TextVR icon indicating copy to clipboard operation
TextVR copied to clipboard

A large Cross-Modal Video Retrieval Dataset with Reading Comprehension

Results 3 TextVR issues
Sort by recently updated
recently updated
newest added

what size are the resized videos? are they also temporally resampled?

你好!! 能提供一下MSR-VTT 和 YouCook2这两个数据集的视频OCR的识别结果吗? 十分感谢~ 我看到论文中有在这两个数据集上进行含场景文本的文本-视频检索实验

Could you please upload the dataset to hugging face?