Sciweavers

467 search results - page 33 / 94
» Generating labels from clicks
Sort
View
CVPR
2001
IEEE
14 years 9 months ago
Temporal Integration of Multiple Silhouette-Based Body-Part Hypotheses
A method for temporally integrating appearance-based body-part labelling is presented. We begin by modifying the silhouette labelling method of Ghost[4]; that system first determi...
Vivek Kwatra, Aaron F. Bobick, Amos Y. Johnson
ICCV
2009
IEEE
15 years 21 days ago
Learning Deformable Action Templates from Crowded Videos
In this paper, we present a Deformable Action Template (DAT) model that is learnable from cluttered real-world videos with weak supervisions. In our generative model, an action ...
Benjamin Yao, Song-Chun Zhu
ASUNAM
2009
IEEE
13 years 5 months ago
Automatically Detecting Points of Interest and Social Networks from Tracking Positions of Avatars in a Virtual World
With hundreds of millions of users already today, virtual worlds will become an important factor in tomorrow's media landscape. In a virtual world, users are represented by s...
Frank Kappe, Bilal Zaka, Michael Steurer
WWW
2009
ACM
14 years 8 months ago
Extracting article text from the web with maximum subsequence segmentation
Much of the information on the Web is found in articles from online news outlets, magazines, encyclopedias, review collections, and other sources. However, extracting this content...
Jeff Pasternack, Dan Roth
ICPR
2008
IEEE
14 years 9 months ago
Semi-supervised learning on large complex simulations
Complex simulations can generate very large amounts of data stored disjointly across many local disks. Learning from this data can be problematic due to the difficulty of obtainin...
John Nicholas Korecki, Kevin W. Bowyer, Larry O. H...