Sciweavers

986 search results - page 66 / 198
» Zero-data Learning of New Tasks
Sort
View
146
Voted
ICCV
2011
IEEE
14 years 3 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
145
Voted
IROS
2007
IEEE
150views Robotics» more  IROS 2007»
15 years 10 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...
150
Voted
PRL
2008
133views more  PRL 2008»
15 years 3 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
143
Voted
APIN
2002
121views more  APIN 2002»
15 years 3 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
125
Voted
ICPR
2010
IEEE
15 years 2 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