Sciweavers

63 search results - page 11 / 13
» Kernelizing the output of tree-based methods
Sort
View
INFOCOM
2012
IEEE
13 years 5 months ago
A statistical approach for target counting in sensor-based surveillance systems
—Target counting in sensor-based surveillance systems is an interesting task that potentially could have many important applications in practice. In such a system, each sensor ou...
Dengyuan Wu, Dechang Chen, Kai Xing, Xiuzhen Cheng
153
Voted
TMM
2010
270views Management» more  TMM 2010»
14 years 9 months ago
Sequence Multi-Labeling: A Unified Video Annotation Scheme With Spatial and Temporal Context
Abstract--Automatic video annotation is a challenging yet important problem for content-based video indexing and retrieval. In most existing works, annotation is formulated as a mu...
Yuanning Li, YongHong Tian, Ling-Yu Duan, Jingjing...
167
Voted
TNN
2010
234views Management» more  TNN 2010»
14 years 9 months ago
Novel maximum-margin training algorithms for supervised neural networks
This paper proposes three novel training methods, two of them based on the back-propagation approach and a third one based on information theory for Multilayer Perceptron (MLP) bin...
Oswaldo Ludwig, Urbano Nunes
ICASSP
2010
IEEE
15 years 1 months ago
A comparison of approaches for modeling prosodic features in speaker recognition
Prosodic information has been successfully used for speaker recognition for more than a decade. The best-performing prosodic system to date has been one based on features extracte...
Luciana Ferrer, Nicolas Scheffer, Elizabeth Shribe...
CVPR
2010
IEEE
15 years 11 months ago
Sufficient Dimensionality Reduction for Visual Sequence Classification
When classifying high-dimensional sequence data, traditional methods (e.g., HMMs, CRFs) may require large amounts of training data to avoid overfitting. In such cases dimensional...
Alex Shyr, Raquel Urtasun, Michael Jordan