Evaluating retraining rules for semi-supervised learning in neural network based cursive word recognition

Training a system to recognize handwritten words is a task that requires a large amount of data with their correct transcription. However, the creation of such a training set, including the generation of the ground truth, is tedious and costly. One way of reducing the high cost of labeled training data acquisition is to exploit unlabeled data, which can be gathered easily. Making use of both labeled and unlabeled data is known as semi-supervised learning. One of the most general versions of semi-supervised learning is self-training, where a recognizer iteratively retrains itself on its own output on new, unlabeled data. In this paper we propose to apply semi-supervised learning, and in particular self-training, to the problem of cursive, handwritten word recognition. The special focus of the paper is on retraining rules that define what data are actually being used in the retraining phase. In a series of experiments it is shown that the performance of a neural network based recognizer can be significantly improved through the use of unlabeled data and self-training if appropriate retraining rules are applied.

Fitting 3D morphable models using implicit representations

We consider the problem of approximating the 3D scan of a real object through an affine combination of examples. Common approaches depend either on the explicit estimation of point-to-point correspondences or on 2-dimensional projections of the target mesh; both present drawbacks. We follow an approach similar to [IF03] by representing the target via an implicit function, whose values at the vertices of the approximation are used to define a robust cost function. The problem is approached in two steps, by approximating first a coarse implicit representation of the whole target, and then finer, local ones; the local approximations are then merged together with a Poisson-based method. We report the results of applying our method on a subset of 3D scans from the Face Recognition Grand Challenge v.1.0.

Rendering Falling Leaves on Graphics Hardware

There is a growing interest in simulating natural phenomena in computer graphics applications. Animating natural scenes in real time is one of the most challenging problems due to the inherent complexity of their structure, formed by millions of geometric entities, and the interactions that happen within. An example of natural scenario that is needed for games or simulation programs are forests. Forests are difficult to render because the huge amount of geometric entities and the large amount of detail to be represented. Moreover, the interactions between the objects (grass, leaves) and external forces such as wind are complex to model. In this paper we concentrate in the rendering of falling leaves at low cost. We present a technique that exploits graphics hardware in order to render thousands of leaves with different falling paths in real time and low memory requirements.

Lower Benefits to the Refugees in Denmark: Missing Recognition?

This article is a study of the contrast between the Danish law concerning reduced economic benefits for newly arrived refugees and immigrants (known as Start Help or as introductory benefit) and the idea of recognition as the condition for individual self-realization and justice. Our assumption is that Start Help both implies economic discrimination against newly arrived persons in Denmark (especially refugees and their families under family reunification rules) and symbolizes a lack of recognition. We have chosen to adopt the theories of recognition (and redistribution) propounded by Axel Honneth and Nancy Fraser to explore our queries about Start Help and the discriminatory impact on its recipients. Empirically the article is based on in-depth qualitative interviews with six refugees who all receive Start Help.

Understanding the Other’s “Understanding” of Violence: Legitimacy, Recognition, and the Challenge of Dealing with the Past in Divided Societies

Post-conflict societies which have achieved a cessation of violence and embarked on a political conflict transformation process cannot in the long-term avoid a process of dealing with the past. Case studies of South Africa and Northern Ireland confirm this normative claim, showing that within the post-war society as a whole a social consensus on how to “understand” and “recognize” the use of violence that occurred during the conflict is necessary: understanding the other’s “understanding” of violence. A mutual understanding must be reached that both sides fought a campaign that was just and legitimate from their own perspective. The morality of the “other’s violence” has to be recognized.