About Text_Swap

[SinyWu0615]

I want to get more details on text_swap. I have found that some text of the 'orig' label and the 'text_swap' label are the same in the datasets. Can you provide a more detailed explanation of text_swap and its fake_text_pos? here is an example: { "id": 683133, "image": "DGM4/origin/guardian/0385/488.jpg", "text": "Making a song and dance David Hasselhoff will perform a oneman show at the Edinburgh festival fringe", "fake_cls": "orig", "fake_image_box": [], "fake_text_pos": [], "mtcnn_boxes": [...] }, { "id": 896499, "image": "DGM4/origin/guardian/0114/251.jpg", "text": "Making a song and dance David Hasselhoff will perform a oneman show at the Edinburgh festival fringe", "fake_cls": "text_swap", "fake_image_box": [], "fake_text_pos": [ 0, 7, 8, 9, 10, 11, 13, 14, 15, 16 ], "mtcnn_boxes": [...] }

[rshaojimmy]

We change the whole text sentence in the sample of "id": 896499, and thus name the fake_cls as text_swap.

Thanks.

[SinyWu0615]

我已收到您的邮件，会尽快处理，祝您生活愉快！