UIT-OpenViIC

UIT-OpenViIC是首个包含越南语描述的大型图像标注数据集，由越南国家大学胡志明市的信息技术大学创建。该数据集包含13,100张图像，每张图像平均有4.7个描述，描述内容涉及越南日常生活和文化。数据集的创建过程严格，确保了描述的多样性和挑战性，适用于越南及全球的视觉语言研究社区。UIT-OpenViIC旨在解决现有图像描述模型在非英语环境下的性能不足问题，为越南语图像描述研究提供了一个标准基准。

UIT-OpenViIC is the first large-scale image captioning dataset with Vietnamese descriptions, developed by the University of Information Technology, Vietnam National University Ho Chi Minh City. This dataset includes 13,100 images, with an average of 4.7 descriptions per image. The descriptions cover Vietnamese daily life and culture. The dataset was created through a rigorous process to ensure the diversity and challenging nature of its annotations, making it suitable for the visual-language research communities in both Vietnam and across the globe. UIT-OpenViIC aims to address the performance gaps of existing image captioning models in non-English contexts, providing a standard benchmark for Vietnamese image captioning research.