Supervised learning and codebook optimization for bag of words models

Mingyuan Jiu 1 Christian Wolf 1 Christophe Garcia 1 Atilla Baskurt 1
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : In this paper, we present a novel approach for supervised codebook learning and optimization for bag of words models. This type of models is frequently used in visual recognition tasks like object class recognition or human action recognition. An entity is represented as a histogram of codewords, which are traditionally clustered with unsupervised methods like \textit{k}-means or random forests, and then classified in a supervised way. We propose a new supervised method for joint codebook creation and class learning, which learns the cluster centers of the codebook in a goal-directed way using the class labels of the training set. As a result, the codebook is highly correlated to the recognition problem, leading to a more discriminative codebook. We propose two different learning algorithms, one based on error backpropagation and one based on cluster label reassignment. We apply the proposed method to human action recognition from video sequences and evaluate it on the KTH dataset, reporting very promising results. The proposed technique allows to improve the discriminative power of an unsupervised learned codebook, or to keep the discriminative power while decreasing the size of the learned codebook, thus decreasing the computational complexity due to the nearest neighbor search.
Type de document :
Article dans une revue
Cognitive Computation, 2012, 4, pp.409-419. 〈10.1007/s12559-012-9137-4 〉
Liste complète des métadonnées
Contributeur : Équipe Gestionnaire Des Publications Si Liris <>
Soumis le : mercredi 10 août 2016 - 16:17:06
Dernière modification le : lundi 10 décembre 2018 - 17:47:40




Mingyuan Jiu, Christian Wolf, Christophe Garcia, Atilla Baskurt. Supervised learning and codebook optimization for bag of words models. Cognitive Computation, 2012, 4, pp.409-419. 〈10.1007/s12559-012-9137-4 〉. 〈hal-01352965〉



Consultations de la notice