BOSSA: extended BoW formalism for image classification

Abstract : 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.
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00625533
Contributor : Sandra Eliza Fontes de Avila <>
Submitted on : Wednesday, September 21, 2011 - 6:32:42 PM
Last modification on : Thursday, March 21, 2019 - 1:07:19 PM
Long-term archiving on : Thursday, December 22, 2011 - 2:40:07 AM

File

1569408599.pdf
Files produced by the author(s)

Identifiers

Citation

Sandra Avila, Nicolas Thome, Matthieu Cord, Eduardo Valle, Arnaldo de Albuquerque Araújo. BOSSA: extended BoW formalism for image classification. IEEE International Conference on Image Processing (ICIP), Sep 2011, Brussels, Belgium. pp.2909-2912, ⟨10.1109/ICIP.2011.6116268⟩. ⟨hal-00625533⟩

Share

Metrics

Record views

497

Files downloads

513