Sciweavers

6113 search results - page 154 / 1223
» Learning Features for Tracking
Sort
View
92
Voted
ICML
2007
IEEE
16 years 3 months ago
Analyzing feature generation for value-function approximation
We analyze a simple, Bellman-error-based approach to generating basis functions for valuefunction approximation. We show that it generates orthogonal basis functions that provably...
Ronald Parr, Christopher Painter-Wakefield, Lihong...
134
Voted
ECCV
2010
Springer
15 years 7 months ago
A Stochastic Graph Evolution Framework for Robust Multi-Target Tracking
Maintaining the stability of tracks on multiple targets in video over extended time periods remains a challenging problem. A few methods which have recently shown encouraging resul...
105
Voted
ICML
2006
IEEE
16 years 3 months ago
Active sampling for detecting irrelevant features
The general approach for automatically driving data collection using information from previously acquired data is called active learning. Traditional active learning addresses the...
Sriharsha Veeramachaneni, Emanuele Olivetti, Paolo...
133
Voted
CVPR
2011
IEEE
14 years 10 months ago
Sharing Features Between Objects and Their Attributes
Visual attributes expose human-defined semantics to object recognition models, but existing work largely restricts their influence to mid-level cues during classifier training....
Sung Ju Hwang, Fei Sha, Kristen Grauman
ICALT
2006
IEEE
15 years 8 months ago
Building Learning Networks for Lifelong Learners: Challenges, Models, Technologies and Standards
In this tutorial five key problems are discussed that occur in the area of lifelong learning. For each problem we will look at the possible technological solutions. The five probl...
Rob Koper