CVOct 15, 2025

Generalizing WiFi Gesture Recognition via Large-Model-Aware Semantic Distillation and Alignment

arXiv:2510.13390v11 citationsh-index: 2ICPADS
Originality Incremental advance
AI Analysis

This provides a scalable solution for generalized RF-based gesture interfaces in AIoT applications, though it appears incremental as it builds on existing WiFi sensing paradigms.

The paper tackles the problem of limited generalization and semantic expressiveness in WiFi-based gesture recognition by proposing GLSDA, a framework that leverages pre-trained large foundation models to enhance gesture representation learning. The method achieves state-of-the-art performance on the Widar3.0 benchmark in both in-domain and cross-domain tasks while reducing model size and inference latency.

WiFi-based gesture recognition has emerged as a promising RF sensing paradigm for enabling non-contact and privacy-preserving human-computer interaction in AIoT environments. However, existing methods often suffer from limited generalization and semantic expressiveness due to the domain-sensitive nature of Channel State Information and the lack of high-level gesture abstraction. To address these challenges, we propose a novel generalization framework, termed Large-Model-Aware Semantic Distillation and Alignment (GLSDA), which leverages the semantic prior of pre-trained large foundation models to enhance gesture representation learning in both in-domain and cross-domain scenarios. Specifically, we first design a dual-path CSI encoding pipeline that captures geometric and dynamic gesture patterns via CSI-Ratio phase sequences and Doppler spectrograms. These representations are then fed into a Multiscale Semantic Encoder, which learns robust temporal embeddings and aligns them with gesture semantics through cross-modal attention mechanisms. To further enhance category discrimination, we introduce a Semantic-Aware Soft Supervision scheme that encodes inter-class correlations and reduces label ambiguity, especially for semantically similar gestures. Finally, we develop a Robust Dual-Distillation strategy to compress the aligned model into a lightweight student network, jointly distilling intermediate features and semantic-informed soft labels from the teacher model. Extensive experiments on the Widar3.0 benchmark show that GLSDA consistently outperforms state-of-the-art methods in both in-domain and cross-domain gesture recognition tasks, while significantly reducing model size and inference latency. Our method offers a scalable and deployable solution for generalized RF-based gesture interfaces in real-world AIoT applications.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes