Human Action Recognition without Human
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2016
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912083576094720 |
|---|---|
| author | Kataoka, Hirokatsu Hara, Kensho Satoh, Yutaka |
| author_facet | Kataoka, Hirokatsu Hara, Kensho Satoh, Yutaka |
| contents | The objective of this paper is to evaluate "human action recognition without human". Motion representation is frequently discussed in human action recognition. We have examined several sophisticated options, such as dense trajectories (DT) and the two-stream convolutional neural network (CNN). However, some features from the background could be too strong, as shown in some recent studies on human action recognition. Therefore, we considered whether a background sequence alone can classify human actions in current large-scale action datasets (e.g., UCF101). In this paper, we propose a novel concept for human action analysis that is named "human action recognition without human". An experiment clearly shows the effect of a background sequence for understanding an action label. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1608_07876 |
| institution | arXiv |
| publishDate | 2016 |
| record_format | arxiv |
| spellingShingle | Human Action Recognition without Human Kataoka, Hirokatsu Hara, Kensho Satoh, Yutaka Computer Vision and Pattern Recognition Multimedia The objective of this paper is to evaluate "human action recognition without human". Motion representation is frequently discussed in human action recognition. We have examined several sophisticated options, such as dense trajectories (DT) and the two-stream convolutional neural network (CNN). However, some features from the background could be too strong, as shown in some recent studies on human action recognition. Therefore, we considered whether a background sequence alone can classify human actions in current large-scale action datasets (e.g., UCF101). In this paper, we propose a novel concept for human action analysis that is named "human action recognition without human". An experiment clearly shows the effect of a background sequence for understanding an action label. |
| title | Human Action Recognition without Human |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/1608.07876 |