Sciweavers

323 search results - page 42 / 65
» Learning nonsingular phylogenies and hidden Markov models
Sort
View
ACL
2010
13 years 6 months ago
Minimized Models and Grammar-Informed Initialization for Supertagging with Highly Ambiguous Lexicons
We combine two complementary ideas for learning supertaggers from highly ambiguous lexicons: grammar-informed tag transitions and models minimized via integer programming. Each st...
Sujith Ravi, Jason Baldridge, Kevin Knight
ICVGIP
2004
13 years 10 months ago
Multi-Cue Exemplar-Based Nonparametric Model for Gesture Recognition
This paper presents an approach for a multi-cue, viewbased recognition of gestures. We describe an exemplarbased technique that combines two different forms of exemplars - shape e...
Vinay D. Shet, V. Shiv Naga Prasad, Ahmed M. Elgam...
CIVR
2008
Springer
207views Image Analysis» more  CIVR 2008»
13 years 10 months ago
Accumulated motion energy fields estimation and representation for semantic event detection
In this paper, a motion-based approach for detecting highlevel semantic events in video sequences is presented. Its main characteristic is its generic nature, i.e. it can be direc...
Georgios Th. Papadopoulos, Vasileios Mezaris, Ioan...
INTERSPEECH
2010
13 years 3 months ago
Boosted mixture learning of Gaussian mixture HMMs for speech recognition
In this paper, we propose a novel boosted mixture learning (BML) framework for Gaussian mixture HMMs in speech recognition. BML is an incremental method to learn mixture models fo...
Jun Du, Yu Hu, Hui Jiang
FOCI
2007
IEEE
14 years 2 months ago
Almost All Learning Machines are Singular
— A learning machine is called singular if its Fisher information matrix is singular. Almost all learning machines used in information processing are singular, for example, layer...
Sumio Watanabe