You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
We've had a feature request from a collaborator around image search.
Extracting more contextual features (url, caption) could help identifying the roots of these cascades and tracing their branching development in a large corpus
The idea here was that if we could extract images and match it up with text near it, the URL it was on, etc. we could help establish context around the images themselves. Right now we extract popular images and hashes so this would enhance things out a bit.
The text was updated successfully, but these errors were encountered:
I think realistically this issue has been addressed in part through our enhanced image extraction - I think providing more functionality here would be getting a bit out of scope. Any objections to closing?
We've had a feature request from a collaborator around image search.
The idea here was that if we could extract images and match it up with text near it, the URL it was on, etc. we could help establish context around the images themselves. Right now we extract popular images and hashes so this would enhance things out a bit.
The text was updated successfully, but these errors were encountered: