Sciweavers

ICCV
2003
IEEE
14 years 11 months ago
Recognizing Action at a Distance
Alexei A. Efros, Alexander C. Berg, Greg Mori, Jit...
ICCV
2003
IEEE
14 years 11 months ago
Controlling Model Complexity in Flow Estimation
This paper describes a novel application of Statistical Learning Theory (SLT) to control model complexity in flow estimation. SLT provides analytical generalization bounds suitabl...
Zoran Duric, Fayin Li, Harry Wechsler, Vladimir Ch...
ICCV
2003
IEEE
14 years 11 months ago
Shape Representation via Harmonic Embedding
We present a novel representation of shape for closed planar contours explicitly designed to possess a linear structure. This greatly simplifies linear operations such as averagin...
Alessandro Duci, Anthony J. Yezzi, Sanjoy K. Mitte...
ICCV
2003
IEEE
14 years 11 months ago
A Multi-scale Generative Model for Animate Shapes and Parts
This paper presents a multi-scale generative model for representing animate shapes and extracting meaningful parts of objects. The model assumes that animate shapes (2D simple clo...
Aleksandr Dubinskiy, Song Chun Zhu
ICCV
2003
IEEE
14 years 11 months ago
Real-Time Simultaneous Localisation and Mapping with a Single Camera
Ego-motion estimation for an agile single camera moving through general, unknown scenes becomes a much more challenging problem when real-time performance is required rather than ...
Andrew J. Davison
ICCV
2003
IEEE
14 years 11 months ago
Constraining Human Body Tracking
Our paper addresses the problem of enforcing constraints in human body tracking. A projection technique is derived to impose kinematic constraints on independent multi-body motion...
David Demirdjian, Teresa Ko, Trevor Darrell
ICCV
2003
IEEE
14 years 11 months ago
Recognizing Human Action Efforts: An Adaptive Three-Mode PCA Framework
We present a computational framework capable of labeling the effort of an action corresponding to the perceived level of exertion by the performer (low ? high). The approach initi...
James W. Davis, Hui Gao
ICCV
2003
IEEE
14 years 11 months ago
Gaze Manipulation for One-to-one Teleconferencing
A new algorithm is proposed for novel view generation in one-toone teleconferencing applications. Given the video streams acquired by two cameras placed on either side of a comput...
Antonio Criminisi, Jamie Shotton, Andrew Blake, Ph...
ICCV
2003
IEEE
14 years 11 months ago
Variational Space-Time Motion Segmentation
Daniel Cremers, Stefano Soatto