Johann Diep

That looks amazing!

Thats very interesting, I have never trained it for so long, max only around 6 hours! Will give it a go!

Btw it does look like per video, you have more than 5 frames. Did you increase the number of frames accepted by the model as well?

Alright, let me increase the frame number as well and give it a go. Report you the results in a couple of days!

@DaddyWesker How did you plot those little GIFs of the results actually?

@DaddyWesker And have you tried testing it on a more sophisticated dataset, i.e. Kinetic-600 with their text annotation? Would be very interesting to see how the results are conditioned on...

@DaddyWesker Have to admit, your results looks far better than mine:  This took me 3 days to train, and I only got 1000 epochs. How were you...

I suggest you read the paper "On Scalar Embedding of Relative Positions in Attention Models". In that paper, they explain the implemented bucketing function.

@ChintanTrivedi Did you had success with that?

@martinriven can you show us some of your results?