Sciweavers

ICASSP
2011
IEEE
13 years 3 months ago
Spatially consistent view synthesis with coordinate alignment
In this paper, we propose a novel method that uses coordinate alignment and background pixel extraction to synthesize highly accurate and spatially consistent intermediate views f...
Lam C. Tran, Ramsin Khoshabeh, Ankit K. Jain, Chri...
ICASSP
2011
IEEE
13 years 3 months ago
L0 sparse graphical modeling
Graphical models are well established in providing compact conditional probability descriptions of complex multivariable interactions. In the Gaussian case, graphical models are d...
Goran Marjanovic, Victor Solo
ICASSP
2011
IEEE
13 years 3 months ago
USPACOR: Universal sparsity-controlling outlier rejection
The recent upsurge of research toward compressive sampling and parsimonious signal representations hinges on signals being sparse, either naturally, or, after projecting them on a...
Georgios B. Giannakis, Gonzalo Mateos, Shahrokh Fa...
ICASSP
2011
IEEE
13 years 3 months ago
Scalable robust hypothesis tests using graphical models
Traditional binary hypothesis testing relies on the precise knowledge of the probability density of an observed random vector conditioned on each hypothesis. However, for many app...
Divyanshu Vats, Vishal Monga, Umamahesh Srinivas, ...
ICASSP
2011
IEEE
13 years 3 months ago
An atlas-based deep brain structure segmentation method: from coarse positioning to fine shaping
Segmentation of deep brain structures is a challenging task for MRI images due to blurry structure boundaries, small object size and irregular shapes. In this paper, we present a ...
Yishan Luo, Albert C. S. Chung
ICASSP
2011
IEEE
13 years 3 months ago
Rapid image retrieval for mobile location recognition
Recognizing the location and orientation of a mobile device from captured images is a promising application of image retrieval algorithms. Matching the query images to an existing...
Georg Schroth, Anas Al-Nuaimi, Robert Huitl, Flori...
ICASSP
2011
IEEE
13 years 3 months ago
A hierarchical static-dynamic framework for emotion classification
The goal of emotion classification is to estimate an emotion label, given representative data and discriminative features. Humans are very good at deriving high-level representat...
Emily Mower, Shrikanth Narayanan
ICASSP
2011
IEEE
13 years 3 months ago
The IBM 2009 GALE Arabic speech transcription system
We describe the Arabic broadcast transcription system elded by IBM in the GALE Phase 4 machine translation evaluation. Key advances over our Phase 3.5 system include improvements ...
Brian Kingsbury, Hagen Soltau, George Saon, Stephe...
ICASSP
2011
IEEE
13 years 3 months ago
Region-adaptive probability model selection for the arithmetic coding of video texture
In video coding systems using adaptive arithmetic coding to compress texture information, the employed symbol probability models need to be retrained every time the coding process...
Kenneth Vermeirsch, Joeri Barbarien, Peter Lambert...
ICASSP
2011
IEEE
13 years 3 months ago
Rotation invariant feature extraction from 3-D acceleration signals
In this paper, we propose a method to extract features from three-dimensional acceleration signals. The proposed method is based on the (auto-)correlation matrix of Fourier transf...
Takumi Kobayashi, Kôiti Hasida, Nobuyuki Ots...