Sciweavers

986 search results - page 66 / 198
» Zero-data Learning of New Tasks
Sort
View
ICCV
2011
IEEE
13 years 10 months ago
Relative Attributes
Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person ...
Devi Parikh, Kristen Grauman
IROS
2007
IEEE
150views Robotics» more  IROS 2007»
15 years 4 months ago
Long-Term learning using multiple models for outdoor autonomous robot navigation
Abstract—Autonomous robot navigation in unstructured outdoor environments is a challenging area of active research. The navigation task requires identifying safe, traversable pat...
Michael J. Procopio, Jane Mulligan, Gregory Z. Gru...
PRL
2008
133views more  PRL 2008»
14 years 9 months ago
Better multiclass classification via a margin-optimized single binary problem
We develop a new multiclass classification method that reduces the multiclass problem to a single binary classifier (SBC). Our method constructs the binary problem by embedding sm...
Ran El-Yaniv, Dmitry Pechyony, Elad Yom-Tov
APIN
2002
121views more  APIN 2002»
14 years 9 months ago
Applying Learning by Examples for Digital Design Automation
This paper describes a new learning by example mechanism and its application for digital circuit design automation. This mechanism uses finite state machines to represent the infer...
Ben Choi
ICPR
2010
IEEE
14 years 8 months ago
Scene-Adaptive Human Detection with Incremental Active Learning
In many computer vision tasks, scene changes hinder the generalization ability of trained classifiers. For instance, a human detector trained with one set of images is unlikely t...
Ajay Joshi, Fatih Porikli