786 search results - page 79 / 158 » FeatureMapper: mapping features to models |
107
Voted
MM
2010
ACM
15 years 20 days ago
2010
ACM
This paper presents a method for movie genre categorization of movie trailers, based on scene categorization. We view our approach as a step forward from using only low-level visu...
89
Voted
ICIP
2000
IEEE
16 years 2 months ago
2000
IEEE
The use of visual information from lip movements can improve the accuracy and robustness of a speech recognition system. Accurate extraction of visual features associated with the...
95
Voted
APCSAC
2005
IEEE
15 years 6 months ago
2005
IEEE
Multimedia devices demands a platform integrated various functional modules and an increasing support of multiple standards. Stream architecture is able to solve the problem. Howev...
101
click to vote
DATE
2005
IEEE
15 years 6 months ago
2005
IEEE
This paper explores methods for hardware acceleration of Hidden Markov Model (HMM) decoding for the detection of persons in still images. Our architecture exploits the inherent st...
159
click to vote
PAMI
2010
14 years 11 months ago
2010
The notion of using context information for solving high-level vision and medical image segmentation problems has been increasingly realized in the field. However, how to learn a...