Sciweavers

56 search results - page 5 / 12
» Automatically Labeling Video Data Using Multi-class Active L...
Sort
View
ACCV
2010
Springer
13 years 3 months ago
Stream-based Active Unusual Event Detection
We present a new active learning approach to incorporate human feedback for on-line unusual event detection. In contrast to most existing unsupervised methods that perform passiv...
Chen Change Loy, Tao Xiang, Shaogang Gong
IJCAI
2007
13 years 9 months ago
Common Sense Based Joint Training of Human Activity Recognizers
Given sensors to detect object use, commonsense priors of object usage in activities can reduce the need for labeled data in learning activity models. It is often useful, however,...
Shiaokai Wang, William Pentney, Ana-Maria Popescu,...
CVPR
2005
IEEE
14 years 9 months ago
Semi-Supervised Cross Feature Learning for Semantic Concept Detection in Videos
For large scale automatic semantic video characterization, it is necessary to learn and model a large number of semantic concepts. But a major obstacle to this is the insufficienc...
Rong Yan, Milind R. Naphade
WWW
2006
ACM
14 years 8 months ago
Large-scale text categorization by batch mode active learning
Large-scale text categorization is an important research topic for Web data mining. One of the challenges in large-scale text categorization is how to reduce the amount of human e...
Steven C. H. Hoi, Rong Jin, Michael R. Lyu
AAAI
2010
13 years 9 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...