About Eq(5) in paper

[232525]

Hi, I have a question about eq(5) in paper, $$\mathcal{Z}(I;{W, B})_{p, i} = B_i + \sumj^c I{p,i}W{i,j}$$ why not $$\mathcal{Z}(I;{W, B})\{p, i} = B_i + \sumj^c I{\textcolor{red}{p,j}}W_{i,j}$$

the output of $\mathcal{Z}_{p, i}$ is producted by the i-th 1*1 conv kernel params $W_i$ and $B_i$, with the input of $I_p$?

have I missed something?

[mlyarthur]

I have the same confusion, maybe the author mistake it.