Component based comparative analysis of each module in image captioning | Zendy

Seoung-Ho Choi | Zendy; Seoung Yeon Jo | Zendy; Sung Hoon Jung | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Component based comparative analysis of each module in image captioning

Author(s) -

Seoung-Ho Choi,

Seoung Yeon Jo,

Sung Hoon Jung

Publication year - 2020

Publication title -

ict express

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.733

H-Index - 22

ISSN - 2405-9595

DOI - 10.1016/j.icte.2020.08.004

Subject(s) - closed captioning , component (thermodynamics) , image (mathematics) , computer science , task (project management) , artificial intelligence , black box , deep learning , engineering , physics , systems engineering , thermodynamics

Image captioning is a task to generate a new caption using the training data of the image and caption. Since existing deep learning is a black-box model, it is crucial to analyze the influence on each module for understanding the model. In this paper, we analyze the impact of the five modules and do a comparative analysis according to three losses and two optimizations using two datasets. From extensive experiments, the best component of each module has been identified as an improved method.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research