Zoomnas: searching for whole-body human pose estimation in the wild
This paper investigates the task of 2D whole-body human pose estimation, which aims to
localize dense landmarks on the entire human body including body, feet, face, and hands …
localize dense landmarks on the entire human body including body, feet, face, and hands …
Knowledge transfer evolutionary search for lightweight neural architecture with dynamic inference
Relying on the availability of massive labeled samples, most neural architecture search
(NAS) methods focus on searching large and complex models; and adopt fixed structures …
(NAS) methods focus on searching large and complex models; and adopt fixed structures …
Detecting and grouping keypoints for multi-person pose estimation using instance-aware attention
Bottom-up human pose estimation models detect keypoints and learn associative
information between keypoints, usually requiring human predefined offset fields or …
information between keypoints, usually requiring human predefined offset fields or …
MHCanonNet: Multi-Hypothesis Canonical lifting Network for self-supervised 3D human pose estimation in the wild video
Recent advancements in 3D Human Pose Estimation using fully-supervised learning
approach have shown impressive results; however, these methods heavily rely on large …
approach have shown impressive results; however, these methods heavily rely on large …
Vital information is only worth one thumbnail: Towards efficient human pose estimation
In pursuit of impressive performance, existing DCNN-based approaches of human pose
estimation usually use massive networks and large-size images to train a deep model …
estimation usually use massive networks and large-size images to train a deep model …
SED: Searching Enhanced Decoder with switchable skip connection for semantic segmentation
Neural architecture search (NAS) has shown excellent performance. However, existing
semantic segmentation models rely heavily on pre-training on Image-Net or COCO and …
semantic segmentation models rely heavily on pre-training on Image-Net or COCO and …
Momentum recursive DARTS
B Ma, Y Zhang, Y Xia - Pattern Recognition, 2024 - Elsevier
DARTS has emerged as a popular method for neural architecture search (NAS) owing to its
efficiency and simplicity. It employs gradient-based bi-level optimization to iteratively …
efficiency and simplicity. It employs gradient-based bi-level optimization to iteratively …
A systematic survey on human pose estimation: upstream and downstream tasks, approaches, lightweight models, and prospects
Z Gao, J Chen, Y Liu, Y Jin, D Tian - Artificial Intelligence Review, 2025 - Springer
In recent years, human pose estimation has been widely studied as a branch task of
computer vision. Human pose estimation plays an important role in the development of …
computer vision. Human pose estimation plays an important role in the development of …
Accurate-PGNet: Learning to Assemble Perceptual Body Parts for Accurate Human Skeleton Establishment
R Zhang, D Lin, X Wang, G Baciu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The human skeleton establishment aims to provide accurate localization information of the
human body from RGB images and establish a complete human skeleton for many …
human body from RGB images and establish a complete human skeleton for many …
Structure guided network for human pose estimation
Y Chen, X Xie, W Yin, B Li, F Li - Applied Intelligence, 2023 - Springer
Humans have an impressive ability to reliably perceive pose with semantic descriptions (eg
both arm up or left leg bent). To leverage the transitive structure characteristics for human …
both arm up or left leg bent). To leverage the transitive structure characteristics for human …