Sciweavers

924 search results - page 147 / 185
» Incremental Probabilistic Inference
Sort
View
CVPR
2008
IEEE
14 years 10 months ago
What can missing correspondences tell us about 3D structure and motion?
Practically all existing approaches to structure and motion computation use only positive image correspondences to verify the camera pose hypotheses. Incorrect epipolar geometries...
Christopher Zach, Arnold Irschara, Horst Bischof
ECCV
2008
Springer
14 years 10 months ago
Robust Visual Tracking Based on an Effective Appearance Model
Most existing appearance models for visual tracking usually construct a pixel-based representation of object appearance so that they are incapable of fully capturing both global an...
Xi Li, Weiming Hu, Zhongfei Zhang, Xiaoqin Zhang
ICIP
1994
IEEE
14 years 10 months ago
Robust Optical Flow Estimation
Motion information is essential in many computer vision and video analysis tasks. Since MPEG is still one of the most prevalent formats for representing, transferring and storing ...
Sugata Ghosal, Rajiv Mehrotra
MM
2009
ACM
169views Multimedia» more  MM 2009»
14 years 3 months ago
Visual speaker localization aided by acoustic models
The following paper presents a novel audio-visual approach for unsupervised speaker locationing. Using recordings from a single, low-resolution room overview camera and a single f...
Gerald Friedland, Chuohao Yeo, Hayley Hung
ATAL
2007
Springer
14 years 2 months ago
Enacting protocols by commitment concession
Commitment protocols formalize interactions among autonomous, heterogeneous agents, leaving the agents’ local policies unspecified. This paper studies the problem of agents ena...
Pinar Yolum, Munindar P. Singh