Code for the Paper: Antonino Furnari and Giovanni Maria Farinella. What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention. International Conference on Computer Vision, 2019.
Thank you for your question. Alpha is the sampling interval (we sample one frame every 0.25 seconds), not the anticipation time. Please see here for more information: http://arxiv.org/pdf/2005.02190.pdf
EK100 paper seems to define the anticipation gap time as 1 second. I want to know the detail.