<p>Human pose estimation (HPE) from images or video is not only a major issue of computer vision, but also it plays a vital role in many real-world applications. The most challenging problems of human pose estimation are the disparity of poses, disturbing background clutter, different camera views, changes in scene lighting conditions, and occlusion. To solve these issues, a significant amount of research effort has been considered in the past. In this paper, we explore various vision-based activity recognition using 2D and 3D human pose estimations. We explore the conventional system, which includes both statistical and deep learning-based approaches for HPE, and then explore the current progress of each one in comparison to existing ones. At last, we also present various current state-of-the-art human activity recognition (HAR) techniques that use HPE for recognition.</p>