Sciweavers

ICMCS
2008
IEEE
144views Multimedia» more  ICMCS 2008»
13 years 11 months ago
Enabling access to sound archives through integration, enrichment and retrieval
Many digital sound archives still suffer from tremendous problems concerning access. Materials are often in different formats, with related media in separate collections, and with...
Ivan Damnjanovic, Josh Reiss, Dan Barry
ICMCS
2008
IEEE
159views Multimedia» more  ICMCS 2008»
13 years 11 months ago
Using graphics devices in reverse: GPU-based Image Processing and Computer Vision
Graphics and vision are approximate inverses of each other: ordinarily Graphics Processing Units (GPUs) are used to convert “numbers into pictures” (i.e. computer graphics). I...
James Fung, Steve Mann
ICMCS
2008
IEEE
128views Multimedia» more  ICMCS 2008»
13 years 11 months ago
Manipulating image patches for compression
We consider how to exploit the correlation in image for compression by virtue of studying image patches in a nonparametric manner. Instead of extracting and recording parameters, ...
Dong Liu, Xiaoyan Sun, Feng Wu
ICMCS
2008
IEEE
115views Multimedia» more  ICMCS 2008»
13 years 11 months ago
Spatial pyramid mining for logo detection in natural scenes
This work introduces a novel data mining scheme, spatial pyramid mining, to discover association rules at multiple resolutions in order to identify frequent spatial configuration...
Jim Kleban, Xing Xie, Wei-Ying Ma
ICMCS
2008
IEEE
138views Multimedia» more  ICMCS 2008»
13 years 11 months ago
Single-loop decoding for multiview video coding
Multiview video coding (MVC) is currently being standardized by the Joint Video Team as an extension of H264/AVC. When an MVC bitstream is decoded, some views (named target views)...
Ying Chen, Ye-Kui Wang, Miska M. Hannuksela, Monce...
ICMCS
2008
IEEE
151views Multimedia» more  ICMCS 2008»
13 years 11 months ago
Fast keyword detection with sparse time-frequency models
We address the problem of keyword spotting in continuous speech streams when training and testing conditions can be different. We propose a keyword spotting algorithm based on spa...
Effrosini Kokiopoulou, Pascal Frossard, Olivier Ve...
ICMCS
2008
IEEE
207views Multimedia» more  ICMCS 2008»
13 years 11 months ago
Structure learning in a Bayesian network-based video indexing framework
Several stochastic models provide an effective framework to identify the temporal structure of audiovisual data. Most of them need as input a first video structure, i.e. connecti...
Siwar Baghdadi, Guillaume Gravier, Claire-Hé...
ICMCS
2008
IEEE
184views Multimedia» more  ICMCS 2008»
13 years 11 months ago
Accompaniment separation and karaoke application based on automatic melody transcription
We propose a method for separating accompaniment from polyphonic music and its karaoke application, both based on automatic melody transcription. First, the method transcribes the...
Matti Ryynänen, Tuomas Virtanen, Jouni Paulus...
ICMCS
2008
IEEE
160views Multimedia» more  ICMCS 2008»
13 years 11 months ago
A study of image-based music composition
Visual and auditory forms have some noticeable associations that can inspire similar cognitive and aesthetical experiences. This paper presents a study on the possibilities of app...
Xiaoying Wu, Ze-Nian Li
ICMCS
2008
IEEE
123views Multimedia» more  ICMCS 2008»
13 years 11 months ago
Enhancement of visual contrast in fluorescence endoscopy
Thomas Stehle, Alexander Behrens, Til Aach