This paper introduces a novel image captioning model designed to effectively combine the geometric and appearance features of objects with linguistic context. The model employs dual self-attention mechanisms to capture both spatial and visual relationships among objects, along with a cross-attention module to align these features with corresponding textual descriptions. The proposed has been evaluated on two Vietnamese image captioning datasets, showcasing its ability to generate accurate, contextually rich captions that outperform several state-of-the-art models. The proposed approach addresses the unique challenges of Vietnamese language structure in image captioning tasks, demonstrating robustness in handling complex interactions between visual and linguistic features. The results indicate that the model effectively bridges the gap between image content and textual representation, making it a promising solution for image captioning applications in Vietnamese. This model offers a significant contribution to the field, particularly for localized applications where understanding the meaning of language and context is essential to generate high-quality image descriptions that are both relevant and informative.