Sciweavers

597 search results - page 30 / 120
» Scalable, updatable predictive models for sequence data
Sort
View
CVPR
2004
IEEE
14 years 11 months ago
Accurate Face Models from Uncalibrated and Ill-Lit Video Sequences
In this paper, we propose a face reconstruction technique that produces models that not only look good when texture mapped, but are also metrically accurate. Our method is designe...
Miodrag Dimitrijevic, Slobodan Ilic, Pascal Fua
ICML
2007
IEEE
14 years 9 months ago
Simple, robust, scalable semi-supervised learning via expectation regularization
Although semi-supervised learning has been an active area of research, its use in deployed applications is still relatively rare because the methods are often difficult to impleme...
Gideon S. Mann, Andrew McCallum
MVA
2008
125views Computer Vision» more  MVA 2008»
13 years 9 months ago
Pearson-based mixture model for color object tracking
To track objects in video sequences, many studies have been done to characterize the target with respect to its color distribution. Most often, the Gaussian Mixture Model (GMM) is ...
William Ketchantang, Stéphane Derrode, Lion...
ISCAS
2006
IEEE
96views Hardware» more  ISCAS 2006»
14 years 3 months ago
Frame-level data reuse for motion-compensated temporal filtering
— Motion-compensated temporal filtering (MCTF) is an open-loop prediction scheme, so the frame-level data reuse for MCTF is possible. In this paper, we propose two general frame...
Ching-Yeh Chen, Yi-Hau Chen, Chih-Chi Cheng, Liang...
ICRA
2007
IEEE
114views Robotics» more  ICRA 2007»
14 years 3 months ago
Generating Traffic Statistical Profiles Using Unmanned Helicopter-Based Video Data
: Small unmanned vertical take off and landing vehicles are used to provide the eye-in-the-sky alternative to monitoring and regulating traffic dynamically. Spatial-temporal visual...
Anuj Puri, Kimon P. Valavanis, Michael Kontitsis