Viet-Anh on Software Logo

What is: Time-aware Large Kernel Convolution?

SourceTime-aware Large Kernel Convolutions
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

A Time-aware Large Kernel (TaLK) convolution is a type of temporal convolution that learns the kernel size of a summation kernel for each time-step instead of learning the kernel weights as in a typical convolution operation. For each time-step, a function is responsible for predicting the appropriate size of neighbor representations to use in the form of left and right offsets relative to the time-step.