Review of human action recognition based on improved deep learning methods
Human action recognition is a basic problem in video tasks. The deep learning method has profound theoretical research significance and strong application value in intelligent monitoring, automatic driving, medical care and other aspects. Firstly, the paper summarizes the video preprocessing and the...
Saved in:
| Main Authors | , |
|---|---|
| Format | Conference Proceeding |
| Language | English |
| Published |
SPIE
16.02.2022
|
| Online Access | Get full text |
Cover
Loading…
| Summary: | Human action recognition is a basic problem in video tasks. The deep learning method has profound theoretical research significance and strong application value in intelligent monitoring, automatic driving, medical care and other aspects. Firstly, the paper summarizes the video preprocessing and the improvement of network structure, and concludes the latest and hottest deep learning methods in the field of human action recognition. Then two kinds of datasets related to human action recognition are listed and introduced in detail. |
|---|---|
| Bibliography: | Conference Date: 2021-08-18|2021-08-20 Conference Location: Kunming, China |
| ISBN: | 9781510650428 1510650423 |
| ISSN: | 0277-786X |
| DOI: | 10.1117/12.2623162 |