Over the years, coding—in its broadest definition—has proven a crucial step in visual recognition systems [4, 7]. Many techniques have been investigated, such as bag of words [1, 9, 16, 18, 19, 31], sparse coding [21, 34], and locality-based coding[33, 35]. All these techniques follow a similar flow: Given a dictionary of code words, a query is associated to one or multiple dictionary elements with different weights (i.e. let@tokeneonedot, binary or real). These weights, or codes, act as the new representation for the query and serve as input to a classifier (i.e., support vector machine (SVM)) after an optional pooling step.
|Title of host publication||Riemannian Computing in Computer Vision|
|Editors||Pavan K. Turaga, Anuj Srivastava|
|Place of Publication||Cham Switzerland|
|Number of pages||17|
|Publication status||Published - 2016|