482 search results - page 6 / 97 » Semi-Markov Models for Sequence Segmentation |
147
Voted
IJCNN
2000
IEEE
15 years 7 months ago
2000
IEEE
This paper presents an unsupervised segmentation method for feature sequences based on competitivelearning hidden Markov models. Models associated with the nodes of the Self-Organ...
146
Voted
ECCV
1992
Springer
16 years 5 months ago
1992
Springer
This paper presents a method for incrementally segmenting images over time using both intensity and motion information. This is done by formulating a model of physically signi cant...
150
Voted
ICML
2001
IEEE
16 years 4 months ago
2001
IEEE
We present conditional random fields, a framework for building probabilistic models to segment and label sequence data. Conditional random fields offer several advantages over hid...
132
Voted
CVPR
1998
IEEE
16 years 5 months ago
1998
IEEE
Stereo sequences promise to be a powerful method for segmenting images for applications such as tracking human figures. We present a method of statistical background modeling for ...
136
Voted
ICIP
2005
IEEE
16 years 5 months ago
2005
IEEE
In this paper we explore the problem of accurately segmenting a person from a video given only approximate location of that person. Unlike previous work which assumes that the app...