Can I read Image Captioning via Semantic Guidance Attention and Consensus Selection Strategy on EtoBox?

Image Captioning via Semantic Guidance Attention and Consensus Selection Strategy by Jie Wu; Haifeng Hu; Yi Wu is a Computer Science article available to read on EtoBox.

What is Image Captioning via Semantic Guidance Attention and Consensus Selection Strategy about?

Recently, a series of attempts have incorporated spatial attention mechanisms into the task of image captioning, which achieves a remarkable improvement in the quality of generative captions. However, the traditional spatial attention mechanism adopts latent and delayed semantic representations to decide which area should be paid more attention to, resulting in inaccurate semantic guidance and the introduction of redundant information. In order to optimize the spatial attention mechanism, we propose the Semantic Guidance Attention (SGA) mechanism in this article. Specifically, SGA utilizes semantic word representations to provide an intuitive semantic guidance that focuses accurately on semantic-related regions. Moreover, we reduce the difficulty of generating fluent sentences by updating the attention information in time. At the same time, the beam search algorithm is widely used to predict words during sequence generation. This algorithm generates a sentence according to the probabilities of words, so it is easy to push out a generic sentence and discard some distinctive captions. In order to overcome this limitation, we design the Consensus Selection (CS) strategy to choose the

Who reads Image Captioning via Semantic Guidance Attention and Consensus Selection Strategy?

Author

Jie Wu; Haifeng Hu; Yi Wu

Publisher

Association for Computing Machinery; Association for Computing Machinery (ACM) (ISSN 1551-6857)

Published

2018

Language

EN

Field

Computer Science (Physical Sciences)