Structural topic model-based comparative review of human pose estimation research in the United States and China

Human pose estimation, a key area in computer vision, benefits various fields. The comparative study of research approaches in the United States and China, both leaders in this domain, is vital for understanding and influencing global trends in this technology. This review collected 191 influential papers from 2014 to 2022, sourced from Google Scholar. The Structural Topic Model (STM) was utilized to analyze research content, preferences, and trends in research topics. Specifically, 10 topics were summarized, and topic proportions, preferences, intensities, and word clouds were displayed via visualization methods. The findings revealed: 1) research on feature extraction and depth image constituted the largest proportion, approximately 12.2