A deep learning method for video‐based action recognition
Abstract In this paper, a deep learning method for video‐based action recognition is proposed. On the one hand, boundary compensation on the basis of a deep neural network is performed to achieve action proposal. Boundary compensation considering non‐maximum suppression according to sliding window p...
Guardado en:
Autores principales: | Guanwen Zhang, Yukun Rao, Changhao Wang, Wei Zhou, Xiangyang Ji |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Wiley
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/da8a99b21cce4c59b135963dcc5b04de |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Latent label mining for group activity recognition in basketball videos
por: Lifang Wu, et al.
Publicado: (2021) -
Class structure‐aware adversarial loss for cross‐domain human action recognition
por: Wanjun Chen, et al.
Publicado: (2021) -
Dual‐view 3D human pose estimation without camera parameters for action recognition
por: Long Liu, et al.
Publicado: (2021) -
Crowd activity recognition in live video streaming via 3D‐ResNet and region graph convolution network
por: Junpeng Kang, et al.
Publicado: (2021) -
A novel face recognition method based on fusion of LBP and HOG
por: Ting Chen, et al.
Publicado: (2021)