Sciweavers

746 search results - page 81 / 150
» A general method for human activity recognition in video
Sort
View
TNN
2008
178views more  TNN 2008»
15 years 6 months ago
IMORL: Incremental Multiple-Object Recognition and Localization
This paper proposes an incremental multiple-object recognition and localization (IMORL) method. The objective of IMORL is to adaptively learn multiple interesting objects in an ima...
Haibo He, Sheng Chen
ICMI
2003
Springer
116views Biometrics» more  ICMI 2003»
15 years 11 months ago
Interactive skills using active gaze tracking
We have incorporated interactive skills into an active gaze tracking system. Our active gaze tracking system can identify an object in a cluttered scene that a person is looking a...
Rowel Atienza, Alexander Zelinsky
MIR
2006
ACM
189views Multimedia» more  MIR 2006»
16 years 4 days ago
Dynamic storyboards for video content summarization
We propose an innovative, general purpose, approach to the selection and hierarchical representation of key frames of a video sequence for video summarization. In the first stage ...
Gianluigi Ciocca, Raimondo Schettini
PKDD
2009
Springer
174views Data Mining» more  PKDD 2009»
16 years 22 days ago
Active and Semi-supervised Data Domain Description
Data domain description techniques aim at deriving concise descriptions of objects belonging to a category of interest. For instance, the support vector domain description (SVDD) l...
Nico Görnitz, Marius Kloft, Ulf Brefeld
DEBS
2010
ACM
15 years 10 months ago
Logic-based representation, reasoning and machine learning for event recognition
Today’s organisations require techniques for automated transformation of the large data volumes they collect during their operations into operational knowledge. This requirement...
Alexander Artikis, Georgios Paliouras, Franç...