OVDEval Dataset

OVDEval includes 9 sub-tasks and introduces evaluations on commonsense knowledge, attribute understanding, position understanding, object relation comprehension, and more. The dataset is meticulously created to provide hard negatives that challenge models' true understanding of visual and linguistic input.

OVDEval 包含9个子任务，并引入了对常识知识、属性理解、位置理解、物体关系理解等多方面的评估。该数据集精心构建，旨在提供具有挑战性的负样本，以考验模型对视觉和语言输入的真正理解能力。