In this survey, we analyze the main contributions and trends of works leveraging Transformers to model video. Specifically, we delve into how videos are handled at the input level first. Then, we study the architectural changes made to deal with video more efficiently, reduce redundancy, re-introduce useful inductive biases, and...
Introduction Since I had an hdd scare and almost lost all of my childhood pictures I started taking backups and disk status seriously. There are many ways to do this. You can pay for cloud storage and let professionals handle it. Or if you’re feeling techie you can set up...