Multiple observation improves the performance of 3D object classification. However, since the distribution of feature vectors obtained from multiple view points have strong nonlin...
Abstract. We propose a novel unsupervised transfer learning framework that utilises unlabelled auxiliary data to quantify and select the most relevant transferrable knowledge for r...
Abstract. In many cases, human actions can be identified not only by the singular observation of the human body in motion, but also properties of the surrounding scene and the rel...
Abstract. Robust tracking of objects in video is a key challenge in computer vision with applications in automated surveillance, video indexing, human-computer-interaction, gesture...
Pankaj Kumar, Michael J. Brooks, Anton van den Hen...
A key challenge in applying kernel-based methods for discriminative learning is to identify a suitable kernel given a problem domain. Many methods instead transform the input data...