Sciweavers

CVPR
2009
IEEE
14 years 6 months ago
Robust shadow and illumination estimation using a mixture model
Illuminant estimation from shadows typically relies on accurate segmentation of the shadows and knowledge of exact 3D geometry, while shadow estimation is difficult in the presen...
Alexandros Panagopoulos, Dimitris Samaras, Nikos P...
CVPR
2009
IEEE
14 years 6 months ago
3D morphable face models revisited
In this paper we revisit the process of constructing a high resolution 3D morphable model of face shape variation. We demonstrate how the statistical tools of thin-plate splines a...
Ankur Patel, William A. P. Smith
CVPR
2009
IEEE
14 years 6 months ago
Trajectory parsing by cluster sampling in spatio-temporal graph
The objective of this paper is to parse object trajectories in surveillance video against occlusion, interruption, and background clutter. We present a spatio-temporal graph (ST-G...
Xiaobai Liu, Liang Lin, Song Chun Zhu, Hai Jin
CVPR
2009
IEEE
14 years 6 months ago
On compositional Image Alignment, with an application to Active Appearance Models
Efficient and accurate fitting of Active Appearance Models (AAM) is a key requirement for many applications. The most efficient fitting algorithm today is Inverse Compositiona...
Brian Amberg, Andrew Blake, Thomas Vetter
CVPR
2009
IEEE
14 years 6 months ago
Fast Mean Shift by compact density representation
Daniel Freedman, Pavel Kisilev
CVPR
2009
IEEE
14 years 6 months ago
On bias correction for geometric parameter estimation in computer vision
Maximum likelihood (ML) estimation is widely used in many computer vision problems involving the estimation of geometric parameters, from conic fitting to bundle adjustment for s...
Takayuki Okatani, Koichiro Deguchi
CVPR
2009
IEEE
14 years 6 months ago
Learning multi-modal densities on Discriminative Temporal Interaction Manifold for group activity recognition
While video-based activity analysis and recognition has received much attention, existing body of work mostly deals with single object/person case. Coordinated multi-object activi...
Ruonan Li, Rama Chellappa, Shaohua Kevin Zhou
CVPR
2009
IEEE
14 years 6 months ago
Efficient algorithms for subwindow search in object detection and localization
Senjian An, Patrick Peursum, Wanquan Liu, Svetha V...
CVPR
2009
IEEE
14 years 6 months ago
Sigma Set: A small second order statistical region descriptor
Given an image region of pixels, second order statistics can be used to construct a descriptor for object representation. One example is the covariance matrix descriptor, which sh...
Xiaopeng Hong, Hong Chang, Shiguang Shan, Xilin Ch...
CVPR
2009
IEEE
14 years 6 months ago
A 3D reconstruction pipeline for digital preservation
—We present a new 3D reconstruction pipeline for digital preservation of natural and cultural assets. This application requires high quality results, making time and space constr...
Alexandre Vrubel, Olga Regina Pereira Bellon, Luci...