Sciweavers

1606 search results - page 204 / 322
» Object Recognition using Junctions
Sort
View
ICPR
2002
IEEE
15 years 11 months ago
Prototype Selection for Finding Efficient Representations of Dissimilarity Data
The nearest neighbor (NN) rule is a simple and intuitive method for solving classification problems. Originally, it uses distances to the complete training set. It performs well, ...
Elzbieta Pekalska, Robert P. W. Duin
KDD
2004
ACM
190views Data Mining» more  KDD 2004»
15 years 10 months ago
Kernel k-means: spectral clustering and normalized cuts
Kernel k-means and spectral clustering have both been used to identify clusters that are non-linearly separable in input space. Despite significant research, these methods have re...
Inderjit S. Dhillon, Yuqiang Guan, Brian Kulis
ICRA
2010
IEEE
170views Robotics» more  ICRA 2010»
14 years 8 months ago
Categorizing object-action relations from semantic scene graphs
— In this work we introduce a novel approach for detecting spatiotemporal object-action relations, leading to both, action recognition and object categorization. Semantic scene g...
Eren Erdal Aksoy, Alexey Abramov, Florentin Wö...
CVPR
2006
IEEE
16 years 2 days ago
SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition
We consider visual category recognition in the framework of measuring similarities, or equivalently perceptual distances, to prototype examples of categories. This approach is qui...
Alexander C. Berg, Hao Zhang 0003, Jitendra Malik,...
CLOR
2006
15 years 1 months ago
Visual Classification by a Hierarchy of Extended Fragments
The chapter describes visual classification by a hierarchy of semantic fragments. In fragment-based classification, objects within a class are represented by common sub-structures ...
Shimon Ullman, Boris Epshtein