1547 search results - page 208 / 310 » Learning a Classification Model for Segmentation |
179
click to vote
CHI
2011
ACM
14 years 8 months ago
2011
ACM
While many devices today increasingly have the ability to predict human activities, it is still difficult to build accurate personalized machine learning models. As users today wi...
149
click to vote
CVPR
2010
IEEE
16 years 1 months ago
2010
IEEE
The dynamic texture (DT) is a probabilistic generative model, defined over space and time, that represents a video as the output of a linear dynamical system (LDS). The DT model ...
172
click to vote
ICRA
2003
IEEE
15 years 10 months ago
2003
IEEE
— In this paper we present a novel method for robot path planning based on learning motion patterns. A motion pattern is defined as the path that results from applying a set of ...
151
click to vote
EMNLP
2008
15 years 6 months ago
2008
We describe an approach for acquiring the domain-specific dialog knowledge required to configure a task-oriented dialog system that uses human-human interaction data. The key aspe...
185
click to vote
CVPR
2009
IEEE
17 years 13 hour ago
2009
IEEE
Active learning strategies can be useful when manual labeling
effort is scarce, as they select the most informative
examples to be annotated first. However, for visual category
...