Boost Image Captioning with Knowledge Reasoning

TL;DR

This paper enhances image captioning by introducing word attention for better visual focus and integrating external knowledge from knowledge graphs, resulting in more accurate and meaningful descriptions that outperform existing methods.

Contribution

It proposes a novel word attention mechanism and knowledge graph integration to improve caption quality in image captioning models.

Findings

Achieves state-of-the-art performance on COCO and Flickr30k datasets.

Outperforms many existing image captioning approaches.

Demonstrates the effectiveness of knowledge reasoning in caption generation.

Abstract

Automatically generating a human-like description for a given image is a potential research in artificial intelligence, which has attracted a great of attention recently. Most of the existing attention methods explore the mapping relationships between words in sentence and regions in image, such unpredictable matching manner sometimes causes inharmonious alignments that may reduce the quality of generated captions. In this paper, we make our efforts to reason about more accurate and meaningful captions. We first propose word attention to improve the correctness of visual attention when generating sequential descriptions word-by-word. The special word attention emphasizes on word importance when focusing on different regions of the input image, and makes full use of the internal annotation knowledge to assist the calculation of visual attention. Then, in order to reveal those incomprehensible intentions that cannot be expressed straightforwardly by machines, we introduce a new strategy to inject external knowledge extracted from knowledge graph into the encoder-decoder framework to facilitate meaningful captioning. Finally, we validate our model on two freely available captioning benchmarks: Microsoft COCO dataset and Flickr30k dataset. The results demonstrate that our approach achieves state-of-the-art performance and outperforms many of the existing approaches.