A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is
We observe that natural factors of variation describing scenes, e.g., the position of pedestrians, have temporally sparse transitions in videos. ... We find that the tested models mostly struggle to generalize to our proposed benchmark. Instead of predicting the correct factors, models tend to predict values in previously observed ranges. ... of the number of changing generative factors. ...doi:10.15496/publikation-67592 fatcat:kzbojwwu5zfdpfz5jf2ipnfhzy