anonymoussubmission2025/submission-viinfographicvqa
收藏Hugging Face2025-11-07 更新2025-11-15 收录
下载链接：
https://hf-mirror.com/datasets/anonymoussubmission2025/submission-viinfographicvqa
下载链接
链接失效反馈官方服务：
资源简介：
ViInfographicVQA是一个越南语的视觉问答基准数据集，用于理解信息图表。它评估模型从数据丰富、布局复杂的视觉中读取、推理和综合信息的能力，这些视觉包括文本、图表、地图和设计元素。数据集提供了两种设置：单图像VQA，回答来自单个信息图表的问题；多图像VQA，需要跨多个语义相关的信息图表进行推理。
ViInfographicVQA is a Vietnamese Visual Question Answering (VQA) benchmark for infographic understanding. It evaluates models ability to read, reason, and synthesize information from data-rich, layout-heavy visuals that mix text, charts, maps, and design elements. Two settings are provided: Single-image VQA - questions answered from one infographic, and Multi-image VQA - questions requiring reasoning across multiple, semantically related infographics.
提供机构：
anonymoussubmission2025
