# CubeLearn: End-to-end Learning for Human Motion Recognition from Raw mmWave Radar Signals

arXiv: https://arxiv.org/abs/2111.03976 · HTML: https://mlsanity.com/paper/2111.03976/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 46 references that are in the map.
- First posted on arXiv 7 Nov 2021.

## Builds on (most cited first, 6 of 6)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Unitary Evolution Recurrent Neural Networks](https://mlsanity.com/paper/1511.06464/) (2015)
- [Deep Complex Networks](https://mlsanity.com/paper/1705.09792/) (2017)
- [On Complex Valued Convolutional Neural Networks](https://mlsanity.com/paper/1602.09046/) (2016)
- [TinyRadarNN: Combining Spatial and Temporal Convolutional Neural Networks for Embedded Gesture Recognition with Short Range Radars](https://mlsanity.com/paper/2006.16281/) (2020)

## Built on by (most cited first, 18 of 18)

- [Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review](https://mlsanity.com/paper/2304.10410/) (2023)
- [T-FFTRadNet: Object Detection with Swin Vision Transformers from Raw ADC Radar Signals](https://mlsanity.com/paper/2303.16940/) (2023)
- [Exploring Radar Data Representations in Autonomous Driving: A Comprehensive Review](https://mlsanity.com/paper/2312.04861/) (2023)
- [milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing](https://mlsanity.com/paper/2306.17010/) (2023)
- [ADCNet: Learning from Raw Radar Data via Distillation](https://mlsanity.com/paper/2303.11420/) (2023)
- [MiliPoint: A Point Cloud Dataset for mmWave Radar](https://mlsanity.com/paper/2309.13425/) (2023)
- [Radar and Camera Fusion for Object Detection and Tracking: A Comprehensive Survey](https://mlsanity.com/paper/2410.19872/) (2024)
- [RETR: Multi-View Radar Detection Transformer for Indoor Perception](https://mlsanity.com/paper/2411.10293/) (2024)
- [RAPTR: Radar-based 3D Pose Estimation using Transformer](https://mlsanity.com/paper/2511.08387/) (2025)
- [REXO: Indoor Multi-View Radar Object Detection via 3D Bounding Box Diffusion](https://mlsanity.com/paper/2511.17806/) (2025)
- [Expanding mmWave Datasets for Human Pose Estimation with Unlabeled Data and LiDAR Datasets](https://mlsanity.com/paper/2603.14507/) (2026)
- [RadProPoser: Probabilistic Radar Tensor Human Pose Estimation That Knows Its Limits](https://mlsanity.com/paper/2508.03578/) (2025)
- [CF-Net: A Cross-Feature Reconstruction Network for High-Accuracy 1-Bit Target Classification](https://mlsanity.com/paper/2512.15105/) (2025)
- [RAVEN: Radar Adaptive Vision Encoders for Efficient Chirp-wise Object Detection and Segmentation](https://mlsanity.com/paper/2604.04490/) (2026)
- [RF-LEGO: Modularized Signal Processing-Deep Learning Co-Design for RF Sensing via Deep Unrolling](https://mlsanity.com/paper/2604.10183/) (2026)
- [PoHAR: Understanding Hyperlocal Human Activities with Pollution Sensor Networks](https://mlsanity.com/paper/2605.09434/) (2026)
- [DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition](https://mlsanity.com/paper/2605.09604/) (2026)
- [RF-HOI: Recognize Human-Object Interaction with Radio Frequency Signals](https://mlsanity.com/paper/2608.00289/) (2026)

## Abstract (arXiv)

mmWave FMCW radar has attracted huge amount of research interest for human-centered applications in recent years, such as human gesture/activity recognition. Most existing pipelines are built upon conventional Discrete Fourier Transform (DFT) pre-processing and deep neural network classifier hybrid methods, with a majority of previous works focusing on designing the downstream classifier to improve overall accuracy. In this work, we take a step back and look at the pre-processing module. To avoid the drawbacks of conventional DFT pre-processing, we propose a learnable pre-processing module, named CubeLearn, to directly extract features from raw radar signal and build an end-to-end deep neural network for mmWave FMCW radar motion recognition applications. Extensive experiments show that our CubeLearn module consistently improves the classification accuracies of different pipelines, especially benefiting those previously weaker models. We provide ablation studies on initialization methods and structure of the proposed module, as well as an evaluation of the running time on PC and edge devices. This work also serves as a comparison of different approaches towards data cube slicing. Through our task agnostic design, we propose a first step towards a generic end-to-end solution for radar recognition problems.