search

salesforce / ALBEF

Code for ALBEF: a new vision-language pre-training method
BSD 3-Clause "New" or "Revised" License
1.56k stars 198 forks source link

questions about Grounding evaluation #15

Closed yechenzhi closed 3 years ago

yechenzhi commented 3 years ago

In your grounding task, you used 'dets.json' to evaluate your results, how do you get the 'dets.json' file? which object detector did you use?

LiJunnan1992 commented 3 years ago

Hi, following previous work such as UNITER, we use the object proposal from Mask-RCNN, provided by "Mattnet: Modular attention network for referring expression comprehension."

yechenzhi commented 3 years ago

Thank you, your work is amazing, It inspires me a lot, I really appreciate it.