首页|Studies from Sangmyung University Reveal New Findings on Machine Learning (Swimt rans Net: a multimodal robotic system for swimming action recognition driven via Swin-Transformer)
Studies from Sangmyung University Reveal New Findings on Machine Learning (Swimt rans Net: a multimodal robotic system for swimming action recognition driven via Swin-Transformer)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New study results on artificial intell igence have been published. According to news originating from Seoul, South Kore a, by NewsRx correspondents, research stated, "IntroductionCurrently, using mach ine learning methods for precise analysis and improvement of swimming techniques holds significant research value and application prospects. The existing machin e learning methods have improved the accuracy of action recognition to some exte nt." The news correspondents obtained a quote from the research from Sangmyung Univer sity: "However, they still face several challenges such as insufficient data fea ture extraction, limited model generalization ability, and poor real-time perfor mance. MethodsTo address these issues, this paper proposes an innovative approac h called Swimtrans Net: A multimodal robotic system for swimming action recognit ion driven via Swin-Transformer. By leveraging the powerful visual data feature extraction capabilities of Swin- Transformer, Swimtrans Net effectively extracts swimming image information. Additionally, to meet the requirements of multimodal tasks, we integrate the CLIP model into the system. Swin-Transformer serves as the image encoder for CLIP, and through fine-tuning the CLIP model, it becomes c apable of understanding and interpreting swimming action data, learning relevant features and patterns associated with swimming. Finally, we introduce transfer learning for pre-training to reduce training time and lower computational resour ces, thereby providing real-time feedback to swimmers."
NETL
NSTL
