Sciweavers

3005 search results - page 254 / 601
» Maximum-Likelihood Image Matching
Sort
View
152
Voted
MM
2010
ACM
208views Multimedia» more  MM 2010»
15 years 4 months ago
A new approach to cross-modal multimedia retrieval
The problem of joint modeling the text and image components of multimedia documents is studied. The text component is represented as a sample from a hidden topic model, learned wi...
Nikhil Rasiwasia, Jose Costa Pereira, Emanuele Cov...
CGF
1998
110views more  CGF 1998»
15 years 4 months ago
Optical Flow Rendering
This paper proposes a new approach to image-based rendering that generates an image viewed from an arbitrary camera position and orientation by rendering optical flows extracted ...
Tae-Joon Park, Seungyong Lee, Sung Yong Shin
ICCV
2005
IEEE
16 years 6 months ago
Fixed Point Probability Field for Complex Occlusion Handling
In this paper, we show that in a multi-camera context, we can effectively handle occlusions in real-time at each frame independently, even when the only available data comes from ...
François Fleuret, Pascal Fua, Richard Lenga...
IROS
2009
IEEE
136views Robotics» more  IROS 2009»
15 years 11 months ago
Self-location from monocular uncalibrated vision using reference omniviews
— In this paper we present a novel approach to perform indoor self-localization using reference omnidirectional images. We only need one omnidirectional image of the whole scene ...
Luis Puig, José Jesús Guerrero
FGR
2002
IEEE
178views Biometrics» more  FGR 2002»
15 years 9 months ago
Eigen Light-Fields and Face Recognition Across Pose
In many face recognition tasks the pose of the probe and gallery images are different. In other cases multiple gallery or probe images may be available, each captured from a diffe...
Ralph Gross, Iain Matthews, Simon Baker