Sciweavers

27 search results - page 3 / 6
» Using quasi-continuous histograms for fuzzy main motion esti...
Sort
View
TCSV
2008
291views more  TCSV 2008»
13 years 7 months ago
A Statistical Video Content Recognition Method Using Invariant Features on Object Trajectories
Abstract--This work is dedicated to a statistical trajectorybased approach addressing two issues related to dynamic video content understanding: recognition of events and detection...
Alexandre Hervieu, Patrick Bouthemy, Jean-Pierre L...
ICIP
2001
IEEE
14 years 8 months ago
Metrics for performance evaluation of video object segmentation and tracking without ground-truth
We present metrics to evaluate the performance of video object segmentation and tracking methods quantitatively when groundtruth segmentation maps are not available. The proposed ...
Çigdem Eroglu Erdem, Bülent Sankur, A....
ICIAR
2009
Springer
13 years 4 months ago
3D Human Pose Estimation from Static Images Using Local Features and Discriminative Learning
In this paper an approach to recover the 3D human body pose from static images is proposed. We adopt a discriminative learning technique to directly infer the 3D pose from appearan...
Suman Sedai, Farid Flitti, Mohammed Bennamoun, Du ...
ICIP
1999
IEEE
14 years 8 months ago
Long-Term Memory Prediction Using Affine Motion Compensation
Long-term memory prediction extends motion compensation from the previous frame to several past frames with the result of increased coding efficiency. In this paper we demonstrate...
Thomas Wiegand, Eckehard G. Steinbach, Bernd Girod
ICIP
2003
IEEE
14 years 8 months ago
Navigating in Manhattan: 3D orientation from video without correspondences
The problem of inferring 3D orientation of a camera from video sequences has been mostly addressed by first computing correspondences of image features. This intermediate step is ...
André F. T. Martins, Mário A. T. Fig...