Sciweavers

1214 search results - page 30 / 243
» Labeling Points with Weights
Sort
View
ICIP
2009
IEEE
15 years 3 months ago
Learning weighted similarity measurements for unconstrained face recognition
Unconstrained face recognition is the problem of deciding if an image pair is showing the same individual or not, without having class specific training material or knowing anythi...
Andre Störmer, Gerhard Rigoll
MICCAI
2008
Springer
16 years 7 months ago
Label Space: A Coupled Multi-shape Representation
Richly labeled images representing several sub-structures of an organ occur quite frequently in medical images. For example, a typical brain image can be labeled into grey matter, ...
James G. Malcolm, Yogesh Rathi, Martha Elizabeth...
ICASSP
2009
IEEE
16 years 28 days ago
Unsupervised acoustic and language model training with small amounts of labelled data
We measure the effects of a weak language model, estimated from as little as 100k words of text, on unsupervised acoustic model training and then explore the best method of using ...
Scott Novotney, Richard M. Schwartz, Jeff Ma
ACL
2010
15 years 3 months ago
Hierarchical Joint Learning: Improving Joint Parsing and Named Entity Recognition with Non-Jointly Labeled Data
One of the main obstacles to producing high quality joint models is the lack of jointly annotated data. Joint modeling of multiple natural language processing tasks outperforms si...
Jenny Rose Finkel, Christopher D. Manning
ICPR
2010
IEEE
15 years 4 months ago
On Dynamic Weighting of Data in Clustering with K-Alpha Means
Although many methods of refining initialization have appeared, the sensitivity of K-Means to initial centers is still an obstacle in applications. In this paper, we investigate a...
Sibao Chen, Haixian Wang, Bin Luo