This is the authors' abstract. We don't add key points for this paper.
The burgeoning field of embodied intelligence, which emphasizes the integration of physical presence with cognitive processes, has opened new avenues for advancing Human-Computer Interactions (HCI), particularly in the domain of smart personalized exercise monitoring. Despite the significant potential, current systems often struggle with the intricacies of multi-user environments, where the accuracy and reliability of exercise tracking are significantly challenged by the complexity of human behaviors and interactions. This paper proposes a multimodal fusion frame work for exercise monitoring system intergrating Radio Frequency Identification (RFID) and Computer Vision (CV), which is the first work to enhance personalized interaction perception in multi-user exercise monitoring scenarios. The system’s workflow is designed to encompass data acquisition, perception modeling, and exercise monitoring, ensuring a comprehensive analysis of exercise performance. The system can utilized multimodal data colledted from RFID and camera to identify who is holding which object and performing what activities. Extensive experi ments have been conducted to evaluate the performance of our system. The experimental results illustrate that the matching accuracy can reach 95%, and estimation accuracy can reach 94% on average.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: