Sciweavers

1354 search results - page 32 / 271
» Learning Object Models from Appearance
Sort
View
ICPR
2006
IEEE
16 years 27 days ago
Latent Layout Analysis for Discovering Objects in Images
Latent Layout Analysis (LLA) is a novel unsupervised learning technique to discover objects in unseen images using a set of un-annotated training images. LLA defines a generative ...
David Liu, Datong Chen, Tsuhan Chen
AMR
2003
Springer
179views Multimedia» more  AMR 2003»
15 years 5 months ago
Building User Models from Observations of Users Accessing Multimedia Learning Objects
Abstract. We report our work towards building user models of learner’s development based upon evidence of their interactions with an e-learning website composed of multimedia lea...
Judy Kay, Andrew Lum
WACV
2005
IEEE
15 years 5 months ago
Using Co-Occurrence and Segmentation to Learn Feature-Based Object Models from Video
A number of recent systems for unsupervised featurebased learning of object models take advantage of cooccurrence: broadly, they search for clusters of discriminative features tha...
Thomas S. Stepleton, Tai Sing Lee
ICCV
2003
IEEE
16 years 1 months ago
Segmenting Foreground Objects from a Dynamic Textured Background via a Robust Kalman Filter
The algorithm presented in this paper aims to segment the foreground objects in video (e.g., people) given timevarying, textured backgrounds. Examples of time-varying backgrounds ...
Jing Zhong, Stan Sclaroff
NIPS
2007
15 years 1 months ago
Learning Visual Attributes
We present a probabilistic generative model of visual attributes, together with an efficient learning algorithm. Attributes are visual qualities of objects, such as ‘red’, ...
Vittorio Ferrari, Andrew Zisserman