# WiFi2Cap: Semantic Action Captioning from Wi-Fi CSI via Limb-Level Semantic Alignment

Source: [WiFi2Cap: Semantic Action Captioning from Wi-Fi CSI via Limb-Level Semantic Alignment](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6467>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-26T05:00:04.122Z

Authors: Tzu-Ti Wei, Chu-Yu Huang, Yu-Chee Tseng, Jen-Jee Chen

Published: 2026-03-24T01:30:46.000Z

## Abstract

Privacy-preserving semantic understanding of human activities is important for indoor sensing, yet existing Wi-Fi CSI-based systems mainly focus on pose estimation or predefined action classification rather than fine-grained language generation. Mapping CSI to natural-language descriptions remains challenging because of the semantic gap between wireless signals and language and direction-sensitive ambiguities such as left/right limb confusion. We propose WiFi2Cap, a three-stage framework for generating action captions directly from Wi-Fi CSI. A vision-language teacher learns transferable supervision from synchronized video-text pairs, and a CSI student is aligned to the teacher's visual space and text embeddings. To improve direction-sensitive captioning, we introduce a Mirror-Consistency Loss that reduces mirrored-action and left-right ambiguities during cross-modal alignment. A prefix-tuned language model then generates action descriptions from CSI embeddings. We also introduce the WiFi2Cap Dataset, a synchronized CSI-RGB-sentence benchmark for semantic captioning from Wi-Fi signals. Experimental results show that WiFi2Cap consistently outperforms baseline methods on BLEU-4, METEOR, ROUGE-L, CIDEr, and SPICE, demonstrating effective privacy-friendly semantic sensing.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Captioning on WiFi2Cap](<https://www.sota2.com/research/sota/captioning-on-wifi2cap.md>): Captioning; WiFi2Cap; BLEU-4: 51.78.

- [Captioning on Person-in-WiFi 3D Single-person](<https://www.sota2.com/research/sota/captioning-on-person-in-wifi-3d-single-person.md>): Captioning; Person-in-WiFi 3D Single-person; BLEU-4: 47.07.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.22690>)

[PDF](<https://arxiv.org/pdf/2603.22690.pdf>)
