search

TIBHannover / MSVA

Deep learning model for supervised video summarization called Multi Source Visual Attention (MSVA)
MIT License
40 stars 17 forks source link

Extracted features for the datasets #1

Open johnbager opened 3 years ago

johnbager commented 3 years ago

could you help me with how to extract features of the datasets? ( I also want to train in my dataset demo)

Junaid112 commented 3 years ago

You want to extract Object features or Motion features?

for object feature you can refer one of our repository https://github.com/VideoAnalysis/EDUVSUM/tree/master/src

For motion features I will refactor the code and upload the feature extraction part with kinetic model.