# DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition

Source: [DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition](<https://www.sota2.com/research/paper/6a02b441dbc836b87d8248b4>)

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

Data updated: 2026-07-04T05:01:04.041Z

Authors: Jiaying Lin, Shiman Wu, Jinfu Liu, Can Wang, Mengyuan Liu

Published: 2026-05-10T15:34:53.000Z

## Abstract

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.

## 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.

- [Human Activity Recognition on UniMM-HAR C-Sub](<https://www.sota2.com/research/sota/human-activity-recognition-on-unimm-har-c-sub.md>): Human Activity Recognition; UniMM-HAR C-Sub; Accuracy: 80.72.

- [Human Activity Recognition on UniMM-HAR (C-Set)](<https://www.sota2.com/research/sota/human-activity-recognition-on-unimm-har-c-set.md>): Human Activity Recognition; UniMM-HAR (C-Set); Accuracy: 81.82.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.09604>)

[PDF](<https://arxiv.org/pdf/2605.09604.pdf>)