more

LCEval: Learned Composite Metric for Caption Evaluation

Sharif, N., White, L., Bennamoun, M., Liu, W. and Shah, S.A.A. (2019) LCEval: Learned Composite Metric for Caption Evaluation. International Journal of Computer Vision, 127 (10). pp. 1586-1610.

Link to Published Version:
*Subscription may be required


Automatic evaluation metrics hold a fundamental importance in the development and fine-grained analysis of captioning systems. While current evaluation metrics tend to achieve an acceptable correlation with human judgements at the system level, they fail to do so at the caption level. In this work, we propose a neural network-based learned metric to improve the caption-level caption evaluation. To get a deeper insight into the parameters which impact a learned metric’s performance, this paper investigates the relationship between different linguistic features and the caption-level correlation of the learned metrics. We also compare metrics trained with different training examples to measure the variations in their evaluation. Moreover, we perform a robustness analysis, which highlights the sensitivity of learned and handcrafted metrics to various sentence perturbations. Our empirical analysis shows that our proposed metric not only outperforms the existing metrics in terms of caption-level correlation but it also shows a strong system-level correlation against human assessments.

Item Type: Journal Article
Murdoch Affiliation(s): Information Technology, Mathematics and Statistics
Publisher: Springer US
Copyright: © 2019 Springer Science+Business Media, LLC, part of Springer Nature
Item Control Page Item Control Page