Sciweavers

153 search results - page 23 / 31
» A New Manifold Representation for Visual Speech Recognition
Sort
View
AAAI
1993
13 years 8 months ago
Learning Object Models from Appearance
We address the problem of automatically learning object models for recognition and pose estimation. In contrast to the traditional approach, we formulate the recognition problem a...
Hiroshi Murase, Shree K. Nayar
SDM
2004
SIAM
141views Data Mining» more  SDM 2004»
13 years 9 months ago
Visually Mining through Cluster Hierarchies
Similarity search in database systems is becoming an increasingly important task in modern application domains such as multimedia, molecular biology, medical imaging, computer aid...
Stefan Brecheisen, Hans-Peter Kriegel, Peer Kr&oum...
CORR
2004
Springer
136views Education» more  CORR 2004»
13 years 7 months ago
Analysis and Visualization of Index Words from Audio Transcripts of Instructional Videos
We introduce new techniques for extracting, analyzing, and visualizing textual contents from instructional videos of low production quality. Using Automatic Speech Recognition, ap...
Alexander Haubold, John R. Kender
TSMC
2010
13 years 2 months ago
Dual Gait Generative Models for Human Motion Estimation From a Single Camera
This paper presents a general gait representation framework for video-based human motion estimation. Specifically, we want to estimate the kinematics of an unknown gait from image ...
Xin Zhang, Guoliang Fan
AIPR
2005
IEEE
14 years 1 months ago
Hyperspectral Detection Algorithms: Operational, Next Generation, on the Horizon
Abstract—The multi-band target detection algorithms implemented in hyperspectral imaging systems represent perhaps the most successful example of image fusion. A core suite of su...
A. Schaum