Sciweavers

2038 search results - page 100 / 408
» Improvements to the Psi-SSA representation
Sort
View
NAACL
2010
14 years 11 months ago
Investigations into the Crandem Approach to Word Recognition
We suggest improvements to a previously proposed framework for integrating Conditional Random Fields and Hidden Markov Models, dubbed a Crandem system (2009). The previous authors...
Rohit Prabhavalkar, Preethi Jyothi, William Hartma...
COLING
2010
14 years 8 months ago
Enhancing Multi-lingual Information Extraction via Cross-Media Inference and Fusion
We describe a new information fusion approach to integrate facts extracted from cross-media objects (videos and texts) into a coherent common representation including multi-level ...
Adam Lee, Marissa Passantino, Heng Ji, Guojun Qi, ...
JMLR
2010
137views more  JMLR 2010»
14 years 8 months ago
HOP-MAP: Efficient Message Passing with High Order Potentials
There is a growing interest in building probabilistic models with high order potentials (HOPs), or interactions, among discrete variables. Message passing inference in such models...
Daniel Tarlow, Inmar Givoni, Richard S. Zemel
ICASSP
2011
IEEE
14 years 5 months ago
Soundtrack classification by transient events
We present a method for video classification based on information in the soundtrack. Unlike previous approaches which describe the audio via statistics of mel-frequency cepstral ...
Courtenay V. Cotton, Daniel P. W. Ellis, Alexander...
ICASSP
2011
IEEE
14 years 5 months ago
An effective foreground/background segmentation approach for bootstrapping video sequences
In this study, an effective foreground/background segmentation approach for bootstrapping video sequences is proposed. First, a modified block representation approach is used to c...
Han-Hui Hsiao, Jin-Jang Leou