A hypothesis is put forward of how global patterns of optical flow, as discussed by Gibson, Johansson, and others, could be processed by relatively simple physiological mechanisms. It is suggested that there may exist motion-sensitive cells in the visual system which operate on the optical flow over the retina, and, in so doing, structure the visual field in terms of distinct surfaces that move...

Let Fn be the binary n-cube, or binary Hamming space of dimension n, endowed with the Hamming distance, and En (respectively, On) the set of vectors with even (respectively, odd) weight. For r 1 and x 2 Fn, we denote by Br(x) the ball of radius r and centre x. A code C Fn is said to be r-identifying if the sets Br(x)\C, x 2 Fn, are all nonempty and distinct. A code C En is said to be r-discrimi...

In this paper we introduce the definite closure operation for matrices with finite permanent, reveal inner structures of definite eigenspaces, and establish some facts about Hilbert distances between these inner structures and the boundary of the definite eigenspace.

trajectories generally used to describe the space and time required to perform a desired motion task for a mobile robot or manipulator system. in this paper, we considered a cubic polynomial trajectory for the problem of moving a mobile robot from its initial position to a goal position in over a continuous set of time. along the path, the robot requires to observe a certain acceleration profil...

The number of potential applications has made automatic recognition of human actions a very active research area. Different approaches have been followed based on trajectories through some state space. In this paper we also model an action as a trajectory through a state space, but we represent the actions as a sequence of temporal isolated instances, denoted primitives. These primitives are ea...

Vectored data frequently occur in a variety of fields, which are easy to handle since they can be mathematically abstracted as points residing in a Euclidean space. An appropriate distance metric in the data space is quite demanding for a great number of applications. In this paper, we pose robust and tractable metric learning under pairwise constraints that are expressed as similarity judgemen...

We study distance-based classification of human actions and introduce a new metric learning approach based on logistic discrimination for the determination of a low-dimensional feature space of increased discrimination power. We argue that for effective distance-based classification, both the optimal projection space and the optimal class representation should be determined. We qualitatively an...

This paper proposes an OCR post-processing approach based on multi-knowledge, which integrates language knowledge and candidate distance information given by the OCR engine. In this approach, statistical language model and semantic lexicon are combined, and candidate distance information is used to reduce the size of the search space. The experimental results show that this approach is very eff...

In this paper, the authors propose a kernel-based approach to improve the retrieval performances of CBIR systems by learning a distance metric based on class probability distributions. Unlike other metric learning methods which are based on local or global constraints, the proposed method learns for each class a nonlinear kernel which transforms the original feature space to a more effective on...