93 search results - page 2 / 19 » An Integrated System for Incremental Learning of Multiple Vi... |
CVPR
2008
IEEE
14 years 7 months ago
2008
IEEE
We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...
ICPR
2000
IEEE
13 years 10 months ago
2000
IEEE
Many realistic visual recognition tasks are “open” in the sense that the number and nature of the categories to be learned are not initially known, and there is no closed set ...
KCAP
2009
ACM
14 years 8 days ago
2009
ACM
One of the grand challenges of AI is to build systems that learn by reading. The ideal system would construct a rich knowledge base capable of automated reasoning. We have built a...
HRI
2006
ACM
13 years 11 months ago
2006
ACM
The paper presents an approach to using structural descriptions, obtained through a human-robot tutoring dialogue, as labels for the visual object models a robot learns. The paper...
ICRA
2010
IEEE
13 years 4 months ago
2010
IEEE
— Multi-target tracking becomes significantly more challenging when the targets are in close proximity or frequently interact with each other. This paper presents a promising tr...