Action Recognition and Detection Based on Deep Learning: A Comprehensive Summary

Action recognition and detection is an important research topic in computer vision,which can be divided into action recognition and action detection.At present,the distinction between action recognition and action detection is not clear,and the relevant reviews are not comprehensive.Thus,this paper summarized the action recognition and detection methods and datasets based on deep learning to accurately present the research status in this field.Firstly,according to the way that temporal and spatial features are extracted from the model,the commonly used models of action recognition are divided into the two stream models,the temporal models,the spatiotemporal models and the transformer models according to the architecture.And this paper briefly analyzes the characteristics of the four models and introduces the accuracy of various algorithms in common data sets.Then,from the perspective of tasks to be completed,action detection is further divided into temporal action detection and spatiotemporal action detection,and commonly used datasets are introduced.From the perspectives of the twostage method and one-stage method,various algorithms of temporal action detection are reviewed,and the various algorithms of spatiotemporal action detection are summarized in detail.Finally,the relationship between different parts of action recognition and detection is discussed,the difficulties faced by the current research are summarized in detail,and future development was prospected。

Nano friction behaviour between magnetic materials and copper considering the inter-diffusion effect

Copper,permalloy,cobalt,and silicon are the materials that have been widely utilised in magnetic devices.When the size of interest is down to the nanoscale,the inter-diffusion between certain materials becomes influential.This paper studies the nanoscale friction characteristics between frictional pairs with and without inter-diffusion properties through the atomic force microscope.The distinct evolution features of nanoscale friction force when inter-diffusion is involved are discovered experimentally,which is also confirmed through theoretical analysis.Firstly,through the thin film deposition method,four pairs of contact materials(Cu–Ni_(81)Fe_(19),Si–Ni_(81)Fe_(19),Cu–Co,Cu–Si)are designed for friction tests,in which diffusion occurs at the interface of Cu–Ni_(81)Fe_(19)pair.Then,the effects of sliding velocity and loading force on the nano friction of each pair are measured.It is found that regardless of the diffusion phenomenon:(1)the adhesion force values exhibit a notable correlation to the values of the friction force;(2)the friction force in all four material pairs consistently increases with the growth of the normal loading force,although the growth rate may differ.In terms of the sliding velocity effect,the friction forces of immiscible materials(Si–Ni_(81)Fe_(19),Cu–Co,and Cu–Si)are found to increase with the increasing sliding velocity.However,the friction force of Cu–Ni_(81)Fe_(19),decreases with the increasing sliding velocity.Furthermore,a compositive friction model considering both the velocity and the normal force effect was proposed,which shows good agreement with the experimental results and explains the nano friction behaviour of both miscible and immiscible metals.