Self-paced learning (SPL) is a recently raised methodology designed through simulating the learning principle of humans/animals. A variety of SPL realization schemes have been designed for different computer vision and pattern recognition tasks, and empirically substantiated to be effective in these applications. However, the investigation on its theoretical insight is still a blank. To this is...

Person re-identification (Re-ID) usually suffers from noisy samples with background clutter and mutual occlusion, which makes it extremely difficult to distinguish different individuals across the disjoint camera views. In this paper, we propose a novel deep selfpaced learning (DSPL) algorithm to alleviate this problem, in which we apply a self-paced constraint and symmetric regularization to h...

(4) Copyright c © 2015, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. where I(·) is the indicator function (equals 1 if the equation within the brackets holds, and 0 otherwise), and the outside sum is taken over ik = 1, . . . , n for k = 1, . . . , n. The coefficients pi1i2...ins are positive and do not depend on the function f . Let f(x) = 1, b...

Since the inception of e-learning technologies, there has been an increase in the use of e-learning systems to support blended learning in Universities by providing a mix of face-to-face classroom teaching, live e-learning, self-paced e-learning and distance learning. Despite the existing benefits of using e-learning, some higher education institutions have not utilised e-learning to its full p...

Distance learning is rapidly becoming pervasive in every aspect of education. From elementary school through doctoral programs, information technology enables self-paced learning with some degree of distance from teaching professionals. Educators sometimes begin this online delivery system without fully examining the academic soundness of this approach. Other considerations are administrative m...

In a weakly-supervised scenario, object detectors need to be trained using image-level annotation only. Since bounding-box-level ground truth is not available, mostof the solutions proposed so far are based on an iterative approach in which theclassifier, obtained in the previous iteration, is used to predict the objects’ positionswhich are used for training in the current itera...

Virtual Campus is an Internet application in education. It combines the advantages of both group and individual learning approaches based on advanced network technologies. Virtual Campus models the new learning environment where students can customize their study in their own pace. Providing up-to-date learning material and personal study guide, Virtual Campus is an ideal study environment for ...

E-learning is the internet enabled learning. Internet has ongoing to restructuring education. Intelligent agent based e-learning provide a common infrastructure to assimilate varied software components. There are two sorts of e-learning synchronous and asynchronous. This paper described the detail of well-known agent based architecture for e-learning. E-learning is going to be gigantic. There a...