Suppose you have a collection of digital photos you took on a trip to a zoo. You want to programmatically classify each photo as one of the 100 different kinds of animals you photographed: "aardvark," ...
Illustration of TiViT on a time series sample from ECG200. We split the time series into segments and stack them to form a grayscale image. Then, we patch the image in 2D and feed it into a frozen ViT ...
Results that may be inaccessible to you are currently showing.
Hide inaccessible results