Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.
The paper (which I was not familiar with) proposes a new pooling method, which they name "Low-rank Bi-linear Pooling". Because it is a pooling method, its output should be a single value over some input spatial region (the goal of pooling is to down-sample an input representation). They do not want to use the resulting vector from the element-wise multiplication, they want to get a single scalar. Notice their initial formula: