Background: Education in social determinants of health (SDH) has become an important part of medical curricula, facilitated increasingly through students' experiential learning with communities. The Community and Workplace Centred Learning Experience (CWCLE) module of the University of Saskatchewan, Canada, aims to integrate and extend second-year medical students' attitudes, skills, and knowledge about SDH and community resources. We aimed to 1) Assess module impact on student achievement of learning objectives, 2) Assess module impact on student attitudes toward SDH, 3) Obtain feedback from community partners and students about their community experiences, and 4) Use feedback to collaboratively develop recommendations to enhance the CWCLE module. Methods: We used a mixed-method approach to combine quantitative data with stories and personal experiences. We developed an online survey for two cohorts of students after completing the module, evaluating students' perceived abilities to perform the module's learning objectives and attitudes towards SDH. We invited representatives from community agencies involved in the CWCLE module to participate in focus groups. We also held separate focus groups with students who participated in the online survey to elaborate on their survey comments.

Repetitive counting (RepCount) is critical in various applications, such as fitness tracking and rehabilitation. Previous methods have relied on the estimation of red-greenand-blue (RGB) frames and body pose landmarks to identify the number of action repetitions, but these methods suffer from a number of issues, including the inability to stably handle changes in camera viewpoints, over-counting, under-counting, difficulty in distinguishing between subactions, inaccuracy in recognizing salient poses, etc. In this paper, based on the work done by [1], we integrate joint angles with body pose landmarks to address these challenges and achieve better results than the state-of-the-art RepCount methods, with a Mean Absolute Error (MAE) of 0.211 and an Off-By-One (OBO) counting accuracy of 0.599 on the RepCount data set [2]. Comprehensive experimental results demonstrate the effectiveness and robustness of our method.