Search

In recent years, various human action recognition algorithms have achieved excellent recognition performance based on a large number of labeled samples. However, in practical applications, acquiring training samples and their corresponding labels is time-consuming and laborious, which limits the actual implementation of the algorithm. This paper summarized the deep learning algorithms for action recognition under weak supervision and few-shot learning. Firstly, in the case of weak supervision, it classified and summarized the semi-supervised action recognition methods and unsupervised domain adaptation video action recognition methods separately. Then, it reviewed video action recognition algorithms based on few-shot learning in detail. Further, it summarized the relevant human behavior datasets and analyzed and compared the performance of various relevant video action recognition algorithms on these datasets. Finally, the paper summarized the full text and discusses the future development trend of human action recognition. [ABSTRACT FROM AUTHOR]

In order to sort out the development of deep learning methods in the field of human action recognition, this paper summarized the most representative models and algorithms in this field in recent years. Firstly, it described in detail the latest achievements, advantages and disadvantages and network structure of deep learning methods in video pre-processing stage based on the task flow of human action recognition. Then, it introduced two kinds of datasets related to human action recognition. Finally, it discussed and prospected the future research direction of human action recognition. [ABSTRACT FROM AUTHOR]

In order to effectively reduce the influence of the characteristics on population density estimation and population behavior, the dense population is characterized by extremely large population and serious occlusion and blockage between adjacent individuals. In this paper, we have provided the distance threshold to improve the intelligent population algorithm, and provided an intelligent population algorithm combined with the gray level occurrence matrix for population density estimation and behavior analysis. Homogenizing samples and setting thresholds can avoid the misjudgment caused by the excessive distance between the target scene and the sample, which is ensuring the performance of classification. The paper enhances the ability of representation by adding distance weights, and reduces the impact of highdimensional features on the classification results. [ABSTRACT FROM AUTHOR]

Video-based human action recognition is currently one of the most active research areas in computer vision. Various research studies indicate that the performance of action recognition is highly dependent on the type of features being extracted and how the actions are represented. Since the release of the Kinect camera, a large number of Kinect-based human action recognition techniques have been proposed in the literature. However, there still does not exist a thorough comparison of these Kinect-based techniques under the grouping of feature types, such as handcrafted versus deep learning features and depth-based versus skeleton-based features. In this paper, we analyze and compare 10 recent Kinect-based algorithms for both cross-subject action recognition and cross-view action recognition using six benchmark datasets. In addition, we have implemented and improved some of these techniques and included their variants in the comparison. Our experiments show that the majority of methods perform better on cross-subject action recognition than cross-view action recognition, that the skeleton-based features are more robust for cross-view recognition than the depth-based features, and that the deep learning features are suitable for large datasets. [ABSTRACT FROM AUTHOR]