Abstract: In various examples, systems and methods are disclosed relating to aligning images into frames of a first video using at least one first temporal attention layer of a neural network model. The first video has a first spatial resolution. A second video having a second spatial resolution is generated by up-sampling the first video using at least one second temporal attention layer of an up-sampler neural network model, wherein the second spatial resolution is higher than the first spatial resolution.

Abstract: The invention relates to elastomer materials based on N-alkylaziridino compounds with a base component which contains the aziridino compounds and with a catalyst component which contains at least one acid-acting compound, both components being mixed before use, characterized in that, as acid-acting compound of the catalyst component, one or more boric acid complexes are used which can be obtained by reaction of boric acid and/or a boric acid derivative with at least one OH-functional compound, the OH functions being able to be present wholly or partly protected, and this reaction being carried out either as an upstream reaction between boric acid and/or a boric acid derivative and at least one such OH-functional compound or during or after the preparation of the catalyst component or by mixing the catalyst component with the base component which then contains at least one OH-functional compound.