Cargando…
Enhanced 3D Pose Estimation in Multi-Person, Multi-View Scenarios through Unsupervised Domain Adaptation with Dropout Discriminator
Data-driven pose estimation methods often assume equal distributions between training and test data. However, in reality, this assumption does not always hold true, leading to significant performance degradation due to distribution mismatches. In this study, our objective is to enhance the cross-dom...
Autores principales: | Deng, Junli, Yao, Haoyuan, Shi, Ping |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10610700/ https://www.ncbi.nlm.nih.gov/pubmed/37896498 http://dx.doi.org/10.3390/s23208406 |
Ejemplares similares
-
Center point to pose: Multiple views 3D human pose estimation for multi-person
por: Liu, Huan, et al.
Publicado: (2022) -
Multi-View-Based Pose Estimation and Its Applications on Intelligent Manufacturing
por: Yang, Haiwei, et al.
Publicado: (2020) -
Unsupervised multi-source domain adaptation with no observable source data
por: Jeon, Hyunsik, et al.
Publicado: (2021) -
Multi-view emotional expressions dataset using 2D pose estimation
por: Zhang, Mingming, et al.
Publicado: (2023) -
Single-view multi-human pose estimation by attentive cross-dimension matching
por: Tian, Wei, et al.
Publicado: (2023)