Sciweavers

7351 search results - page 1167 / 1471
» Segmenting Point Sets
Sort
View
CVPR
2009
IEEE
17 years 2 months ago
Multi-Camera Activity Correlation Analysis
We propose a novel approach for modelling correlations between activities in a busy public space captured by multiple non-overlapping and uncalibrated cameras. In our approach, ...
Chen Change Loy (Queen Mary, University of London)...
DAGM
2011
Springer
14 years 6 months ago
Agnostic Domain Adaptation
The supervised learning paradigm assumes in general that both training and test data are sampled from the same distribution. When this assumption is violated, we are in the setting...
Alexander Vezhnevets, Joachim M. Buhmann
CVPR
2012
IEEE
14 years 1 days ago
Foreground Detection Using Spatiotemporal Projection Kernels
Foreground detection is at the core of many video processing tasks. In this paper, we propose a novel video foreground detection method that exploits the statistics of 3D space-tim...
Y. Moshe, H. Hel-Or, and Y. Hel-Or
PAMI
2012
13 years 9 months ago
Quantifying and Transferring Contextual Information in Object Detection
— Context is critical for reducing the uncertainty in object detection. However, context modelling is challenging because there are often many different types of contextual infor...
Wei-Shi Zheng, Shaogang Gong, Tao Xiang
KDD
2012
ACM
205views Data Mining» more  KDD 2012»
13 years 9 months ago
Rank-loss support instance machines for MIML instance annotation
Multi-instance multi-label learning (MIML) is a framework for supervised classification where the objects to be classified are bags of instances associated with multiple labels....
Forrest Briggs, Xiaoli Z. Fern, Raviv Raich
« Prev « First page 1167 / 1471 Last » Next »