search

LJOVO / TranSalNet

TranSalNet: Towards perceptually relevant visual saliency prediction. Neurocomputing (2022)
https://doi.org/10.1016/j.neucom.2022.04.080
MIT License
51 stars 10 forks source link

Can we test this code on our own input videos? #5

Closed venkat19-spec closed 4 months ago

LJOVO commented 5 months ago

Hi,

Yes. You would need to input the videos frame by frame into the model and resize each frame to 384x288 (width x height ).

Best.