search

microsoft / VideoX

VideoX: a collection of video cross-modal models
Other
978 stars 161 forks source link

about Upper Bound in Table 4 #39

Closed onlyonewater closed 3 years ago

onlyonewater commented 3 years ago

hi, in the paper, you provide the upper bound results on activitynet captioning dataset, I want to know how to calculate the upper bound results, thanks!!!

Sy-Zhang commented 3 years ago

hi, in the paper, you provide the upper bound results on activitynet captioning dataset, I want to know how to calculate the upper bound results, thanks!!!

For each map of size NxN, we assume the moment that has the highest IoU value with the ground truth is our prediction. The upper bound can then be computed.

onlyonewater commented 3 years ago

oh, I get it. thanks!!!!