About CIDEr of MSR-VTT

[guoliwu]

It is mentioned in the paper that the CIDERr of MSR-VTT dataset is only 48.5 when AC LOSS is not added, and it can reach 49.5 after adding it, but I found that the CIDEr reached 48.8 before adding it, and it is still 48.8 after adding it, I would like to ask if it is caused by which step of my experiment is wrong?