To illustrate a two-dimensional cross-correlation operation, consider a $3 \times 3$ input tensor and a $2 \times 2$ kernel tensor. Let the input be $\begin{bmatrix} 0 & 1 & 2 3 & 4 & 5 6 & 7 & 8 \end{bmatrix}$ and the kernel be $\begin{bmatrix} 0 & 1 2 & 3 \end{bmatrix}$. The convolution window begins at the upper-left corner of the input. The input subtensor within this window and the kernel are multiplied elementwise, and the products are summed to yield a single scalar value: $0 \times 0 + 1 \times 1 + 3 \times 2 + 4 \times 3 = 19$. As the window slides across the input tensor from left to right and top to bottom, this process is repeated. The resulting output tensor has a shape of $2 \times 2$ and contains the four derived scalar values, forming the matrix $\begin{bmatrix} 19 & 25 37 & 43 \end{bmatrix}$.