Sciweavers

864 search results - page 80 / 173
» Selective Attention Improves Learning
Sort
View
IJDAR
2010
169views more  IJDAR 2010»
14 years 11 months ago
A Bayesian network for combining descriptors: application to symbol recognition
Inthispaper,weproposeadescriptorcombination method, which enables to improve significantly the recognition rate compared to the recognition rates obtained by each descriptor. This ...
Sabine Barrat, Salvatore Tabbone
MIR
2005
ACM
198views Multimedia» more  MIR 2005»
15 years 6 months ago
Semi-automatic video annotation based on active learning with multiple complementary predictors
In this paper, we will propose a novel semi-automatic annotation scheme for video semantic classification. It is well known that the large gap between high-level semantics and low...
Yan Song, Xian-Sheng Hua, Li-Rong Dai, Meng Wang
ICMCS
2007
IEEE
133views Multimedia» more  ICMCS 2007»
15 years 7 months ago
Data Modeling Strategies for Imbalanced Learning in Visual Search
In this paper we examine a novel approach to the difficult problem of querying video databases using visual topics with few examples. Typically with visual topics, the examples a...
Jelena Tesic, Apostol Natsev, Lexing Xie, John R. ...
ICCV
2005
IEEE
15 years 6 months ago
Visual Learning Given Sparse Data of Unknown Complexity
This study addresses the problem of unsupervised visual learning. It examines existing popular model order selection criteria before proposes two novel criteria for improving visu...
Tao Xiang, Shaogang Gong
NIPS
2007
15 years 2 months ago
Multiple-Instance Active Learning
We present a framework for active learning in the multiple-instance (MI) setting. In an MI learning problem, instances are naturally organized into bags and it is the bags, instea...
Burr Settles, Mark Craven, Soumya Ray