Sciweavers

2925 search results - page 374 / 585
» Input Modeling Using Quantile Statistical Methods
Sort
View
ICML
2006
IEEE
16 years 1 months ago
Nightmare at test time: robust learning by feature deletion
When constructing a classifier from labeled data, it is important not to assign too much weight to any single input feature, in order to increase the robustness of the classifier....
Amir Globerson, Sam T. Roweis
121
Voted
ISBI
2006
IEEE
16 years 1 months ago
Sketch initialized Snakes for rapid, accurate and repeatable interactive medical image segmentation
We combine a pen and pressure-sensitive tablet input device, and a sketch-based user initialization process, with a general subdivisioncurve Snake to create an intuitive, fast, ac...
Tim McInerney, M. Reza Akhavan Sharif
101
Voted
ECCV
2004
Springer
16 years 2 months ago
Synthesizing Dynamic Texture with Closed-Loop Linear Dynamic System
Dynamic texture can be defined as a temporally continuous and infinitely varying stream of images that exhibit certain temporal statistics. Linear dynamic system (LDS) represented ...
Lu Yuan, Fang Wen, Ce Liu, Heung-Yeung Shum
CVPR
1998
IEEE
16 years 2 months ago
Action Recognition Using Probabilistic Parsing
A new approach to the recognition of temporal behaviors and activities is presented. The fundamental idea, inspired by work in speech recognition, is to divide the inference probl...
Aaron F. Bobick, Yuri A. Ivanov
130
Voted
ECCV
2008
Springer
16 years 2 months ago
Segmentation and Recognition Using Structure from Motion Point Clouds
We propose an algorithm for semantic segmentation based on 3D point clouds derived from ego-motion. We motivate five simple cues designed to model specific patterns of motion and 3...
Gabriel J. Brostow, Jamie Shotton, Julien Fauqueur...