Annotation for grounded caption task. #1398
Kingofolk
started this conversation in
Ideas / Feature requests
Replies: 1 comment 1 reply
-
|
Like AI-mask, AI-polygon, but with text not a point? SAM model supports that, which is already used in Labelme, so this should be close to possible. |
Beta Was this translation helpful? Give feedback.
1 reply
-
|
Yes, u r right. Grounded caption annotation aims to write a paragragh to describe the image, then grounded each valuable noun phrase on the original picture. Could you give me a path to know how to achieve this via labelme? As I do not find tutorial about this on the intro page. Thanks a lot! |
Beta Was this translation helpful? Give feedback.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hi, is there any ways to accompolish the annotation of grounded caption? If not, could this function be incoportated? Thx a lot!
best regards
Beta Was this translation helpful? Give feedback.
All reactions