Sciweavers

413 search results - page 40 / 83
» Information matrix for hidden Markov models with covariates
Sort
View
ICIP
2009
IEEE
16 years 1 days ago
Combining Multimodal And Temporal Contextual Information For Semantic Video Analysis
In this paper, a graphical modeling-based approach to semantic video analysis is presented for jointly realizing modality fusion and temporal context exploitation. Overall, the ex...
COLING
2008
15 years 13 days ago
Weakly Supervised Supertagging with Grammar-Informed Initialization
Much previous work has investigated weak supervision with HMMs and tag dictionaries for part-of-speech tagging, but there have been no similar investigations for the harder proble...
Jason Baldridge
ICNC
2005
Springer
15 years 4 months ago
Texture Segmentation Using Neural Networks and Multi-scale Wavelet Features
This paper presents a novel texture segmentation method using Bayesian estimation and neural networks. Multi-scale wavelet coefficients and the context information extracted from n...
Tae-Hyung Kim, Il Kyu Eom, Yoo Shin Kim
FGR
2011
IEEE
267views Biometrics» more  FGR 2011»
14 years 2 months ago
A dynamic approach to the recognition of 3D facial expressions and their temporal models
— In this paper we propose a method that exploits 3D motion-based features between frames of 3D facial geometry sequences for dynamic facial expression recognition. An expressive...
Georgia Sandbach, Stefanos Zafeiriou, Maja Pantic,...
ICMLA
2009
14 years 8 months ago
Structured Prediction Models for Chord Transcription of Music Audio
Chord sequences are a compact and useful description of music, representing each beat or measure in terms of a likely distribution over individual notes without specifying the not...
Adrian Weller, Daniel P. W. Ellis, Tony Jebara