用文字提示提升无线传感模型性能，无需改架构也不增数据
Talk is Not Always Cheap: Promoting Wireless Sensing Models with Text Prompts
- 通过三种文本提示策略融合语义信息
- 多数据集验证，准确率最高提升13.68%
- 适合无线人体感知研究者快速部署
基于无线信号的人体感知技术（如WiFi、毫米波雷达、RFID）可非接触检测人体存在、姿态与活动，在公共安全、医疗健康和智慧环境中有重要应用。这些技术虽具非接触与环境适应性优势，但现有系统未能有效利用数据集中的文本信息。为此，我们提出新型文本增强框架WiTalk，通过三类分层提示策略——仅标签、简短描述、详细动作描述——无缝融入语义知识，无需修改模型结构且不增加额外数据成本。我们在三个公开基准数据集上验证：XRF55用于人体动作识别（HAR），WiFiTAL和XRFV2用于WiFi时序动作定位（TAL）。实验表明性能显著提升：在XRF55上，WiFi、RFID、mmWave的准确率分别提高3.9%、2.59%、0.46%；在WiFiTAL上，WiFiTAD平均性能提升4.98%；在XRFV2上，各类方法的mAP提升4.02%至13.68%。代码已开源：https://github.com/yangzhenkui/WiTalk。
原文摘要 · Abstract (English)
Wireless signal-based human sensing technologies, such as WiFi, millimeter-wave (mmWave) radar, and Radio Frequency Identification (RFID), enable the detection and interpretation of human presence, posture, and activities, thereby providing critical support for applications in public security, healthcare, and smart environments. These technologies exhibit notable advantages due to their non-contact operation and environmental adaptability; however, existing systems often fail to leverage the textual information inherent in datasets. To address this, we propose an innovative text-enhanced wireless sensing framework, WiTalk, that seamlessly integrates semantic knowledge through three hierarchical prompt strategies-label-only, brief description, and detailed action description-without requiring architectural modifications or incurring additional data costs. We rigorously validate this framework across three public benchmark datasets: XRF55 for human action recognition (HAR), and WiFiTAL and XRFV2 for WiFi temporal action localization (TAL). Experimental results demonstrate significant performance improvements: on XRF55, accuracy for WiFi, RFID, and mmWave increases by 3.9%, 2.59%, and 0.46%, respectively; on WiFiTAL, the average performance of WiFiTAD improves by 4.98%; and on XRFV2, the mean average precision gains across various methods range from 4.02% to 13.68%. Our codes have been included in https://github.com/yangzhenkui/WiTalk.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。