提出DAP-Net模型，提升异构毫米波雷达动作识别的泛化能力
DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition
- 利用多普勒特征进行自适应几何增强与特征重校准
- 在异构雷达数据上达到最新准确率，跨源鲁棒性强
- 适用于真实场景中不同设备/频段雷达的动作识别
毫米波雷达提供隐私保护感知，在人体动作识别（HAR）中具有价值。现有毫米波点云数据集规模有限，且大多在同源单设备设置下采集，难以应对真实世界中因异构雷达源（如不同设备、频段）导致的分布偏移。为此，我们构建了首个大规模异构多源毫米波点云动作识别数据集UniMM-HAR，标准化三种不同雷达配置，用于评估跨源泛化能力。进一步提出多普勒感知点云网络（DAP-Net），通过增强模态内表示并实现跨模态对齐，学习源无关的动作语义。基于动作一致的时空多普勒模式作为锚点，双空间多普勒重参数化（D2R）模块实现样本自适应几何稠密化与多普勒引导特征重校准；文本对齐模块（TAM）利用预训练文本空间提供稳定语义锚点。实验表明，DAP-Net在异构雷达设置下显著优于现有方法，达到当前最优准确率并具备强跨源鲁棒性。
原文摘要 · Abstract (English)
Millimeter-wave (mmWave) radar provides privacy-preserving sensing and is valuable for human action recognition (HAR). Existing mmWave point cloud datasets are limited in scale and mostly collected under homogeneous single-source settings, preventing current methods from handling real-world distribution shifts caused by heterogeneous radar sources, such as different devices and frequency bands. To address this, we introduce UniMM-HAR, the largest and first mmWave point cloud HAR dataset for heterogeneous multi-source scenarios, standardizing three distinct radar configurations to realistically evaluate cross-source generalization. We further propose the Doppler-aware Point Cloud Network (DAP-Net) to tackle heterogeneity challenges. DAP-Net enhances intra-modal representations and performs cross-modal alignment to learn source-invariant action semantics. Leveraging action-consistent spatio-temporal Doppler patterns as anchors, the Dual-space Doppler Reparameterization (D2R) module performs sample-adaptive geometric densification and Doppler-guided feature recalibration, while the Text Alignment Module (TAM) provides stable semantic anchors via a pretrained textual space. Experiments show that DAP-Net significantly outperforms existing methods under heterogeneous radar settings, achieving state-of-the-art accuracy and strong cross-source robustness.
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。