Busca avançada
Ano de início
Entree


BOSSA: EXTENDED BOW FORMALISM FOR IMAGE CLASSIFICATION

Texto completo
Autor(es):
Avila, S. ; Thome, N. ; Cord, M. ; Valle, E. ; Araujo, A. de A. ; IEEE
Número total de Autores: 6
Tipo de documento: Artigo Científico
Fonte: 2011 18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP); v. N/A, p. 4-pg., 2011-01-01.
Resumo

In image classification, the most powerful statistical learning approaches are based on the Bag-of-Words paradigm. In this article, we propose an extension of this formalism. Considering the Bag-of-Features, dictionary coding and pooling steps, we propose to focus on the pooling step. Instead of using the classical sum or max pooling strategies, we introduced a density function-based pooling strategy. This flexible formalism allows us to better represent the links between dictionary codewords and local descriptors in the resulting image signature. We evaluate our approach in two very challenging tasks of video and image classification, involving very high level semantic categories with large and nuanced visual diversity. (AU)

Processo FAPESP: 09/05951-8 - Indexação de dados multimídia em alta dimensionalidade: aplicação à busca em bases de imagens e vídeos
Beneficiário:Eduardo Alves Do Valle Junior
Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado