$P^{2}$ Net: Augmented Parallel-Pyramid Net for Attention Guided Pose Estimation

Hou, Luanxuan; Cao, Jie; Zhao, Yuan; Shen, Haifeng; Tang, Jian; He, Ran

doi:10.1109/icpr48806.2021.9412759

Search citation statements

Order By: Relevance

Paper Sections

Select...

Heuristic Methods1

Random Data Augmentation1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2021

2022

Publication Types

Select...

Other1

Article1

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike adversarial learning based methods, the second type instead aims to optimize the data augmentation application process. For instance, Hou et al [35] first defined a search space with different operators such as flipping, cropping, rotation. By treating the sequence of applying these operators as a trainable component, they turned this problem into a discrete optimization problem and solved it via an existing differentiable search algorithm [45].…”

Section: Heuristic Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Single Person Pose Estimation: A Survey

Zhang,

Zhu,

Wang

2021

Preprint

View full text Add to dashboard Cite

Human pose estimation in unconstrained images and videos is a fundamental computer vision task. To illustrate the evolutionary path in technique, in this survey we summarize representative human pose methods in a structured taxonomy, with a particular focus on deep learning models and single-person image setting. Specifically, we examine and survey all the components of a typical human pose estimation pipeline, including data augmentation, model architecture and backbone, supervision representation, post-processing, standard datasets, evaluation metrics. To envisage the future directions, we finally discuss the key unsolved problems and potential trends for human pose estimation.

show abstract

Section: Heuristic Methodsmentioning

confidence: 99%

“…Generic data augmentation [75,60] Pose-specific data augmentation [40,79,57] Optimized data augmentation Neural Architecture Search (NAS) based methods [35] Generative Adversarial Network (GAN) based methods [58] Deep human pose model…”

Section: Random Data Augmentationmentioning

confidence: 99%