Sciweavers

3951 search results - page 610 / 791
» Automatic amortized analysis
Sort
View
MM
2009
ACM
269views Multimedia» more  MM 2009»
16 years 1 months ago
Semi-supervised topic modeling for image annotation
We propose a novel technique for semi-supervised image annotation which introduces a harmonic regularizer based on the graph Laplacian of the data into the probabilistic semantic ...
Yuanlong Shao, Yuan Zhou, Xiaofei He, Deng Cai, Hu...
MM
2009
ACM
125views Multimedia» more  MM 2009»
16 years 1 months ago
Unfolding speaker clustering potential: a biomimetic approach
Speaker clustering is the task of grouping a set of speech utterances into speaker-specific classes. The basic techniques for solving this task are similar to those used for spea...
Thilo Stadelmann, Bernd Freisleben
MM
2009
ACM
142views Multimedia» more  MM 2009»
16 years 1 months ago
Investigating the use of visual focus of attention for audio-visual speaker diarisation
Audio-visual speaker diarisation is the task of estimating “who spoke when” using audio and visual cues. In this paper we propose the combination of an audio diarisation syste...
Giulia Garau, Sileye O. Ba, Hervé Bourlard,...
MM
2009
ACM
169views Multimedia» more  MM 2009»
16 years 1 months ago
Visual speaker localization aided by acoustic models
The following paper presents a novel audio-visual approach for unsupervised speaker locationing. Using recordings from a single, low-resolution room overview camera and a single f...
Gerald Friedland, Chuohao Yeo, Hayley Hung
MM
2009
ACM
138views Multimedia» more  MM 2009»
16 years 1 months ago
WOW: wild-open warning for broadcast basketball video based on player trajectory
In basketball games, wild-open means that there is an offensive player not well defended by his/her opponents. The occurrence of wild-open usually implies the existence of a succe...
Ming-Hsiu Chang, Ming-Chun Tien, Ja-Ling Wu