Sciweavers

45 search results - page 1 / 9
» Using Semantic Features for Scene Classification: how Good d...
Sort
View
ICMCS
2006
IEEE
182views Multimedia» more  ICMCS 2006»
13 years 11 months ago
Using Semantic Features for Scene Classification: how Good do they Need to Be?
Semantic scene classification is a useful, yet challenging problem in image understanding. Most existing systems are based on low-level features, such as color or texture, and suc...
Matthew R. Boutell, Anustup Choudhury, Jiebo Luo, ...
ICASSP
2011
IEEE
12 years 8 months ago
Continuous F0 in the source-excitation generation for HMM-based TTS: Do we need voiced/unvoiced classification?
Most HMM-based TTS systems use a hard voiced/unvoiced classification to produce a discontinuous F0 signal which is used for the generation of the source-excitation. When a mixed ...
Javier Latorre, Mark J. F. Gales, Sabine Buchholz,...
MM
2009
ACM
245views Multimedia» more  MM 2009»
13 years 11 months ago
Concept detectors: how good is good enough?
Today, semantic concept based video retrieval systems often show insufficient performance for real-life applications. Clearly, a big share of the reason is the lacking performance...
Robin Aly, Djoerd Hiemstra
ICPR
2010
IEEE
13 years 2 months ago
Low-Level Image Segmentation Based Scene Classification
This paper is aimed at evaluating the semantic information content of multiscale, low-level image segmentation. As a method of doing this, we use selected features of segmentation...
Emre Akbas, Narendra Ahuja
BMVC
2010
13 years 2 months ago
Improving object classification using semantic attributes
This paper shows how semantic attribute features can be used to improve object classification performance. The semantic attributes used fall into five groups: scene (e.g. `road�...
Yu Su, Moray Allan, Frédéric Jurie