The Language of Touch: Translating Vibrations into Text with Dual-Branch Learning
触觉的语言:通过双分支学习将振动转化为文本
机构 * Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information, Fuzhou University(福州大学福建省媒体信息智能处理与无线传输重点实验室) ; Fujian Science and Technology Innovation Laboratory for Optoelectronic Information of China(福建省光电信息科学与技术创新实验室) ; School of Artificial Intelligence, Hubei University(湖北大学人工智能学院) ; Key Laboratory of Intelligent Sensing System and Security, Hubei University and Ministry of Education(湖北大学及教育部智能感知系统与安全重点实验室) ; School of Computer Science and Engineering, South China University of Technology(华南理工大学计算机科学与工程学院)
专题命中 其他安全 :alignment(abstract);分类 cs.AI
AI总结 本文首次尝试解决触觉描述生成问题,提出ViPAC方法,通过双分支策略和动态融合机制处理触觉数据的周期性和非周期性特性,构建首个触觉-文本配对数据集LMT108-CAP,实验表明其在词汇准确性和语义对齐方面优于基线方法。
Comments 9 pages, 6 figures