cmhungsteve / SSTDA

[CVPR 2020] Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation (PyTorch)

Home Page:https://arxiv.org/abs/2003.02824

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

I3D Feature

Alen-T opened this issue · comments

Each video feature dimension:(2048,X), Whether the feature dimension of each frame extracted is 2048? or divide the video into X frames, and then extract all the frames with a special frame (2048, X)?
I3D doesn't seem to be able to extract features from a single frame, so, I want to know how you extract features from a video. Can you provide code to extract features? Thank you very much!

I used the features provided by MS-TCN.
You can check how they extract features here: yabufarha/ms-tcn#16.
Although you cannot extract I3D features using a single frame, you can utilize neighbor frames.
For example, to extract a feature representing frame n, we can use a video clip with frames [n-7,n+7].