3-D Deconvolutional Networks for the Unsupervised Representation Learning of Human Motions.

Data representation learning is one of the most important problems in machine learning. Unsupervised representation learning becomes meritorious as it has no necessity of label information with observed data. Due to the highly time-consuming learning of deep-learning models, there are many machine-learning models directly adapting well-trained deep models that are obtained in a supervised and end-to-end manner as feature abstractors to distinct problems.

[Research progress on wind erosion control].

Wind erosion is the main inducement and an important process of desertification, and also, a main environmental problem needed to be controlled in many countries and areas. Based on the formation mechanisms of wind erosion and some important research results, this paper reviewed the biological, chemical, and mechanical measures in wind erosion control, which could be applied individually or integrated together to decrease or prevent wind erosion. It was suggested that management should be strengthened to ensure a better effect in applying these measures to further improve ecological environment.

[Dynamics of carbon and nitrogen storages in plant-soil system during desertification process in Horqin sandy land].

Organic carbon and nitrogen storages in plant-soil system were measured at different desertification stages (potential, light, moderate, severe, and most-severe) in Horqin sandy land. From potential desertification to light, moderate, severe, and most-severe desertification, total biomass (aboveground and belowground) carbon storages decrease by 26.4%, 51.