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 …

Inferring human pose from a monocular RGB image remains an interesting field of research
in computer vision. It serves as a fundamental key for many real-world applications …

The recently-developed DETR approach applies the transformer encoder and decoder
architecture to object detection and achieves promising performance. In this paper, we …

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 …

We introduce YOLO-pose, a novel heatmap-free approach for joint detection, and 2D multi-
person pose estimation in an image based on the popular YOLO object detection …

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 …

Pose estimation plays a critical role in human-centered vision applications. However, it is
difficult to deploy state-of-the-art HRNet-based pose estimation models on resource …

Human pose is typically represented by a coordinate vector of body joints or their heatmap
embeddings. While easy for data processing, unrealistic pose estimates are admitted due to …

The existing multi-person absolute 3D pose estimation methods are mainly based on two-
stage paradigm, ie, top-down or bottom-up, leading to redundant pipelines with high …

In keypoint estimation tasks such as human pose estimation, heatmap-based regression is
the dominant approach despite possessing notable drawbacks: heatmaps intrinsically suffer …