Sciweavers

35 search results - page 2 / 7
» Unsupervised Discovery of Action Classes
Sort
View
ICCV
2005
IEEE
13 years 10 months ago
LOCUS: Learning Object Classes with Unsupervised Segmentation
We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...
John M. Winn, Nebojsa Jojic
ICML
2000
IEEE
13 years 9 months ago
Using Learning by Discovery to Segment Remotely Sensed Images
In this paper, we describe our research in computer-aided image analysis. We have incorporated machine learning methodologies with traditional image processing to perform unsuperv...
Leen-Kiat Soh, Costas Tsatsoulis
ISWC
2006
IEEE
13 years 10 months ago
Discovering Characteristic Actions from On-Body Sensor Data
We present an approach to activity discovery, the unsupervised identification and modeling of human actions embedded in a larger sensor stream. Activity discovery can be seen as ...
David Minnen, Thad Starner, Irfan A. Essa, Charles...
AAAI
2010
13 years 6 months ago
Unsupervised Learning of Event Classes from Video
We present a method for unsupervised learning of event classes from videos in which multiple actions might occur simultaneously. It is assumed that all such activities are produce...
Muralikrishna Sridhar, Anthony G. Cohn, David C. H...
ML
2000
ACM
13 years 4 months ago
Multistrategy Discovery and Detection of Novice Programmer Errors
Detecting and diagnosing errors in novice behavior is an important student modeling task. In this paper, we describe MEDD, an unsupervised incremental multistrategy system for the ...
Raymund Sison, Masayuki Numao, Masamichi Shimura