A Systematic Survey on Human Behavior Recognition Methods

Abstract

Human behavior is an essential component of social interaction and is of great significance to identify and analyze human behaviors in a variety of fields. Due to the rapid development of computer vision and machine learning technology, machine with intelligence has started replacing human beings to observe, perceive and analyze the explosive growth of image and video data. Computer vision and machine learning-based human behavior recognition is one of these tasks, which has become a particularly hot research topic in many different fields, such as intelligent monitoring, human-computer interaction, smart home, virtual reality, and medical diagnosis. In this study, we survey systematically the popular methods, algorithms, models and well-known action datasets in human behavior analysis in the past two decades. In addition, the advantages and disadvantages of the methods are discussed and propitious future research directions are also presented. The results of this survey reveal that paradigms of human behavior analysis is being shifted from traditional RGB to RGB-D, from deep learning to more intelligent and automated deep reinforcement learning, and from fixed camera devices to portable devices and channel state information (CSI), and paradigms based on automated deep reinforcement learning and portable devices and CSI would become some hot topics for future research on human behavior analysis.

A new branch of fake review detection research -- A review of fake review detection in the Chinese film industry in the post-epidemic era

“…Fake reviews are reviews that don't match the actual user experience [4]. Reviews are an important reference for consumers to purchase products, through which they can learn other users' understanding of product features and user experience.…”

“…Even if a single review can be judged to be true or false, it is also difficult to see from a large number of data what proportion of reviews are untrue. The two directions of fake review detection are text detection and reviewer behavior detection [4], and the main tools are text analysis, data mining, and statistics. Fake review detection was first proposed by Jindal et al [6], but only at the text level of reviews.…”

“…The general process of fake review detection is data acquisition, data processing, dimension selection, modeling, and effect evaluation. [4] The reviews that have the most significant impact on the box office of the movie are the reviews in the early stage. Different from the reviews of physical goods, the water army of the movie starts to warm up the box office before the movie is released and is mainly active in the early stage of the movie release period.…”

“…fake review detection is a method to identify fake reviews from a large number of reviews. The existing research results include text detection, reviewer detection, and comprehensive detection [4]. However, the application of this technology in the Chinese film field is lacking.…”