No studies have investigated cross-cultural and cross-language characteristics of depressed speech. We investigated the generalisability of a vocal biomarker-based approach to depression detection in clinical interviews recorded in three countries (Australia, the USA and Germany), two languages (German and English) and different accents (Australian and American). Several approaches to training ...

In two experiments, we investigated the benefits of using interactive animation and virtual geometric solids for spatial visualization training. Individuals with low spatial ability were trained to recognize the cross section of a threedimensional (3D) object using interactive animations in which they passed a plane through a 3D object, observed, and drew the resulting cross section. In both ex...

In this paper, we propose XGPT, a new method of Cross-modal Generative Pre-Training for Image Captioning that is designed to pre-train text-to-image caption generators through four novel generation tasks, including Adversarial (AIC), Image-conditioned Masked Language Modeling (IMLM), Denoising Autoencoding (IDA), and Text-conditioned Feature Generation (TIFG). As result, the pre-trained XGPT ca...