English

Belief Revision based Caption Re-ranker with Visual Semantic Information

Computer Vision and Pattern Recognition 2022-09-20 v1 Computation and Language

Abstract

In this work, we focus on improving the captions generated by image-caption generation systems. We propose a novel re-ranking approach that leverages visual-semantic measures to identify the ideal caption that maximally captures the visual information in the image. Our re-ranker utilizes the Belief Revision framework (Blok et al., 2003) to calibrate the original likelihood of the top-n captions by explicitly exploiting the semantic relatedness between the depicted caption and the visual context. Our experiments demonstrate the utility of our approach, where we observe that our re-ranker can enhance the performance of a typical image-captioning system without the necessity of any additional training or fine-tuning.

Keywords

Cite

@article{arxiv.2209.08163,
  title  = {Belief Revision based Caption Re-ranker with Visual Semantic Information},
  author = {Ahmed Sabir and Francesc Moreno-Noguer and Pranava Madhyastha and Lluís Padró},
  journal= {arXiv preprint arXiv:2209.08163},
  year   = {2022}
}

Comments

COLING 2022

R2 v1 2026-06-28T01:28:48.041Z