Local Descriptors Encoded by Fisher Vectors for Person Re-identification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

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.
Fichier principal
Vignette du fichier
12_ECCVW_reidentification.pdf (321.67 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00806066 , version 1 (29-03-2013)

Identifiants

Citer

Bingpeng Ma, Yu Su, Frédéric Jurie. Local Descriptors Encoded by Fisher Vectors for Person Re-identification. 12th European Conference on Computer Vision (ECCV) Workshops, 2012, Italy. pp.413-422, ⟨10.1007/978-3-642-33863-2_41⟩. ⟨hal-00806066⟩
433 Consultations
698 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More