Sciweavers

1601 search results - page 143 / 321
» Learning Gaussian processes from multiple tasks
Sort
View
151
Voted
ICCV
2003
IEEE
15 years 8 months ago
Reinforcement Learning for Combining Relevance Feedback Techniques
Relevance feedback (RF) is an interactive process which refines the retrievals by utilizing user’s feedback history. Most researchers strive to develop new RF techniques and ign...
Peng-Yeng Yin, Bir Bhanu, Kuang-Cheng Chang, Anlei...
CVPR
2005
IEEE
16 years 5 months ago
Learning a Similarity Metric Discriminatively, with Application to Face Verification
We present a method for training a similarity metric from data. The method can be used for recognition or verification applications where the number of categories is very large an...
Sumit Chopra, Raia Hadsell, Yann LeCun
139
Voted
KDD
2009
ACM
227views Data Mining» more  KDD 2009»
16 years 4 months ago
Efficiently learning the accuracy of labeling sources for selective sampling
Many scalable data mining tasks rely on active learning to provide the most useful accurately labeled instances. However, what if there are multiple labeling sources (`oracles...
Pinar Donmez, Jaime G. Carbonell, Jeff Schneider
CVPR
2008
IEEE
16 years 5 months ago
Decomposition, discovery and detection of visual categories using topic models
We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...
Mario Fritz, Bernt Schiele
182
Voted
CVPR
2009
IEEE
16 years 10 months ago
Learning General Optical Flow Subspaces for Egomotion Estimation and Detection of Motion Anomalies
This paper deals with estimation of dense optical flow and ego-motion in a generalized imaging system by exploiting probabilistic linear subspace constraints on the flow. We dea...
Richard Roberts (Georgia Institute of Technology),...