YapengTian/AVE-ECCV18

Request for information on mapping h5 content to video ids

Closed this issue · 2 comments

Hi,

The labels in the h5 file are numerical while the Annotations.txt contain text only. Can you please let me know the mapping scheme? i.e. is Churchbell=label0 and Mandolin=label28 or is it in some other way?

Thanks!

image
Yes. But, we will plus one background class. So, the first 28 classes are in the order. The last one refers to the background class in our one-hot encoding.

Perfect. Thanks!