ppriyank/Video-Action-Transformer-Network-Pytorch-

About replication

wanna-fly opened this issue · 2 comments

Hi, thanks for this helpful code! Have you replicated performance mentioned in the original paper?

While I have implemented it, I don't work in action recognition, hence I can't possibly comment on it. Though I have verified the architectures with the actual authors, I will post it as a note on ReadMe to resolve this issue, if anyone has been able to reproduce the results.

@ppriyank ok, thank you so much!