Deep learning-based human pose estimation: A survey

C Zheng, W Wu, C Chen, T Yang, S Zhu, J Shen… - ACM Computing …, 2023 - dl.acm.org
Human pose estimation aims to locate the human body parts and build human body
representation (eg, body skeleton) from input data such as images and videos. It has drawn …

A review of multimodal human activity recognition with special emphasis on classification, applications, challenges and future directions

SK Yadav, K Tiwari, HM Pandey, SA Akbar - Knowledge-Based Systems, 2021 - Elsevier
Human activity recognition (HAR) is one of the most important and challenging problems in
the computer vision. It has critical application in wide variety of tasks including gaming …

Physical inertial poser (pip): Physics-aware real-time human motion tracking from sparse inertial sensors

X Yi, Y Zhou, M Habermann… - Proceedings of the …, 2022 - openaccess.thecvf.com
Motion capture from sparse inertial sensors has shown great potential compared to image-
based approaches since occlusions do not lead to a reduced tracking quality and the …

Gfpose: Learning 3d human pose prior with gradient fields

H Ci, M Wu, W Zhu, X Ma, H Dong… - Proceedings of the …, 2023 - openaccess.thecvf.com
Learning 3D human pose prior is essential to human-centered AI. Here, we present GFPose,
a versatile framework to model plausible 3D human poses for various applications. At the …

Emdb: The electromagnetic database of global 3d human pose and shape in the wild

M Kaufmann, J Song, C Guo, K Shen… - Proceedings of the …, 2023 - openaccess.thecvf.com
We present EMDB, the Electromagnetic Database of Global 3D Human Pose and Shape in
the Wild. EMDB is a novel dataset that contains high-quality 3D SMPL pose and shape …

A review of 3D human pose estimation algorithms for markerless motion capture

Y Desmarais, D Mottet, P Slangen… - Computer Vision and …, 2021 - Elsevier
Human pose estimation is a very active research field, stimulated by its important
applications in robotics, entertainment or health and sports sciences, among others …

Transformer inertial poser: Real-time human motion reconstruction from sparse imus with simultaneous terrain generation

Y Jiang, Y Ye, D Gopinath, J Won, AW Winkler… - SIGGRAPH Asia 2022 …, 2022 - dl.acm.org
Real-time human motion reconstruction from a sparse set of (eg six) wearable IMUs
provides a non-intrusive and economic approach to motion capture. Without the ability to …

Faster voxelpose: Real-time 3d human pose estimation by orthographic projection

H Ye, W Zhu, C Wang, R Wu, Y Wang - European Conference on …, 2022 - Springer
While the voxel-based methods have achieved promising results for multi-person 3D pose
estimation from multi-cameras, they suffer from heavy computation burdens, especially for …

Learning analytical posterior probability for human mesh recovery

Q Fang, K Chen, Y Fan, Q Shuai… - Proceedings of the …, 2023 - openaccess.thecvf.com
Despite various probabilistic methods for modeling the uncertainty and ambiguity in human
mesh recovery, their overall precision is limited because existing formulations for joint …

Adafuse: Adaptive multiview fusion for accurate human pose estimation in the wild

Z Zhang, C Wang, W Qiu, W Qin, W Zeng - International Journal of …, 2021 - Springer
Occlusion is probably the biggest challenge for human pose estimation in the wild. Typical
solutions often rely on intrusive sensors such as IMUs to detect occluded joints. To make the …