Sciweavers

480 search results - page 50 / 96
» Parameterized Modeling and Recognition of Activities
Sort
View
ICCV
2003
IEEE
15 years 11 months ago
Automatically Labeling Video Data Using Multi-class Active Learning
Labeling video data is an essential prerequisite for many vision applications that depend on training data, such as visual information retrieval, object recognition, and human act...
Rong Yan, Jie Yang, Alexander G. Hauptmann
CVPR
2011
IEEE
14 years 6 months ago
Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds
Active learning and crowdsourcing are promising ways to efficiently build up training sets for object recognition, but thus far techniques are tested in artificially controlled ...
Sudheendra Vijayanarasimhan, Kristen Grauman
IUI
2009
ACM
15 years 6 months ago
Using salience to segment desktop activity into projects
Knowledge workers must manage large numbers of simultaneous, ongoing projects that collectively involve huge numbers of resources (documents, emails, web pages, calendar items, et...
Daniel Lowd, Nicholas Kushmerick
PAMI
2002
112views more  PAMI 2002»
14 years 9 months ago
Feature Space Trajectory Methods for Active Computer Vision
We advance new active object recognition algorithms that classify rigid objects and estimate their pose from intensity images. Our algorithms automatically detect if the class or p...
Michael A. Sipe, David Casasent
ICARIS
2007
Springer
15 years 3 months ago
Towards a Novel Immune Inspired Approach to Temporal Anomaly Detection
Abstract. In this conceptual paper, we report on studies and initial definitions of an immune-inspired approach to temporal anomaly detection problems, where there is a strict temp...
Thiago S. Guzella, Tomaz A. Mota-Santos, Walmir M....