Cargando…
Zero-Shot Action Recognition with Three-Stream Graph Convolutional Networks †
Large datasets are often used to improve the accuracy of action recognition. However, very large datasets are problematic as, for example, the annotation of large datasets is labor-intensive. This has encouraged research in zero-shot action recognition (ZSAR). Presently, most ZSAR methods recognize...
Autores principales: | Wu, Nan, Kawamoto, Kazuhiko |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8198984/ https://www.ncbi.nlm.nih.gov/pubmed/34070872 http://dx.doi.org/10.3390/s21113793 |
Ejemplares similares
-
Learning Three Dimensional Tennis Shots Using Graph Convolutional Networks
por: Skublewska-Paszkowska, Maria, et al.
Publicado: (2020) -
Shallow Graph Convolutional Network for Skeleton-Based Action Recognition
por: Yang, Wenjie, et al.
Publicado: (2021) -
Zero-shot learning of aerosol optical properties with graph neural networks
por: Lamb, K. D., et al.
Publicado: (2023) -
CGUN-2A: Deep Graph Convolutional Network via Contrastive Learning for Large-Scale Zero-Shot Image Classification
por: Li, Liangwei, et al.
Publicado: (2022) -
GAS-GCN: Gated Action-Specific Graph Convolutional Networks for Skeleton-Based Action Recognition
por: Chan, Wensong, et al.
Publicado: (2020)