Human Pose Estimation (HPE) is the task that aims to predict the location of human joints
from images and videos. This task is used in many applications, such as sports analysis and …

In the field of human pose estimation, regression-based methods have been dominated in
terms of speed, while heatmap-based methods are far ahead in terms of performance. How …

In computer vision, it is often observed that formulating regression problems as a
classification task often yields better performance. We investigate this curious phenomenon …

In human and hand pose estimation, heatmaps are a crucial intermediate representation for
a body or hand keypoint. Two popular methods to decode the heatmap into a final joint …

Local counts, or the number of objects in a local area, is a continuous value by nature. Yet
recent state-of-the-art methods show that formulating counting as a classification task …

For tackling the task of 2D human pose estimation, the great majority of the recent methods
regard this task as a heatmap estimation problem, and optimize the heatmap prediction …

Human pose estimation typically encompasses three categories: heatmap-, regression-, and
integral-based methods. While integral-based methods possess advantages such as end-to …

Occlusion is a common challenge in human pose estimation. Curiously, learning from
occluded keypoints hinders a model to detect visible keypoints. We speculate that the …

Most 2D human pose estimation frameworks estimate keypoint confidence in an ad-hoc
manner, using heuristics such as the maximum value of heatmaps. The confidence is part of …

A standard hardware bottleneck when training deep neural networks is GPU memory. The
bulk of memory is occupied by caching intermediate tensors for gradient computation in the …