1243 search results - page 60 / 249 » Reduced-Rank Hidden Markov Models |
NAACL
2007
15 years 6 months ago
2007
Letter-to-phoneme conversion generally requires aligned training data of letters and phonemes. Typically, the alignments are limited to one-to-one alignments. We present a novel t...
221
click to vote
IPCV
2010
15 years 2 months ago
2010
In this paper, we discuss usage of a multi-stage Residual Vector Quantization (RVQ) strategy for human action recognition. To the best of our knowledge, this is the first reported...
140
click to vote
CVPR
2006
IEEE
16 years 6 months ago
2006
IEEE
We consider the problem of computing the likelihood of a gesture from regular, unaided video sequences, without relying on perfect segmentation of the scene. Instead of requiring ...
122
click to vote
ICIP
2004
IEEE
16 years 6 months ago
2004
IEEE
In this paper we present a coherent approach using the hierarchical HMM with shared structures to extract the structural units that form the building blocks of an education/traini...