Sciweavers

488 search results - page 32 / 98
» Multilayer Sequence Labeling
Sort
View
CVPR
2012
IEEE
12 years 3 days ago
Discriminative virtual views for cross-view action recognition
We propose an approach for cross-view action recognition by way of ‘virtual views’ that connect the action descriptors extracted from one (source) view to those extracted from...
Ruonan Li, Todd Zickler
ICIP
1998
IEEE
14 years 11 months ago
Lip Features Automatic Extraction
An algorithm for speaker's lip segmentation and features extraction is presented in this paper. A color video sequence of speaker's face is acquired, under natural light...
Franck Luthon, Marc Liévin
ECEASST
2010
13 years 7 months ago
Checking Graph-Transformation Systems for Confluence
d Abstract) Detlef Plump Abstract. In general, it is undecidable whether a terminating graphtransformation system is confluent or not. We introduce the class of coverable hypergrap...
Detlef Plump
ICML
2004
IEEE
14 years 3 months ago
Online learning of conditionally I.I.D. data
In this work we consider the task of relaxing the i.i.d assumption in online pattern recognition (or classification), aiming to make existing learning algorithms applicable to a ...
Daniil Ryabko
JMLR
2006
99views more  JMLR 2006»
13 years 9 months ago
Worst-Case Analysis of Selective Sampling for Linear Classification
A selective sampling algorithm is a learning algorithm for classification that, based on the past observed data, decides whether to ask the label of each new instance to be classi...
Nicolò Cesa-Bianchi, Claudio Gentile, Luca ...