Sciweavers

Share
CVPR
2012
IEEE
6 years 9 months ago
Robust camera self-calibration from monocular images of Manhattan worlds
We focus on the detection of orthogonal vanishing points using line segments extracted from a single view, and using these for camera self-calibration. Recent methods view this pr...
Horst Wildenauer, Allan Hanbury
CVPR
2012
IEEE
6 years 9 months ago
A line-structure-preserving approach to image resizing
This paper proposes a content-aware image resizing method which simultaneously preserves both salient image features and important line structure properties: parallelism, collinea...
Che-Han Chang, Yung-Yu Chuang
CVPR
2012
IEEE
6 years 9 months ago
Dense Lagrangian motion estimation with occlusions
We couple occlusion modeling and multi-frame motion estimation to compute dense, temporally extended point trajectories in video with significant occlusions. Our approach combine...
Susanna Ricco, Carlo Tomasi
CVPR
2012
IEEE
6 years 9 months ago
View invariant human action recognition using histograms of 3D joints
In this paper, we present a novel approach for human action recognition with histograms of 3D joint locations (HOJ3D) as a compact representation of postures. We extract the 3D sk...
Lu Xia, Chia-Chih Chen, J. K. Aggarwal
CVPR
2012
IEEE
6 years 9 months ago
Supervised hashing with kernels
Recent years have witnessed the growing popularity of hashing in large-scale vision problems. It has been shown that the hashing quality could be boosted by leveraging supervised ...
Wei Liu, Jun Wang, Rongrong Ji, Yu-Gang Jiang, Shi...
CVPR
2012
IEEE
6 years 9 months ago
Single image multimaterial estimation
Estimating the reflectance and illumination from a single image becomes particularly challenging when the object surface consists of multiple materials. The key difficulty lies ...
Stephen Lombardi, Ko Nishino
CVPR
2012
IEEE
6 years 9 months ago
Enhanced continuous sign language recognition using PCA and neural network features
In this work a Gaussian Hidden Markov Model (GHMM) based automatic sign language recognition system is built on the SIGNUM database. The system is trained on appearance-based feat...
Yannick L. Gweth, Christian Plahl, Hermann Ney
CVPR
2012
IEEE
6 years 9 months ago
Robust plane-based structure from motion
We introduce a new approach to structure and motion recovery directly from one or more large planes in the scene. When such a plane exists, we demonstrate how to automatically det...
Zihan Zhou, Hailin Jin, Yi Ma
CVPR
2012
IEEE
6 years 9 months ago
Bag of textons for image segmentation via soft clustering and convex shift
We propose an unsupervised image segmentation method based on texton similarity and mode seeking. The input image is first convolved with a filter-bank, followed by soft cluster...
Zhiding Yu, Ang Li, Oscar C. Au, Chunjing Xu
CVPR
2012
IEEE
6 years 9 months ago
Multi-output Laplacian dynamic ordinal regression for facial expression recognition and intensity estimation
Automated facial expression recognition has received increased attention over the past two decades. Existing works in the field usually do not encode either the temporal evolutio...
Ognjen Rudovic, Vladimir Pavlovic, Maja Pantic
books