Sciweavers

1546 search results - page 211 / 310
» Computing Pose Sequences Directly from Videos
Sort
View
FGR
2011
IEEE
271views Biometrics» more  FGR 2011»
13 years 9 days ago
Active conditional models
— Matching images with large geometric and iconic changes (e.g. faces under different poses and facial expressions) is an open research problem in computer vision. There are two ...
Ying Chen, Fernando De la Torre
CVPR
2008
IEEE
14 years 11 months ago
Learning human actions via information maximization
In this paper, we present a novel approach for automatically learning a compact and yet discriminative appearance-based human action model. A video sequence is represented by a ba...
Jingen Liu, Mubarak Shah
ICCV
2003
IEEE
14 years 10 months ago
Fusion of Static and Dynamic Body Biometrics for Gait Recognition
Human identification at a distance has recently gained growing interest from computer vision researchers. This paper aims to propose a visual recognition algorithm based upon fusi...
Liang Wang, Huazhong Ning, Tieniu Tan, Weiming Hu
CRV
2006
IEEE
148views Robotics» more  CRV 2006»
14 years 17 days ago
Robust SSD tracking with incremental 3D structure estimation
While the geometric aspects of structure and motion estimation from uncalibrated images are well understood, and it has great promise in applications, it has not seen widespread u...
Adam Rachmielowski, Dana Cobzas, Martin Jäger...
ICMCS
2009
IEEE
136views Multimedia» more  ICMCS 2009»
13 years 6 months ago
Single-iteration full-search fractional motion estimation for quad full HD H.264/AVC encoding
Fractional motion estimation (FME) is widely used in video compression standards. In H.264/AVC, the precision of motion vector is down to quarter pixels to improve the coding effi...
Pei-Kuei Tsung, Wei-Yin Chen, Li-Fu Ding, Chuan-Yu...