Sciweavers

128 search results - page 15 / 26
» Conditional random fields for activity recognition
Sort
View
NAACL
2007
13 years 9 months ago
Joint Versus Independent Phonological Feature Models within CRF Phone Recognition
We compare the effect of joint modeling of phonological features to independent feature detectors in a Conditional Random Fields framework. Joint modeling of features is achieved ...
Ilana Bromberg, Jeremy Morris, Eric Fosler-Lussier
CVPR
2012
IEEE
11 years 10 months ago
Top-down and bottom-up cues for scene text recognition
Scene text recognition has gained significant attention from the computer vision community in recent years. Recognizing such text is a challenging problem, even more so than the ...
Anand Mishra, Karteek Alahari, C. V. Jawahar
CVPR
2007
IEEE
14 years 9 months ago
Contextual Identity Recognition in Personal Photo Albums
We present an efficient probabilistic method for identity recognition in personal photo albums. Personal photos are usually taken under uncontrolled conditions ? the captured face...
Dragomir Anguelov, Kuang-chih Lee, Salih Burak G&o...
AAAI
2008
13 years 10 months ago
Hidden Dynamic Probabilistic Models for Labeling Sequence Data
We propose a new discriminative framework, namely Hidden Dynamic Conditional Random Fields (HDCRFs), for building probabilistic models which can capture both internal and external...
Xiaofeng Yu, Wai Lam
ICASSP
2011
IEEE
12 years 11 months ago
MLP based phoneme detectors for Automatic Speech Recognition
Phoneme posterior probabilities estimated using Multi-Layer Perceptrons (MLPs) are extensively used both as acoustic scores and features for speech recognition. In this paper we e...
Samuel Thomas, Patrick Nguyen, Geoffrey Zweig, Hyn...