When we want to use classifiers like SVM, we first should extract descriptors using algorithms like SIFT.
But I have a question which might call a silly one: Let's assume $$ \begin {equation} D_a=\{d_{a,1},d_{a,2},d_{a,3},...,d_{a,M}\} \end {equation} $$ where M is total number of descriptors and $d_{a,?}$ denotes the description vector of mth descriptors. My question is: what the sentence "$d_{a,?}$ denotes the description vector of m-th descriptors" means? Does it mean that we have 1000 interest point in the image that each of them has ,let's say, a 128-dimension SIFT descriptors? Do we have 128000 values?