Sciweavers

131 search results - page 3 / 27
» Improved Segmentation Based on Probabilistic Labeling
Sort
View
ICIP
2007
IEEE
14 years 6 months ago
Semantics-Based Video Indexing using a Stochastic Modeling Approach
Semantic video indexing is the first step towards automatic video retrieval and personalization. We propose a data-driven stochastic modeling approach to perform both video segmen...
Yong Wei, Suchendra M. Bhandarkar, Kang Li
ECCV
2010
Springer
13 years 10 months ago
Enhancing Interactive Image Segmentation with Automatic Label Set Augmentation
Abstract. We address the problem of having insufficient labels in an interactive image segmentation framework, for which most current methods would fail without further user inter...
ICCV
2009
IEEE
14 years 10 months ago
Label Set Perturbation for MRF based Neuroimaging Segmentation
Graph-cuts based algorithms are effective for a variety of segmentation tasks in computer vision. Ongoing research is focused toward making the algorithms even more general, as ...
Dylan Hower, Vikas Singh, Sterling C. Johnson
IJCAI
2003
13 years 6 months ago
A Learning Algorithm for Localizing People Based on Wireless Signal Strength that Uses Labeled and Unlabeled Data
This paper summarizes a probabilistic approach for localizing people through the signal strengths of a wireless IEEE 802.11b network. Our approach uses data labeled by ground trut...
Sebastian Thrun, Geoffrey J. Gordon, Frank Pfennin...
ICIP
2006
IEEE
14 years 6 months ago
Region-Based Shape Incorporation for Probabilistic Spatio-Temporal Video Object Segmentation
Embedding generic shape information into probabilistic spatiotemporal video object segmentation is of pivotal importance to achieving better segmentation, since it provides valuab...
Rakib Ahmed, Gour C. Karmakar, Laurence S. Dooley