Deep Learning Approaches for Activity Recognition

Abstract

     Recognition of activities from videos plays an important role in many different real-world applications. Its goal is to recognize the activities of a single person or collection of individuals from the sensors or from videos including the knowledge of the context in which these activities take place. In the past years this field is at great demand because of upcoming technology based on deep learning. This paper provides diverse techniques which are used for activity recognition purposes especially using deep learning approaches. Comparative study in contrast with accuracy and datasets is included in this paper.