Sciweavers

737 search results - page 72 / 148
» A General Model for Multiple View Unsupervised Learning
Sort
View
CORR
2008
Springer
107views Education» more  CORR 2008»
13 years 9 months ago
A Spectral Algorithm for Learning Hidden Markov Models
Hidden Markov Models (HMMs) are one of the most fundamental and widely used statistical tools for modeling discrete time series. In general, learning HMMs from data is computation...
Daniel Hsu, Sham M. Kakade, Tong Zhang
MM
2010
ACM
336views Multimedia» more  MM 2010»
13 years 9 months ago
Movie genre classification via scene categorization
This paper presents a method for movie genre categorization of movie trailers, based on scene categorization. We view our approach as a step forward from using only low-level visu...
Howard Zhou, Tucker Hermans, Asmita V. Karandikar,...
CVIU
2008
179views more  CVIU 2008»
13 years 9 months ago
Incremental, scalable tracking of objects inter camera
This paper presents a scalable solution to the problem of tracking objects across spatially separated, uncalibrated cameras with non overlapping fields of view. The approach relie...
Andrew Gilbert, Richard Bowden
ICB
2007
Springer
280views Biometrics» more  ICB 2007»
14 years 3 months ago
3D Model-Based Face Recognition in Video
Face recognition in video has gained wide attention due to its role in designing surveillance systems. One of the main advantages of video over still frames is that evidence accumu...
Unsang Park, Anil K. Jain
ICASSP
2011
IEEE
13 years 22 days ago
Multi-view and multi-objective semi-supervised learning for large vocabulary continuous speech recognition
Current hidden Markov acoustic modeling for large vocabulary continuous speech recognition (LVCSR) relies on the availability of abundant labeled transcriptions. Given that speech...
Xiaodong Cui, Jing Huang, Jen-Tzung Chien