Local Descriptors Encoded by Fisher Vectors for Person Re-identification
Résumé
This paper proposes a new descriptor for person re- identi cation building on the recent advances of Fisher Vectors. Speci cally, a simple vector of attributes consisting in the pixel coordinates, its intensity as well as the rst and second-order derivatives is computed for each pixel of the image. These local descriptors are turned into Fisher Vectors before being pooled to produce a global representation of the image. The so-obtained Local Descriptors encoded by Fisher Vector (LDFV) have been validated through experiments on two person re-identi cation benchmarks (VIPeR and ETHZ), achieving state-of-the-art performance on both datasets.
Origine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...