Fisher encoding (Fisher Vector encoding (FV)) More...
#include "generic.h"
Go to the source code of this file.
Defines | |
Fisher vector options | |
#define | VL_FISHER_FLAG_SQUARE_ROOT (0x1 << 0) |
Use signed squared-root (Normalization and improved Fisher vectors). | |
#define | VL_FISHER_FLAG_NORMALIZED (0x1 << 1) |
Gobally normalize the Fisher vector in L2 norm (Normalization and improved Fisher vectors). | |
#define | VL_FISHER_FLAG_IMPROVED (VL_FISHER_FLAG_NORMALIZED|VL_FISHER_FLAG_SQUARE_ROOT) |
Improved Fisher vector. This is the same as VL_FISHER_FLAG_SQUARE_ROOT|VL_FISHER_FLAG_NORMALIZED . | |
#define | VL_FISHER_FLAG_FAST (0x1 << 2) |
Fast but more approximate calculations (Faster computations). Keep only the larges data to cluster assignment (posterior). | |
Functions | |
VL_EXPORT vl_size | vl_fisher_encode (void *enc, vl_type dataType, void const *means, vl_size dimension, vl_size numClusters, void const *covariances, void const *priors, void const *data, vl_size numData, int flags) |
Fisher encoding (Fisher Vector encoding (FV))
Definition in file fisher.h.
#define VL_FISHER_FLAG_FAST (0x1 << 2) |
Fast but more approximate calculations (Faster computations). Keep only the larges data to cluster assignment (posterior).
Improved Fisher vector. This is the same as VL_FISHER_FLAG_SQUARE_ROOT|VL_FISHER_FLAG_NORMALIZED
.
#define VL_FISHER_FLAG_NORMALIZED (0x1 << 1) |
Gobally normalize the Fisher vector in L2 norm (Normalization and improved Fisher vectors).
#define VL_FISHER_FLAG_SQUARE_ROOT (0x1 << 0) |
Use signed squared-root (Normalization and improved Fisher vectors).