Sciweavers

1585 search results - page 34 / 317
» Using a Non-prior Training Active Feature Model
Sort
View
ISVC
2007
Springer
15 years 8 months ago
Robust Infants Face Tracking Using Active Appearance Models: A Mixed-State CONDENSATION Approach
Abstract. In this paper a new extension of the CONDENSATION algorithm, with application to infants face tracking, will be introduced. In this work we address the problem of trackin...
Luigi Bagnato, Matteo Sorci, Gianluca Antonini, Gi...
SIGIR
2008
ACM
15 years 1 months ago
Learning from labeled features using generalized expectation criteria
It is difficult to apply machine learning to new domains because often we lack labeled problem instances. In this paper, we provide a solution to this problem that leverages domai...
Gregory Druck, Gideon S. Mann, Andrew McCallum
JMM2
2006
219views more  JMM2 2006»
15 years 1 months ago
Fully Automatic Real-Time 3D Object Tracking using Active Contour and Appearance Models
This paper presents an efficient, robust and fully automatic real-time system for 3D object pose tracking in image sequences. The developed application integrates two main componen...
Giorgio Panin, Alois Knoll
112
Voted
ICIAP
2001
Springer
16 years 2 months ago
Lip Detection and Tracking
We present a model for the lips using the Active Shape Model (ASM) based on B?ezier Curves which can capture the dynamics of the lips efficiently. The curves are defined only by a...
Alice Caplier
122
Voted
IJRR
2007
186views more  IJRR 2007»
15 years 1 months ago
Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields
Learning patterns of human behavior from sensor data is extremely important for high-level activity inference. We show how to extract a person’s activities and significant plac...
Lin Liao, Dieter Fox, Henry A. Kautz