Sciweavers

1807 search results - page 130 / 362
» Backdoors in the Context of Learning
Sort
View
MM
2010
ACM
115views Multimedia» more  MM 2010»
14 years 8 months ago
Interactive learning of heterogeneous visual concepts with local features
In the context of computer-assisted plant identification we are facing challenging information retrieval problems because of the very high within-class variability and of the lim...
Wajih Ouertani, Michel Crucianu, Nozha Boujemaa
IJCNLP
2005
Springer
15 years 3 months ago
A Chunking Strategy Towards Unknown Word Detection in Chinese Word Segmentation
This paper proposes a chunking strategy to detect unknown words in Chinese word segmentation. First, a raw sentence is pre-segmented into a sequence of word atoms 1 using a maximum...
Guodong Zhou
ECCV
2010
Springer
15 years 3 months ago
A Stochastic Graph Evolution Framework for Robust Multi-Target Tracking
Maintaining the stability of tracks on multiple targets in video over extended time periods remains a challenging problem. A few methods which have recently shown encouraging resul...
ICPR
2008
IEEE
15 years 11 months ago
On refining dissimilarity matrices for an improved NN learning
Application-specific dissimilarity functions can be used for learning from a set of objects represented by pairwise dissimilarity matrices in this context. These dissimilarities m...
Elzbieta Pekalska, Robert P. W. Duin
ICIP
2009
IEEE
15 years 11 months ago
Learning Contextual Rules For Priming Object Categories In Images
In this paper we introduce and exploit the concept of contextual rules in the field of object detection. These rules are defined as associations between different object likelihoo...