Deep learning-based human pose estimation: A survey
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 …
representation (eg, body skeleton) from input data such as images and videos. It has drawn …
Recent advances of monocular 2d and 3d human pose estimation: A deep learning perspective
Estimation of the human pose from a monocular camera has been an emerging research
topic in the computer vision community with many applications. Recently, benefiting from the …
topic in the computer vision community with many applications. Recently, benefiting from the …
Alphapose: Whole-body regional multi-person pose estimation and tracking in real-time
Accurate whole-body multi-person pose estimation and tracking is an important yet
challenging topic in computer vision. To capture the subtle actions of humans for complex …
challenging topic in computer vision. To capture the subtle actions of humans for complex …
Vitpose: Simple vision transformer baselines for human pose estimation
Although no specific domain knowledge is considered in the design, plain vision
transformers have shown excellent performance in visual recognition tasks. However, little …
transformers have shown excellent performance in visual recognition tasks. However, little …
Instructdiffusion: A generalist modeling interface for vision tasks
We present InstructDiffusion a unified and generic framework for aligning computer vision
tasks with human instructions. Unlike existing approaches that integrate prior knowledge …
tasks with human instructions. Unlike existing approaches that integrate prior knowledge …
Revealing the dark secrets of masked image modeling
Masked image modeling (MIM) as pre-training is shown to be effective for numerous vision
downstream tasks, but how and where MIM works remain unclear. In this paper, we compare …
downstream tasks, but how and where MIM works remain unclear. In this paper, we compare …
Multi-animal pose estimation, identification and tracking with DeepLabCut
Estimating the pose of multiple animals is a challenging computer vision problem: frequent
interactions cause occlusions and complicate the association of detected keypoints to the …
interactions cause occlusions and complicate the association of detected keypoints to the …
Bottom-up human pose estimation via disentangled keypoint regression
In this paper, we are interested in the bottom-up paradigm of estimating human poses from
an image. We study the dense keypoint regression framework that is previously inferior to …
an image. We study the dense keypoint regression framework that is previously inferior to …
Human pose regression with residual log-likelihood estimation
Heatmap-based methods dominate in the field of human pose estimation by modelling the
output distribution through likelihood heatmaps. In contrast, regression-based methods are …
output distribution through likelihood heatmaps. In contrast, regression-based methods are …
End-to-end multi-person pose estimation with transformers
Current methods of multi-person pose estimation typically treat the localization and
association of body joints separately. In this paper, we propose the first fully end-to-end multi …
association of body joints separately. In this paper, we propose the first fully end-to-end multi …