Human Activity Recognition Transformer (HART) is a transformer based architecture that has been specifically adapted for IMU sensing devices. Findings shows that HART uses fewer paremeters, FLOPs and achieves state-of-the-art results.
☆78Dec 10, 2024Updated last year
Alternatives and similar repositories for Lightweight-Transformer-Models-For-HAR-on-Mobile-Devices
Users that are interested in Lightweight-Transformer-Models-For-HAR-on-Mobile-Devices are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Intertial-based Human Activity Recognition with Transformers☆95Jun 18, 2026Updated last month
- Transformer for Human Activity Recognition☆78Jan 18, 2023Updated 3 years ago
- Improving Human Activity Recognition through Self-training with Unlabeled Data☆43Jul 13, 2021Updated 5 years ago
- An up-to-date & curated list of Awesome IMU-based Human Activity Recognition(Ubiquitous Computing) papers, methods & resources. Please no…☆338Nov 29, 2024Updated last year
- Developing a Convolutional LSTM model for human posture recognition from wearable IMUs sensors☆13Aug 2, 2020Updated 5 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆11Aug 17, 2022Updated 3 years ago
- ☆91Jun 16, 2023Updated 3 years ago
- [PAKDD-2021] Hierarchical Self Attention Based Autoencoder for Open-Set Human Activity Recognition☆17May 23, 2023Updated 3 years ago
- iOS indoor map app for Aalto University☆10Dec 14, 2016Updated 9 years ago
- Improving Deep Learning for HAR with shallow LSTMs (best paper award), Bock et al., presented at ISWC 2021 (online)☆63Mar 21, 2025Updated last year
- Four Federated learning datasets for Human Activity Recognition☆57Jul 8, 2023Updated 3 years ago
- 3-layer-CNN and ResNet with OPPORTUNITY dataset, PAMAP2 dataset, UCI-HAR dataset, UniMiB-SHAR dataset, USC-HAD dataset, and WISDM dataset…☆61May 21, 2022Updated 4 years ago
- MotionSense Dataset for Human Activity and Attribute Recognition ( time-series data generated by smartphone's sensors: accelerometer and …☆368Oct 19, 2021Updated 4 years ago
- Official implementation of SWL-Adapt.☆14Apr 4, 2023Updated 3 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Code for the paper, SAMoSA - Sensing Activities with Motion and Sub-sampled Audio☆19Jan 24, 2023Updated 3 years ago
- DANA: Dimension-Adaptive Neural Architecture (UbiComp'21)( ACM IMWUT)☆47Oct 25, 2021Updated 4 years ago
- Accelerometer app built in SwiftUI, support for Apple Watch☆14Aug 21, 2021Updated 4 years ago
- Simulates human body pose from IMU data in unity☆11Sep 25, 2020Updated 5 years ago
- A python based imu AHRS system to provide position data from gyroscope and acceleration sensors. It is based on the Open source IMU and A…☆13Oct 24, 2017Updated 8 years ago
- 室内行人移动方位推算技术 (Pedestrian Dead Reckoning, PDR)☆98Dec 2, 2022Updated 3 years ago
- Data and Code of the paper Survey of Motion Tracking Methods Based on Inertial Sensors: A Focus on Upper Limb Human Motion☆34Jun 14, 2017Updated 9 years ago
- This is temporal repository for 3-D human motion tracking from videos and/or IMUs☆16Apr 9, 2023Updated 3 years ago
- The MHEALTH (Mobile Health) dataset is devised to benchmark techniques dealing with human behavior analysis based on multimodal body sens…☆26Mar 10, 2021Updated 5 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- [T-CSVT 2021]: DeepOIS: Gyroscope-Guided Deep Optical Image Stabilizer Compensation☆11Jul 4, 2023Updated 3 years ago
- MAINS: A Magnetic Field Aided Inertial Navigation System for Indoor Positioning☆41Jun 2, 2025Updated last year
- MATLAB implementation of gait cycle validation and segmentation using inertial sensors.☆18Jun 11, 2021Updated 5 years ago
- A dataset of egocentric vision, eye-tracking and full body kinematics from human locomotion in out-of-the-lab environments. Also, differe…☆12Nov 5, 2023Updated 2 years ago
- Baseline Machine Learning models for the Human Activity Recognition Trondheim (HARTH) dataset☆45Jan 13, 2025Updated last year
- Code for data processing used for the experiment in paper "Deepsense: a unified deep learning framework for time-series mobile sensing da…☆29Jul 15, 2017Updated 9 years ago
- Ensembles of Deep LSTM Learners for Human Activity Recognition using Wearables in Pytorch☆15May 22, 2019Updated 7 years ago
- Using Machine Learning to determine Human Activity using data from 6 d.o.f. IMU sensor.☆19Apr 14, 2020Updated 6 years ago
- Code for our IJCAI 2019 paper "A Novel Distribution-Embedded Neural Network for Sensor-Based Activity Recognition".☆17Mar 18, 2020Updated 6 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Contrastive Learning (SimCLR) for Human Activity Recognition☆81Apr 6, 2021Updated 5 years ago
- ActiveHARNet: Towards On-Device Deep Bayesian Active Learning for Human Activity Recognition☆16Nov 7, 2020Updated 5 years ago
- Custom Keras ML block example for Edge Impulse☆12Updated this week
- This is an implementation based on this paper, "ECG arrhythmia classification using a 2-D convolutional neural network", Tae Joon Jun et …☆32Mar 2, 2020Updated 6 years ago
- Pytorch implementation of Spiking Neural Networks for Human Activity Recognition.☆21Dec 11, 2022Updated 3 years ago
- Self-supervised learning for wearables using the UK-Biobank (>700,000 person-days)☆162Oct 24, 2024Updated last year
- CZU-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and 10 wearable inertial sensors☆26Jun 2, 2022Updated 4 years ago