CVPR
2010
IEEE
14 years 1 months ago
2010
IEEE
Surface registration is widely used in machine vision and medical imaging, where 1-1 correspondences between surfaces are computed to study their variations. Surface maps are usua...
CVPR
2010
IEEE
14 years 1 months ago
2010
IEEE
We present a fast and accurate algorithm for computing the 2D pose of objects in images called cascaded pose regression (CPR). CPR progressively refines a loosely specified initia...
CVPR
2010
IEEE
14 years 1 months ago
2010
IEEE
Kernel methods provide an efficient mechanism to derive nonlinear algorithms. In classification problems as well as in feature extraction, kernel-based approaches map the original...
CVPR
2010
IEEE
14 years 1 months ago
2010
IEEE
We introduce a method to accelerate the evaluation of object detection cascades with the help of a divide-andconquer procedure in the space of candidate regions. Compared to the e...
CVPR
2010
IEEE
14 years 1 months ago
2010
IEEE
Videos can be naturally represented as multidimensional arrays known as tensors. However, the geometry of the tensor space is often ignored. In this paper, we argue that the under...
CVPR
2010
IEEE
14 years 1 months ago
2010
IEEE
The design of robust classifiers, which can contend with the noisy and outlier ridden datasets typical of computer vision, is studied. It is argued that such robustness requires l...
ECCV
2010
Springer
14 years 1 months ago
2010
Springer
Abstract. The aim of this paper is to learn driving behaviour by associating the actions recorded from a human driver with pre-attentive visual input, implemented using holistic im...
ECCV
2010
Springer
14 years 1 months ago
2010
Springer
Accurately annotating entities in video is labor intensive and expensive. As the quantity of online video grows, traditional solutions to this task are unable to scale to meet the ...
ECCV
2010
Springer
14 years 1 months ago
2010
Springer
We present a novel similarity measure for bag-of-words type large scale image retrieval. The similarity function is learned in an unsupervised manner, requires no extra space over ...
ECCV
2010
Springer
14 years 1 months ago
2010
Springer
Most methods for the recognition of shape classes from 3D datasets focus on classifying clean, often manually generated models. However, 3D shapes obtained through acquisition tech...