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...
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...
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...
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...
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...
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...
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...
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 ...
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 ...
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...