Abstract
This paper replicates the experiment presented in the work of Xu et al. [1], and examines errors in the generated captions. The analysis of the identified errors aims to provide deeper insight into the underlying causes. This study also encompasses subsequent experiments aiming at investigating the feasibility of rectifying these errors via a post-processing stage. Image recognition and object detection models, as well as a language probability computational model were explored. The findings presented in this paper aim to contribute towards the overarching objective of Explainable Artificial Intelligence (XAI), thereby providing potential pathways to improve image captioning.
Export citation and abstract BibTeX RIS
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.