Digital, interactive content can support active learning and provide both motivation and an automated feedback to students. Unfortunately authoring interactive content remains a difficult task for teachers. There are few interoperable standards and e-learning platforms often restrict what is technically possible. Even if some teachers create amazing interactive content it is challenging to publish and share this content with colleagues. This paper proposes a way to leverage Web Components, a rather new technology supported by modern browsers, to allow teachers to quickly author interactive exercises involving mathematical expressions and visualizations. As Web Components are standardized they can be shared and embedded in any website. The proposed Web Components for mathematics allow for: 1. A convenient visual input method for expressions and formulas, 2. A sophisticated validation system for these expressions in order to give immediate feedback to students on their solutions.

Online courses often require students to work self-dependently using books or video material. For abstract subjects such as mathematics this is particularly challenging. To improve student motivation and learning results, we propose an interactive feedback and assessment tool tailored to math exercises. Our system is able to process and analyze mathematical expressions using an underlying computer algebra system. It allows teachers to create exercises with a much wider range of question types as it is possible with today’s learning management systems, which are mostly restricted to multiple choice questions. We can provide automatic individual feedback to students for almost any kind of mathematical exercise. Thus, making it easier for students to practice and study math in a self-dependent manner.

Online courses raise many new challenges. It is particularly difficult to teach subjects, which focus on techni- cal principles and require students to practice. In order to motivate and support students we need to provide assistance and feedback. When the number of students in online courses increases to several thousand partic- ipants this assistance and feedback cannot be handled by the teaching staff alone. In this paper we propose a system, which allows to automatically validate programming exercises at a fine-grained level using unit tests. Thus, students get immediate feedback, which helps them understanding the encountered problems. The proposed system offers a wide range of possible exercise types for programming exercises. These range from exercises where students need to provide only code snippets to exercises including complex algorithms. Moreover, the system allows teachers to grade student exercises automatically. Unlike common grading tools for programming exercises, it can deal with partial solutions and avoids an all-or-nothing style grading.

Object class detection in scenes of realistic complexity remains a challenging task in computer vision. Most recent approaches focus on a single and general model for object class detection. However, in particular in the context of image sequences, it may be advantageous to adapt the general model to a more object-instance specific model in order to detect this particular object reliably within the image sequence. In this work we present a generative object model that is capable to scale from a general object class model to a more specific object-instance model. This allows to detect class instances as well as to distinguish between individual object instances reliably. We experimentally evaluate the performance of the proposed system on both still images and image sequences.

A wide range of methods have been proposed to detect and recognize objects. However, effective and efficient multiviewpoint detection of objects is still in its infancy, since most current approaches can only handle single viewpoints or aspects. This paper proposes a general approach for multiaspect detection of objects. As the running example for detection we use pedestrians, which add another difficulty to the problem, namely human body articulations. Global appearance changes caused by different articulations and viewpoints of pedestrians are handled in a unified manner by a generalization of the Implicit Shape Model [5]. An important property of this new approach is to share local appearance across different articulations and viewpoints, therefore requiring relatively few training samples. The effectiveness of the approach is shown and compared to previous approaches on two datasets containing pedestrians with different articulations and from multiple viewpoints.

Pedestrian detection in real world scenes is a challenging problem. In recent years a variety of approaches have been proposed, and impressive results have been reported on a variety of databases. This paper systematically evaluates (1) various local shape descriptors, namely Shape Context and Local Chamfer descriptor and (2) four different interest point detectors for the detection of pedestrians. Those results are compared to the standard global Chamfer matching approach. A main result of the paper is that Shape Context trained on real edge images rather than on clean pedestrian silhouettes combined with the Hessian-Laplace detector outperforms all other tested approaches. 1

In this paper, we address the problem of detecting pedestrians in crowded real-world scenes with severe overlaps. Our basic premise is that this problem is too difficult for any type of model or feature alone. Instead, we present an algorithm that integrates evidence in multiple iterations and from different sources. The core part of our method is the combination of local and global cues via probabilistic top-down segmentation. Altogether, this approach allows examining and comparing object hypotheses with high precision down to the pixel level. Qualitative and quantitative results on a large data set confirm that our method is able to reliably detect pedestrians in crowded scenes, even when they overlap and partially occlude each other. In addition, the flexible nature of our approach allows it to operate on very small training sets.

We describe our system which facilitates collaboration using multiple modalities, including speech, handwriting, gestures, gaze tracking, direct manipulation, large projected touch-sensitive displays, laser pointer tracking, regular monitors with a mouse and keyboard, and wireless networked handhelds. Our system allows multiple, geographically dispersed participants to simultaneously and flexibly mix different modalities using the right interface at the right time on one or more machines. We discuss each of the modalities provided, how they were integrated in the system architecture, and how the user interface enabled one or more people to flexibly use one or more devices.