rubenvillegas / iclr2017mcnet

Tensorflow implementation of the ICLR 2017 paper: Decomposing Motion and Content for Natural Video Sequence Prediction

Home Page:https://sites.google.com/a/umich.edu/rubenevillegas/iclr2017

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

preprocessing for KTH Dataset

GuptaSonam opened this issue · comments

Hi,
The paper says that "Sub-clips for running, jogging and walking were manually trimmed to ensure humans are always present in the frames."
Does this mean that the frames having partially visible human (mostly the beginning and the end frames) have been trimmed to?

Thanks

As far as I remember, the answer is yes.