CSI-TextBench：用于语言关联环境感知的数据集与基准
CSI-TextBench: A Dataset and Benchmark for Language-Grounded Ambient Sensing Perception
AI总结：
本研究提出CSI-TextBench数据集与基准，将CSI数据与自然语言对齐，构建200万组训练元组，验证对比式对齐方法的性能，实现组合场景理解并优于特定分类器集成。
摘要：
由环境感知解码的室内上下文支撑着从辅助生活到智能建筑的诸多应用，但仍与现代多模态系统的语言对齐范式联系薄弱。通过数十亿物联网设备，环境WiFi信道状态信息（CSI）可通过无处不在、始终在线的基础设施被动捕捉人类活动与环境动态的室内上下文。然而，与视觉或音频不同，CSI缺乏字幕或转录本等自然配对文本，限制了其与语言驱动AI系统的集成。我们提出CSI-TextBench，这是一个用于对齐CSI数据与自然语言的大规模数据集和基准，将3个感知基准统一为7个任务下的285790个样本，并通过多对多分配将其与2291个分层结构、标签衍生的描述配对，构建了200万个CSI-文本训练元组。对来自4个范式家族的5种对齐方法进行基准测试，结果表明，对比式CSI-文本对齐在无类别标签的情况下可与监督分类器相匹配，能以少量样本适应未见类别，并响应开放词汇的自然语言提示。单个统一模型支持组合场景理解，回答关于活动、邻近度和身份的联合查询，在140个组合场景上达到86.9%的top-1准确率，优于任务特定分类器集成。CSI-TextBench将无处不在的环境感知作为语言索引的感知层，为语言驱动AI系统提供室内上下文感知能力。
英文摘要：
Indoor context deciphered by ambient sensing underpins many applications, from assisted living to smart buildings, yet remains weakly connected to the language-aligned paradigm of modern multimodal systems. Through billions of IoT devices, ambient WiFi Channel State Information (CSI) captures the indoor context of human activity and environmental dynamics passively via ubiquitous, always-on infrastructure. However, unlike vision or audio, CSI lacks naturally paired text like captions or transcripts, limiting its integration with language-driven AI systems. We present CSI-TextBench, a large-scale dataset and benchmark for aligning CSI data with natural language, unifying 3 sensing benchmarks into 285,790 samples across 7 tasks and pairing them with 2,291 hierarchically structured, label-derived descriptions via many-to-many assignment to construct 2.0 million CSI-text training tuples. Benchmarking 5 alignment methods from 4 paradigm families, we show that contrastive CSI-text alignment matches supervised classifiers without class labels, adapts to unseen classes with few samples, and responds to open-vocabulary natural-language prompts. A single unified model supports compositional scene understanding, answering joint queries over activity, proximity, and identity, achieving 86.9% top-1 accuracy on 140 composite scenes, outperforming task-specific classifier ensembles. CSI-TextBench enables ubiquitous ambient sensing as a language-indexed perception layer, enabling indoor contextual awareness in language-driven AI systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
