Sciweavers

942 search results - page 168 / 189
» Comparing Automatic and Human Evaluation of NLG Systems
Sort
View
ICCV
2009
IEEE
15 years 1 months ago
Is a detector only good for detection?
A common design of an object recognition system has two steps, a detection step followed by a foreground withinclass classification step. For example, consider face detection by...
Quan Yuan and Stan Sclaroff
CVPR
2006
IEEE
14 years 10 months ago
A Simple Bayesian Framework for Content-Based Image Retrieval
We present a Bayesian framework for content-based image retrieval which models the distribution of color and texture features within sets of related images. Given a userspecified ...
Katherine A. Heller, Zoubin Ghahramani
WWW
2009
ACM
14 years 8 months ago
Scrolling behaviour with single- and multi-column layout
The standard layout model used by web browsers is to lay text out in a vertical scroll using a single column. The horizontal-scroll layout model--in which text is laid out in colu...
Cameron Braganza, Kim Marriott, Peter Moulder, Mic...
IJCNN
2006
IEEE
14 years 2 months ago
Reinforcement Learning for Parameterized Motor Primitives
Abstract— One of the major challenges in both action generation for robotics and in the understanding of human motor control is to learn the “building blocks of movement genera...
Jan Peters, Stefan Schaal
MM
2006
ACM
184views Multimedia» more  MM 2006»
14 years 2 months ago
Extraction of social context and application to personal multimedia exploration
Personal media collections are often viewed and managed along the social dimension, the places we spend time at and the people we see, thus tools for extracting and using this inf...
Brett Adams, Dinh Q. Phung, Svetha Venkatesh