Millimeter-wave (mmWave) radar has attracted increasing research interest for contactless gesture recognition. However, in practical deployment, models trained on existing users often exhibit significant performance degradation when applied to unseen users. This decline arises because each user constitutes a distinct domain with unique behavioral patterns and physiological characteristics, leading to severe cross-domain distribution shifts in radar signal features. To address these challenges, we propose a two-stage few-shot gesture recognition adaptation method. During pre-training, a dual-prototype consistency strategy is proposed to explicitly align user-specific sub-distributions within each gesture class, overcoming the limitation of conventional methods that treat multiple source users as a single monolithic domain and thereby enhancing the model’s transferability to unseen users. In the adaptation stage, we perform source-free and lightweight fine-tuning using only a few labeled samples from the target domain, while avoiding the computational burden and privacy concerns of joint training. Specifically, a variational autoencoder (VAE)–based latent-space regularization with z-space alignment is employed to achieve stable and accurate recognition for the new target domain. Furthermore, Knowledge Distillation (KD) and L2 regularization toward the starting point (L2-SP) are incorporated to mitigate overfitting and prevent catastrophic forgetting of the source gesture knowledge. Experiments on a multi-subject mmWave gesture dataset show that the proposed method significantly improves recognition performance for the target domains and maintains high accuracy on the original users. Visualization analyses further confirm effective latent-space semantic alignment with minimal supervision.

This paper presents a novel mmWave-based aerial text input method that allows users to write freely through hand movements in the air, effectively recognizing English words. Unlike existing radar character recognition methods that require pauses between adjacent letters for segmentation, the proposedmmScribesystem supports continuous handwriting and streaming recognition. Our approach first utilizes Frequency-Modulated Continuous Wave (FMCW) mmWave radar to extract micro-Doppler time series features characterizing gesture movements. Then, a hybrid CTC/attention architecture baseline method is proposed to achieve end-to-end (E2E) text output without explicit letter segmentation. By introducing a dynamic block training strategy, the model can process contextual data of arbitrary length. During inference, the connectionist temporal classification (CTC) decoder generates n-best hypotheses at the character level in a streaming manner, while the attention decoder subsequently re-scores these hypotheses to update the final result at the text level. We have constructed the first word-level handwriting dataset for mmWave radar, and also conducted a comprehensive evaluation of the proposed method on this dataset. The results demonstrate that the method exhibits excellent performance. Furthermore, when deployed on mobile devices, mmScribe maintains its outstanding performance with minimal latency. Our code and dataset are available at:https://github.com/Tkwer/mmScribe.

In the scenario of ultrashort range (USR) gesture interaction, the joint range-angle parameter estimation encounters numerous challenges when using multiple-input-multiple-output (MIMO) frequency-modulated continuous-wave (FMCW) millimeter-wave (mmWave) radar. In signal modeling, the traditional far-field plane-wave assumption breaks down due to the hand motion spanning the near-field and far-field regions. Moreover, the hand target exhibits a significant angular extent in USR, making a distributed source model more realistic than a point target model. For joint parameter estimation, while the wideband FMCW signal improves range resolution, it may introduce direction-of-arrival (DOA) estimation bias and ambiguities. To address these issues, this article establishes a spherical wavefront distributed source signal model applicable to hybrid-field scenarios, which accurately reflects real-world signal propagation in USR. We analyze the errors induced by traditional signal processing algorithms, and proposes a joint range-DOA estimation algorithm for spatial localization. This method initially performs meticulous peak alignment within the range domain to correct for phase residuals from wideband signals. It then iteratively processes each range-bin data using a 2-D Capon angle estimation algorithm, which is based on the spherical wavefront MIMO radar array model, for joint estimation. Ultimately, the target’s Cartesian coordinates are computed utilizing an elliptic geometric model. Our simulations and real-data results both validate the effectiveness of the proposed model and method.