Sciweavers

345 search results - page 25 / 69
» Multiclass Object Recognition with Sparse, Localized Feature...
Sort
View
ICPR
2004
IEEE
16 years 25 days ago
Object Recognition Using Composed Receptive Field Histograms of Higher Dimensionality
Recent work has shown that effective methods for recognising objects or spatio-temporal events can be constructed based on receptive field responses summarised into histograms or ...
Oskar Linde, Tony Lindeberg
ACCV
2007
Springer
15 years 6 months ago
Hierarchical Learning of Dominant Constellations for Object Class Recognition
Abstract. The importance of spatial configuration information for object class recognition is widely recognized. Single isolated local appearance codes are often ambiguous. On the...
Nathan Mekuz, John K. Tsotsos
TCSV
2008
195views more  TCSV 2008»
14 years 11 months ago
Locality Versus Globality: Query-Driven Localized Linear Models for Facial Image Computing
Conventional subspace learning or recent feature extraction methods consider globality as the key criterion to design discriminative algorithms for image classification. We demonst...
Yun Fu, Zhu Li, Junsong Yuan, Ying Wu, Thomas S. H...
ICPR
2002
IEEE
16 years 24 days ago
To Each According to its Need: Kernel Class Specific Classifiers
We present in this paper a new multi-class Bayes classifier that permits using separate feature vectors, chosen specifically for each class. This technique extends previous work o...
Barbara Caputo, Heinrich Niemann
IJCV
2000
149views more  IJCV 2000»
14 years 11 months ago
Recognition without Correspondence using Multidimensional Receptive Field Histograms
The appearance of an object is composed of local structure. This local structure can be described and characterized by a vector of local features measured by local operators such a...
Bernt Schiele, James L. Crowley