Sciweavers

Share
warning: Creating default object from empty value in /var/www/modules/taxonomy/taxonomy.module on line 1416.
PAMI
2002
150views more  PAMI 2002»
10 years 4 months ago
Object Tracking with Bayesian Estimation of Dynamic Layer Representations
Decomposing video frames into coherent two-dimensional motion layers is a powerful method for representing videos. Such a representation provides an intermediate description that e...
Hai Tao, Harpreet S. Sawhney, Rakesh Kumar
MM
2006
ACM
221views Multimedia» more  MM 2006»
10 years 10 months ago
Video object segmentation by motion-based sequential feature clustering
Segmentation of video foreground objects from background has many important applications, such as human computer interaction, video compression, multimedia content editing and man...
Mei Han, Wei Xu, Yihong Gong
ICPR
2006
IEEE
11 years 5 months ago
Robust Segmentation of Hidden Layers in Video Sequences
In this paper, we propose a novel and robust method for extracting motion layers in video sequences. Taking advantage of temporal continuity, our framework considers both the visi...
Romain Dupont, Olivier Juan, Renaud Keriven
ICIP
2003
IEEE
11 years 6 months ago
Highly scalable video compression with scalable motion coding
A scalable video coder cannot be equally efficient over a wide range of bit-rates unless both the video data and the motion information are scalable. We propose a wavelet-based, h...
Andrew Secker, David Taubman
ICIP
2004
IEEE
11 years 6 months ago
Layered motion estimation and coding for fully scalable 3d wavelet video coding
This paper proposes a framework of scalable motion estimation and coding with the structure of multi-layers for 3D wavelet video coding. The motion representation consists of mult...
Ruiqin Xiong, Jizheng Xu, Feng Wu, Shipeng Li, Ya-...
CVPR
2003
IEEE
1110views Computer Vision» more  CVPR 2003»
11 years 6 months ago
Motion Segmentation with Accurate Boundaries - A Tensor Voting Approach
Producing an accurate motion flow field is very difficult at motion boundaries. We present a novel, noniterative approach for segmentation from image motion, based on two voting p...
Gérard G. Medioni, Mircea Nicolescu
books