mmWave sensing
PulseAugur coverage of mmWave sensing — every cluster mentioning mmWave sensing across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
RadarDINO framework distills visual AI into mmWave radar for human mesh reconstruction
Researchers have developed RadarDINO, a novel framework for human mesh reconstruction using mmWave radar. This approach distills visual semantics from the DINOv3 model into 3D radar representations, incorporating explic…
-
New mmWave radar tech identifies people by daily activities, not just gait
Researchers have developed a new method for person identification using millimeter-wave (mmWave) radar point clouds that extends beyond traditional gait analysis. The study introduces mm-ADL, a dataset featuring seven d…
-
MITO dataset and simulator advance non-line-of-sight perception with mmWave sensing
Researchers have introduced MITO, a novel dataset and simulator designed to enhance non-line-of-sight (NLOS) perception using millimeter-wave (mmWave) sensing. This dataset comprises over 24 million mmWave frames and 55…
-
mmWave sensing enables pixel-level hand localization with mmHand system
Researchers have developed mmHand, a novel system for precise hand localization using a single mmWave device. This privacy-preserving technology addresses limitations of existing methods, such as privacy concerns with v…
-
New PT$^3$ framework enhances human point cloud representation from mmWave sensing
Researchers have developed PT$^3$, a novel self-supervised pretraining framework designed to create generalizable human representations from millimeter-wave (mmWave) sensing data. This method utilizes shared prototypes …
-
mmPencil system uses mmWave radar and VLMs for in-air handwriting recognition
Researchers have developed mmPencil, a novel system for in-air handwriting recognition that utilizes mmWave radar sensing and large vision-language models (VLMs). This system reconstructs 3D handwriting trajectories fro…
-
New Wavelet Method Tackles Modality Inhibitance in Recommendation Systems
Researchers have identified a phenomenon called the "modality inhibitance effect" in multi-modal recommendation systems, where performance significantly degrades when transitioning from dual-modal to tri-modal configura…
-
GRADE system uses generative AI to improve radar depth estimation in poor visibility
Researchers have developed GRADE, a novel system for estimating high-fidelity metric depth from single-frame radar data, particularly under challenging visual conditions like smoke, fog, and darkness. GRADE leverages a …
-
New framework uses daily activities for mmWave person identification
Researchers have developed a new framework for person identification using millimeter-wave (mmWave) sensing that goes beyond traditional gait analysis. This approach leverages various activities of daily living (ADLs) t…
-
Graph Neural Networks Optimize mmWave Beamforming Using Sub-6 GHz CSI
Researchers have developed a novel beamforming method for millimeter-wave (mmWave) cell-free massive MIMO systems that utilizes graph neural networks (GNNs) to learn beamformers from sub-6 GHz channel state information …
-
UAV-gNB control system integrates aerial placement with per-user scheduling
Researchers have developed a hierarchical control system for tethered mmWave UAV-gNBs that integrates aerial placement with per-user scheduling. This system utilizes O-RAN disaggregation and a multi-timescale RIC archit…
-
New benchmark enables LLMs to understand mmWave radar data
Researchers have developed a novel method to enable large language models (LLMs) to process and understand millimeter-wave (mmWave) radar data. This approach involves converting mmWave point clouds into natural language…
-
New multimodal system enhances fall detection for elderly in bathrooms
Researchers have developed P2MFDS, a novel multimodal system designed to detect falls among elderly individuals in bathroom environments. This system integrates millimeter-wave radar and 3D vibration sensing to overcome…
-
New ML framework enhances 6G localization with RIS and mmWave sensing
Researchers have developed a new machine learning framework for precise localization in 6G networks utilizing reconfigurable intelligent surfaces (RIS) and millimeter-wave (mmWave) sensing. This method maps received sig…
-
New mmWave-language model mmMind bridges gap between radar sensing and LLMs
Researchers have developed mmMind, a novel radar-language model designed to enable large language models to understand human behavior in physical spaces. This model utilizes synchronized 3D pose data during training as …
-
Wave2Body framework uses radar to translate signals into human pose estimates
Researchers have introduced Wave2Body, a novel framework for human pose estimation using millimeter-wave (mmWave) radar. Unlike previous methods that directly regress joint coordinates, Wave2Body decouples learning targ…
-
HybridSim simulator generates realistic mmWave radar signals for human sensing
Researchers have developed HybridSim, a novel physics-learning hybrid simulator designed to generate realistic mmWave radar signals for dynamic human motion. This tool synthesizes signals by decoupling propagation into …
-
Privacy-preserving ergonomic assessment uses mmWave radar for REBA scoring
Researchers have developed a novel framework for privacy-preserving ergonomic assessments using millimetre-wave (mmWave) radar. This system reconstructs 3D human skeletons from radar data to estimate Rapid Entire Body A…
-
New dataset and model tackle heterogeneous mmWave action recognition
Researchers have introduced UniMM-HAR, a new dataset designed to address the challenges of heterogeneous multi-source scenarios in millimeter-wave (mmWave) radar human action recognition. This dataset is the largest of …
-
New system GaMi identifies materials using mmWave and acoustic sensing
Researchers have developed GaMi, a new system for identifying materials without physical contact, integrating mmWave and acoustic sensing. GaMi addresses challenges posed by varying object geometry and single-sensor lim…