Contrastive learning of graph encoder for accelerating pedestrian trajectory prediction training
Abstract In the area of pedestrian trajectory prediction, the hybrid structures of temporal feature extractor or spatial feature extractor have paved the way for the precise prediction model, and they are in larger and larger scale. Learning of specific feature encoding model not only influenced by...
Guardado en:
Autores principales: | Zonggui Yao, Jun Yu, Jiajun Ding |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Wiley
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/a221bb83f854462eb70822cb29fb44d5 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Crowd activity recognition in live video streaming via 3D‐ResNet and region graph convolution network
por: Junpeng Kang, et al.
Publicado: (2021) -
CA‐PMG: Channel attention and progressive multi‐granularity training network for fine‐grained visual classification
por: Peipei Zhao, et al.
Publicado: (2021) -
Latent label mining for group activity recognition in basketball videos
por: Lifang Wu, et al.
Publicado: (2021) -
Cross‐modal semantic correlation learning by Bi‐CNN network
por: Chaoyi Wang, et al.
Publicado: (2021) -
Multi‐dimensional weighted cross‐attention network in crowded scenes
por: Yefan Xie, et al.
Publicado: (2021)