Cargando…
Self-Supervised Action Representation Learning Based on Asymmetric Skeleton Data Augmentation
Contrastive learning has received increasing attention in the field of skeleton-based action representations in recent years. Most contrastive learning methods use simple augmentation strategies to construct pairs of positive samples. When using such pairs of positive samples to learn action represe...
Autores principales: | Zhou, Hualing, Li, Xi, Xu, Dahong, Liu, Hong, Guo, Jianping, Zhang, Yihan |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9698072/ https://www.ncbi.nlm.nih.gov/pubmed/36433585 http://dx.doi.org/10.3390/s22228989 |
Ejemplares similares
-
ConMLP: MLP-Based Self-Supervised Contrastive Learning for Skeleton Data Analysis and Action Recognition
por: Dai, Chuan, et al.
Publicado: (2023) -
Contrastive self-supervised representation learning without negative samples for multimodal human action recognition
por: Yang, Huaigang, et al.
Publicado: (2023) -
Self-supervised representation learning for surgical activity recognition
por: Paysan, Daniel, et al.
Publicado: (2021) -
Heuristic Attention Representation Learning for Self-Supervised Pretraining
por: Tran, Van Nhiem, et al.
Publicado: (2022) -
Generalized Pose Decoupled Network for Unsupervised 3D Skeleton Sequence-Based Action Representation Learning
por: Liu, Mengyuan, et al.
Publicado: (2022)