GTA: Geometric transform-attention network for enhanced spatial reasoning in image captioning

Neurocomputing 2026

View at publisher
Authors: Mohammad Alamgir Hossain, Zhongfu Ye, Md.Bipul Hossen, Md Shohidul Islam, Md.Ibrahim Abdullah
DOI: 10.1016/j.neucom.2026.133497
Cited by: 7
References: 18

Fields of Study & Subjects

Multimodal Machine Learning Applications Constraint Satisfaction and Optimization Visual Attention and Saliency Detection

Publication details

Journal / source
Neurocomputing
Publisher
Elsevier BV
Volume
683
Pages
133497–133497
Publication date
31 March 2026
Language
EN