Pairwise Kernels for Human Interaction Recognition

2013 ◽  
pp. 210-221 ◽  
Author(s):  
Saeid Motiian ◽  
Ke Feng ◽  
Harika Bharthavarapu ◽  
Sajid Sharlemin ◽  
Gianfranco Doretto
Keyword(s):  
Human Interaction ◽  
Interaction Recognition ◽  
Human Interaction Recognition

Dyadic Relational Graph Convolutional Networks for Skeleton-based Human Interaction Recognition

2021 ◽  
pp. 107920
Author(s):  
Liping Zhu ◽  
Bohua Wan ◽  
Chengyang Li ◽  
Gangyi Tian ◽  
Yi Hou ◽  
...  
Keyword(s):  
Human Interaction ◽  
Convolutional Networks ◽  
Interaction Recognition ◽  
Human Interaction Recognition

Human interaction recognition method based on parallel multi-feature fusion network

2021 ◽  
Vol 25 (4) ◽  
pp. 809-823
Author(s):  
Qing Ye ◽  
Haoxin Zhong ◽  
Chang Qu ◽  
Yongmei Zhang
Keyword(s):  
Activity Recognition ◽  
Feature Fusion ◽  
Gaussian Model ◽  
Research Direction ◽  
Recognition Algorithm ◽  
Human Interaction ◽  
Amount Of Information ◽  
Interaction Recognition ◽  
Time Periods ◽  
Human Interaction Recognition

Human activity recognition is a key technology in intelligent video surveillance and an important research direction in the field of computer vision. However, the complexity of human interaction features and the differences in motion characteristics at different time periods have always existed. In this paper, a human interaction recognition algorithm based on parallel multi-feature fusion network is proposed. First of all, in view of the different amount of information provided by the different time periods of action, an improved time-phased video down sampling method based on Gaussian model is proposed. Second, the Inception module uses different scale convolution kernels for feature extraction. It can improve network performance and reduce the amount of network parameters at the same time. The ResNet module mitigates degradation problem due to increased depth of neural networks and achieves higher classification accuracy. The amount of information provided in the motion video in different stages of motion time is also different. Therefore, we combine the advantages of the Inception network and ResNet to extract feature information, and then we integrate the extracted features. After the extracted features are merged, the training is continued to realize parallel connection of the multi-feature neural network. In this paper, experiments are carried out on the UT dataset. Compared with the traditional activity recognition algorithm, this method can accomplish the recognition tasks of six kinds of interactive actions in a better way, and its accuracy rate reaches 88.9%.

Sign in / Sign up

Export Citation Format

Share Document