Sciweavers

ECCV
2008
Springer

Hierarchical Support Vector Random Fields: Joint Training to Combine Local and Global Features

15 years 1 months ago
Hierarchical Support Vector Random Fields: Joint Training to Combine Local and Global Features
Abstract. Recently, impressive results have been reported for the detection of objects in challenging real-world scenes. Interestingly however, the underlying models vary greatly even between the most successful approaches. Methods using a global feature descriptor (e.g. [1]) paired with discriminative classifiers such as SVMs enable high levels of performance, but require large amounts of training data and typically degrade in the presence of partial occlusions. Local feature-based approaches (e.g. [2?4]) are more robust in the presence of partial occlusions but often produce a significant number of false positives. This paper proposes a novel approach called hierarchical support vector random field that allows 1) to combine the power of global feature-based approaches with the flexibility of local feature-based methods in one consistent multi-layer framework and 2) to automatically learn the tradeoff and the optimal interplay between local, semi-local and global feature contributions...
Paul Schnitzspan, Mario Fritz, Bernt Schiele
Added 15 Oct 2009
Updated 15 Oct 2009
Type Conference
Year 2008
Where ECCV
Authors Paul Schnitzspan, Mario Fritz, Bernt Schiele
Comments (0)