About some problems of sh

[Lee-AI-sco]

sh = mtimesx(samplesf{k1}, permute(hf{k1}, [3 4 1 2]), 'speed'); sh(:,1,1+pad_sz{k}(1):end-pad_sz{k}(1), 1+pad_sz{k}(2):end) = ... sh(:,1,1+pad_sz{k}(1):end-pad_sz{k}(1), 1+pad_sz{k}(2):end) + mtimesx(samplesf{k}, permute(hf{k}, [3 4 1 2]), 'speed');

hello: Your work is great.Recently,I plan to implement your ECO using C++,but I met some problems about the variable ''sh'',I have a question of what it denotes in the lhs_operation_joint.m,and I wonder why you occur to implement the two steps.

[martin-danelljan]

Hi. The variable sh is actually just the Fourier coefficients of the target confidence scores on all the training samples. It is computed by multiplying the training samples samplesf with the filter hf. The loop and the index variable k goes over the different feature blocks.