An Efficient Approach Using Knowledge Distillation Methods to Stabilize Performance in a Lightweight Top-Down Posture Estimation Network
Multi-person pose estimation has been gaining considerable interest due to its use in several real-world applications, such as activity recognition, motion capture, and augmented reality. Although the improvement of the accuracy and speed of multi-person pose estimation techniques has been recently...
Guardado en:
Autores principales: | Changhyun Park, Hean Sung Lee, Woo Jin Kim, Han Byeol Bae, Jaeho Lee, Sangyoun Lee |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
MDPI AG
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/5b7260bb507a4836b4ee492f48aad005 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Knowledge Distillation of Grassmann Manifold Network for Remote Sensing Scene Classification
por: Ling Tian, et al.
Publicado: (2021) -
Distilled-MobileNet Model of Convolutional Neural Network Simplified Structure for Plant Disease Recognition
por: QIU Wenjie, et al.
Publicado: (2021) -
Improved Dual-Channel Attention Mechanism Image Classification Method for Lightweight Network
por: Song Tainian, Qin Weiwei, Liang Zhuo, Wang Kui, Liu Gang
Publicado: (2021) -
Graph-Based Hand-Object Meshes and Poses Reconstruction With Multi-Modal Input
por: Murad Almadani, et al.
Publicado: (2021) -
Remote Sensing Scene Image Classification Based on Dense Fusion of Multi-level Features
por: Cuiping Shi, et al.
Publicado: (2021)