Sciweavers

1871 search results - page 176 / 375
» Selecting for evolvable representations
Sort
View
ICCV
2007
IEEE
14 years 10 months ago
Vector Quantizing Feature Space with a Regular Lattice
Most recent class-level object recognition systems work with visual words, i.e., vector quantized local descriptors. In this paper we examine the feasibility of a dataindependent ...
Tinne Tuytelaars, Cordelia Schmid
ICML
2008
IEEE
14 years 9 months ago
Memory bounded inference in topic models
What type of algorithms and statistical techniques support learning from very large datasets over long stretches of time? We address this question through a memory bounded version...
Ryan Gomes, Max Welling, Pietro Perona
IV
2008
IEEE
91views Visualization» more  IV 2008»
14 years 2 months ago
Candidate Mapping: Finding Your Place Amongst the Candidates
The process ofvoting for a candidate involves selecting an individual who best matches a personal system of values and beliefs. Typically, voters must select a candidate whom they...
Justin Donaldson, William R. Hazlewood
ICMCS
2005
IEEE
103views Multimedia» more  ICMCS 2005»
14 years 1 months ago
Embedded Key-Frame Extraction for CG Animation by Frame Decimation
This paper proposes a method for key-frame selection of captured motion data. In many cases, it is desirable to obtain a compact representation of the human motion. Key-framing is...
Shiyu Li, Masahiro Okuda, Shinichi Takahashi
IBPRIA
2005
Springer
14 years 1 months ago
A Learning Framework for Object Recognition on Image Understanding
Abstract. In this paper an object learning system for image understanding is proposed. The knowledge acquisition system is designed as a supervised learning task, which emphasises ...
Xavier Muñoz, Anna Bosch, Joan Martí...