722 search results - page 66 / 145 » Learning from Relevant Tasks Only |
AAAI
2008
13 years 11 months ago
2008
We consider the problem of grasping novel objects in cluttered environments. If a full 3-d model of the scene were available, one could use the model to estimate the stability and...
CVPR
2010
IEEE
14 years 5 months ago
2010
IEEE
For object category recognition to scale beyond a small number of classes, it is important that algorithms be able to learn from a small amount of labeled data per additional clas...
CVPR
2009
IEEE
15 years 4 months ago
2009
IEEE
Given an image, we propose a hierarchical generative
model that classifies the overall scene, recognizes and segments
each object component, as well as annotates the image
with ...
COLT
2007
Springer
14 years 3 months ago
2007
Springer
Property testing deals with tasks where the goal is to distinguish between the case that an object (e.g., function or graph) has a prespecified property (e.g., the function is li...
PCM
2001
Springer
14 years 1 months ago
2001
Springer
An E-Partner is a photo-realistic conversation agent, which has a talking head that not only look photo-realistic but also can have a conversation with the user about a given topic...