Deep Learning Approaches Based on Transformer Architectures for Image Captioning Tasks

Deep Learning Approaches Based on Transformer Architectures for Image Captioning Tasks

This paper focuses on <italic>visual attention</italic>, a state-of-the-art approach for image captioning tasks within the computer vision research area. We study the impact that different hyperparemeter configurations on an encoder-decoder visual attention architecture in terms of effic...

Full description

Bibliographic Details
Main Authors: Roberto Castro, Israel Pineda, Wansu Lim, Manuel Eugenio Morocho-Cayamcela
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Image captioning
visual attention
computer vision
supervised learning
artificial intelligence
Online Access:https://ieeexplore.ieee.org/document/9739703/

Internet

https://ieeexplore.ieee.org/document/9739703/

Similar Items