1585 search results - page 40 / 317 » Using a Non-prior Training Active Feature Model |
148
click to vote
MLMI
2007
Springer
15 years 10 months ago
2007
Springer
Abstract. Prosody has been actively studied as an important knowledge source for speech recognition and understanding. In this paper, we are concerned with the question of exploiti...
156
click to vote
ICIP
2007
IEEE
15 years 10 months ago
2007
IEEE
In this paper, we propose a system identification approach for group activity recognition in traffic surveillance. Statistical shape theory is used to extract features, and then...
125
click to vote
COLING
2008
15 years 5 months ago
2008
Och's (2003) minimum error rate training (MERT) procedure is the most commonly used method for training feature weights in statistical machine translation (SMT) models. The u...
145
click to vote
ECCV
2008
Springer
16 years 6 months ago
2008
Springer
Appearance features are good at discriminating activities in a fixed view, but behave poorly when aspect is changed. We describe a method to build features that are highly stable u...
123
click to vote
PERVASIVE
2004
Springer
15 years 9 months ago
2004
Springer
Abstract. In this work, algorithms are developed and evaluated to detect physical activities from data acquired using five small biaxial accelerometers worn simultaneously on di...