Spatio-Temporal Information Fusion and Filtration for Human Action Recognition
Human action recognition (HAR) as the most representative human-centred computer vision task is critical in human resource management (HRM), especially in human resource recruitment, performance appraisal, and employee training. Currently, prevailing approaches to human action recognition primarily...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/15/12/2177 |
| _version_ | 1797379310522204160 |
|---|---|
| author | Man Zhang Xing Li Qianhan Wu |
| author_facet | Man Zhang Xing Li Qianhan Wu |
| author_sort | Man Zhang |
| collection | DOAJ |
| description | Human action recognition (HAR) as the most representative human-centred computer vision task is critical in human resource management (HRM), especially in human resource recruitment, performance appraisal, and employee training. Currently, prevailing approaches to human action recognition primarily emphasize either temporal or spatial features while overlooking the intricate interplay between these two dimensions. This oversight leads to less precise and robust action classification within complex human resource recruitment environments. In this paper, we propose a novel human action recognition methodology for human resource recruitment environments, which aims at symmetrically harnessing temporal and spatial information to enhance the performance of human action recognition. Specifically, we compute Depth Motion Maps (DMM) and Depth Temporal Maps (DTM) from depth video sequences as space and time descriptors, respectively. Subsequently, a novel feature fusion technique named Center Boundary Collaborative Canonical Correlation Analysis (CBCCCA) is designed to enhance the fusion of space and time features by collaboratively learning the center and boundary information of feature class space. We then introduce a spatio-temporal information filtration module to remove redundant information introduced by spatio-temporal fusion and retain discriminative details. Finally, a Support Vector Machine (SVM) is employed for human action recognition. Extensive experiments demonstrate that the proposed method has the ability to significantly improve human action recognition performance. |
| first_indexed | 2024-03-08T20:20:18Z |
| format | Article |
| id | doaj.art-af82a3607db74654a5afbfed6a67e44e |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-08T20:20:18Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-af82a3607db74654a5afbfed6a67e44e2023-12-22T14:45:19ZengMDPI AGSymmetry2073-89942023-12-011512217710.3390/sym15122177Spatio-Temporal Information Fusion and Filtration for Human Action RecognitionMan Zhang0Xing Li1Qianhan Wu2College of Information Science and Technology & College of Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, ChinaCollege of Information Science and Technology & College of Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, ChinaSchool of Computer and Information, Hohai University, Nanjing 211100, ChinaHuman action recognition (HAR) as the most representative human-centred computer vision task is critical in human resource management (HRM), especially in human resource recruitment, performance appraisal, and employee training. Currently, prevailing approaches to human action recognition primarily emphasize either temporal or spatial features while overlooking the intricate interplay between these two dimensions. This oversight leads to less precise and robust action classification within complex human resource recruitment environments. In this paper, we propose a novel human action recognition methodology for human resource recruitment environments, which aims at symmetrically harnessing temporal and spatial information to enhance the performance of human action recognition. Specifically, we compute Depth Motion Maps (DMM) and Depth Temporal Maps (DTM) from depth video sequences as space and time descriptors, respectively. Subsequently, a novel feature fusion technique named Center Boundary Collaborative Canonical Correlation Analysis (CBCCCA) is designed to enhance the fusion of space and time features by collaboratively learning the center and boundary information of feature class space. We then introduce a spatio-temporal information filtration module to remove redundant information introduced by spatio-temporal fusion and retain discriminative details. Finally, a Support Vector Machine (SVM) is employed for human action recognition. Extensive experiments demonstrate that the proposed method has the ability to significantly improve human action recognition performance.https://www.mdpi.com/2073-8994/15/12/2177human-centred computer visionhuman action recognitiondepth video sequencehuman resource management |
| spellingShingle | Man Zhang Xing Li Qianhan Wu Spatio-Temporal Information Fusion and Filtration for Human Action Recognition Symmetry human-centred computer vision human action recognition depth video sequence human resource management |
| title | Spatio-Temporal Information Fusion and Filtration for Human Action Recognition |
| title_full | Spatio-Temporal Information Fusion and Filtration for Human Action Recognition |
| title_fullStr | Spatio-Temporal Information Fusion and Filtration for Human Action Recognition |
| title_full_unstemmed | Spatio-Temporal Information Fusion and Filtration for Human Action Recognition |
| title_short | Spatio-Temporal Information Fusion and Filtration for Human Action Recognition |
| title_sort | spatio temporal information fusion and filtration for human action recognition |
| topic | human-centred computer vision human action recognition depth video sequence human resource management |
| url | https://www.mdpi.com/2073-8994/15/12/2177 |
| work_keys_str_mv | AT manzhang spatiotemporalinformationfusionandfiltrationforhumanactionrecognition AT xingli spatiotemporalinformationfusionandfiltrationforhumanactionrecognition AT qianhanwu spatiotemporalinformationfusionandfiltrationforhumanactionrecognition |