mingming

Hi, I'm meng. Sorry to bother you, I download the GazeCapture_supplementary.h5, I find this file only include 1366 person, while there are total 1474 person in GazeCapture dataset. So I...

Can BLIP generate more words image caption?

7

Hi, I have try BLIP_large model, which finetuned on COCO, but it seems only generate about 10 words length caption, even I set max_length to 40, which is twice as...

Thank you for sharing your work. I have some trouble in equivariance loss, which is Eq.10 in paper. In your code, it seems to trnsform the the key point of...

Thanks for sharing, but I only find code for segmentation, is there any code for the image classification task reported in paper?