Sciweavers

1091 search results - page 74 / 219
» Visibility-based feature extraction from discrete models
Sort
View
ICASSP
2010
IEEE
14 years 10 months ago
Boosted binary features for noise-robust speaker verification
The standard approach to speaker verification is to extract cepstral features from the speech spectrum and model them by generative or discriminative techniques. We propose a nov...
Anindya Roy, Mathew Magimai-Doss, Sébastien...
3DPVT
2006
IEEE
186views Visualization» more  3DPVT 2006»
15 years 3 months ago
Range Image Registration Based on Circular Features
Range sensing technology allows the photo-realistic modeling of large-scale scenes, such as urban structures. A major bottleneck in the process of 3D scene acquisition is the auto...
Cecilia Chao Chen, Ioannis Stamos
MM
2006
ACM
221views Multimedia» more  MM 2006»
15 years 3 months ago
Video object segmentation by motion-based sequential feature clustering
Segmentation of video foreground objects from background has many important applications, such as human computer interaction, video compression, multimedia content editing and man...
Mei Han, Wei Xu, Yihong Gong
ICCV
2011
IEEE
13 years 9 months ago
Manhattan Scene Understanding Using Monocular, Stereo, and 3D Features
This paper addresses scene understanding in the context of a moving camera, integrating semantic reasoning ideas from monocular vision with 3D information available through struct...
Alex Flint, David Murray, Ian Reid
PAMI
2007
92views more  PAMI 2007»
14 years 9 months ago
Modeling and Predicting Face Recognition System Performance Based on Analysis of Similarity Scores
—This paper presents methods of modeling and predicting face recognition (FR) system performance based on analysis of similarity scores. We define the performance of an FR system...
Peng Wang, Qiang Ji, James L. Wayman