search

laura-wang / video_repres_sts

Pytorch implementation of our T-PAMI 2021 paper: Self-supervised Video Representation Learning by Uncovering Motion and Appearance Statistics
48 stars 7 forks source link

Datasets for Benchmarks #3

Open amitbcp opened 3 years ago

amitbcp commented 3 years ago

Thanks for opensourcing the code base. The paper was really insightful and I was looking to conduct few experiments, is it possible to share the code used for adding the other datasets and experiments as mentioned in the dataset ?

laura-wang commented 3 years ago

Thanks for your interests.

I will provide these code by the end of this week. Please stay tuned.

amitbcp commented 2 years ago

Thanks @laura-wang for the code .

I wanted to request your help to understand the temporal statistics. The sts folder I can see the scripts for generating and calculating it. But in the readme it says to generate optical flow using tlv1 and we pass the folders to train.py

Can you please share how to generate the temporal statistics for the input RGB videos. Thanks in advance