Efficient tracking of human poses using a manifold hierarchy

In this paper a 3D human pose tracking framework is presented. A new dimensionality reduction method (Hierarchical Temporal Laplacian Eigenmaps) is introduced to represent activities in hierarchies of low dimensional spaces. Such a hierarchy provides increasing independence between limbs, allowing higher flexibility and adaptability that result in improved accuracy. Moreover, a novel deterministic optimisation method (Hierarchical Manifold Search) is applied to estimate efficiently the position of the corresponding body parts. Finally, evaluation on public datasets such as HumanEva demonstrates that our approach achieves a 62.5mm-65mm average joint error for the walking activity and outperforms state-of-the-art methods in terms of accuracy and computational cost.

A Pension for Injured Victims of the Troubles: Reparations or Reifying Victim Hierarchy?

Reparations have been often used victim-centred measures to redress both private harm and gross violations of human rights. However, with the increasing occurrence of internal armed conflict and political violence, identities of victims and perpetrators in protracted conflicts can become blurred for some individuals. In countries like Peru and Northern Ireland that have suffered protracted violence, victimhood has been contested around which individuals are seen as innocent and deserving to exclude any members of non-state armed groups from claiming reparations. This article explores the issue of a proposed bill on a pension for injured victims of the Troubles in Northern Ireland. It identifies that there is no consistent state practice or human rights jurisprudence in this area, but instead offers a more complex approach through four models that can grapple with the seeming diametrically opposed victimhood and responsibility, by including victimised-perpetrators in reparations programmes such as that proposed for a pension of seriously injured victims in Northern Ireland.