BlazePose: On-device Real-time Body Pose tracking
Not on the map. Why?
Abstract (arXiv)
We present BlazePose, a lightweight convolutional neural network architecture for human pose estimation that is tailored for real-time inference on mobile devices. During inference, the network produces 33 body keypoints for a single person and runs at over 30 frames per second on a Pixel 2 phone. This makes it particularly suited to real-time use cases like fitness tracking and sign language recognition. Our main contributions include a novel body pose tracking solution and a lightweight body pose estimation neural network that uses both heatmaps and regression to keypoint coordinates.
Key facts. Cited by 113 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Jun 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 5; 2022: 10; 2023: 34; 2024: 29; 2025: 16; 2026: 19.
113 papers.
Sort:
By area:
- 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 175
- 2022Generative Neural Articulated Radiance Fieldscited by 101
- 2021HSPACE: Synthetic Parametric Humans Animated in Complex Environmentscited by 29
- 2024EventEgo3D: 3D Human Motion Capture from Egocentric Event Streamscited by 29
- 2023Vision-Based Human Pose Estimation via Deep Learning: A Surveycited by 20
- 2021COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modalitycited by 19
- 2023PoseRAC: Pose Saliency Transformer for Repetitive Action Countingcited by 17
- 2022BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimationcited by 13
- 2024Reading Between the Frames: Multi-Modal Depression Detection in Videos from Non-Verbal Cuescited by 11
- 2023Humans as Light Bulbs: 3D Human Reconstruction from Thermal Reflectioncited by 10
- 2024Biometrics and Behavior Analysis for Detecting Distractions in e-Learningcited by 10
- 2026MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generationcited by 10
38 more
- 2023Towards Single Camera Human 3D-Kinematicscited by 8
- 2021On-device Real-time Hand Gesture Recognitioncited by 6
- 2024HumMUSS: Human Motion Understanding using State Space Modelscited by 6
- 2024Automatic infant 2D pose estimation from videos: comparing seven deep neural network methodscited by 6
- 2023Full-Body Cardiovascular Sensing with Remote Photoplethysmographycited by 5
- 2023Towards the extraction of robust sign embeddings for low resource sign language recognitioncited by 5
- 2023VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViGcited by 5
- 2024The AffectToolbox: Affect Analysis for Everyonecited by 5
- 2024Design2Cloth: 3D Cloth Generation from 2D Maskscited by 5
- 2024WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair Userscited by 5
- 2024Optimizing Hand Region Detection in MediaPipe Holistic Full-Body Pose Estimation to Improve Accuracy and Avoid Downstream Errorscited by 5
- 2024A Medical Low-Back Pain Physical Rehabilitation Dataset for Human Body Movement Analysiscited by 5
- 2024WheelPoser: Sparse-IMU Based Body Pose Estimation for Wheelchair Userscited by 5
- 2023Using Learnable Physics for Real-Time Exercise Form Recommendationscited by 4
- 2025Clothes-Changing Person Re-identification Based On Skeleton Dynamicscited by 4
- 2023EMERSK -- Explainable Multimodal Emotion Recognition with Situational Knowledgecited by 3
- 2023Selecting the motion ground truth for loose-fitting wearables: benchmarking optical MoCap methodscited by 3
- 20233DYoga90: A Hierarchical Video Dataset for Yoga Pose Understandingcited by 3
- 2024Attention-based Shape and Gait Representations Learning for Video-based Cloth-Changing Person Re-Identificationcited by 3
- 2024Comparing Apples to Oranges: LLM-powered Multimodal Intention Prediction in an Object Categorization Taskcited by 3
- 2024The Influence of Faulty Labels in Data Sets on Human Pose Estimationcited by 3
- 2025Metamorphic Testing for Pose Estimation Systemscited by 3
- 2022Muscle Vision: Real Time Keypoint Based Pose Classification of Physical Exercisescited by 2
- 2022Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Rendererscited by 2
- 2022Protecting President Zelenskyy against Deep Fakescited by 2
- 2024Deep-Learning-Based Markerless Pose Estimation Systems in Gait Analysis: DeepLabCut Custom Training and the Refinement Functioncited by 2
- 2024Comparison of marker-less 2D image-based methods for infant pose estimationcited by 2
- 2025Action Recognition in Real-World Ambient Assisted Living Environmentcited by 2
- 2025SEZ-HARN: Self-Explainable Zero-shot Human Activity Recognition Networkcited by 2
- 2022Human Pose Driven Object Effects Recommendationcited by 1
- 2022Combining Efficient and Precise Sign Language Recognition: Good pose estimation library is all you needcited by 1
- 2022A Symbolic Representation of Human Posture for Interpretable Learning and Reasoningcited by 1
- 2023Multimodal Adaptive Fusion of Face and Gait Features using Keyless attention based Deep Neural Networks for Human Identificationcited by 1
- 2023Is end-to-end learning enough for fitness activity recognition?cited by 1
- 2023XFormer: Fast and Accurate Monocular 3D Body Capturecited by 1
- 2023Advancements in Repetitive Action Counting: Joint-Based PoseRAC Model With Improved Performancecited by 1
- 2023A webcam-based machine learning approach for three-dimensional range of motion evaluationcited by 1
- 2024Computer-Vision-Enabled Worker Video Analysis for Motion Amount Quantificationcited by 1
50 most cited of 113 All 113 (JSON)
- 2026Robust Real-Time Monocular Human Pose Estimation with Insole-Based Sensor Fusion14 Oct 2026
- 2026Impact of Patient Orientation in Single- and Multi-View Camera Environments for AI-based Rehabilitation Monitoring28 Sep 2026
- 2026STA-TFM: Spatio-Temporal Aggregation Across Views TransForMer for Pose Estimation21 Sep 2026
- 2026GenStream: Semantic Streaming Framework for Generative Reconstruction of Human-centric Media16 Sep 2026
- 2026Frame-Synchronous Hand Gesture Detection by Projected Winding Order7 Sep 2026
- 2026FISICA: A Deployed Service for Plantar-Pressure and Posture Assessment with Ontology-Grounded Recommendation29 Aug 2026
- 2026Markerless Pose Estimation for Resistance Training Technique Assessment25 Aug 2026
- 2026RSC-GestureNet: Reliability-Aware Selective Causal Recognition of Chinese Traffic Police Gestures3 Aug 2026
- 2026SAGE-Yoga: Multi-Cue Learning for Yoga Pose Classification and Joint-Level Correction28 Jul 2026
- 2026Impact Detection in Fall Events: Leveraging Spatio-Temporal Graph Convolutional Networks and Recurrent Neural Networks Using 3D Skeletons Data28 Jul 2026
- 2026Toward Real-Time Sentence-Level Sign Language Translation10 Jul 2026
- 2026Seeing Through Occlusion: Deterministic Arm Kinematic Correction for Robot Teleoperation17 Jun 2026
38 more
- 2026Measurement-Calibrated Multi-Camera Fusion for Vision-Based Indoor Localization11 Jun 2026
- 2026AIGaitor: Privacy-preserving and cloud-free motion analysis for everyone, using edge computing20 May 2026
- 2026MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation19 May 2026
- 2026BadmintonGRF: A Multimodal Dataset and Benchmark for Markerless Ground Reaction Force Estimation in Badminton3 May 2026
- 2026Emotion-Conditioned Short-Horizon Human Pose Forecasting with a Lightweight Predictive World Model26 Apr 2026
- 2026SignDATA: Data Pipeline for Sign Language Translation22 Apr 2026
- 2026Recognition of Daily Activities through Multi-Modal Deep Learning: A Video, Pose, and Object-Aware Approach for Ambient Assisted Living4 Mar 2026
- 2025Transformer-Driven Multimodal Fusion for Explainable Suspiciousness Estimation in Visual Surveillance10 Dec 2025
- 2025Integrating Skeleton Based Representations for Robust Yoga Pose Classification Using Deep Learning Models29 Nov 2025
- 2025Fusing Biomechanical and Spatio-Temporal Features for Fall Prediction: Characterizing and Mitigating the Simulation-to-Reality Gap18 Nov 2025
- 2025BdSL-SPOTER: A Transformer-Based Framework for Bengali Sign Language Recognition with Cultural Adaptation15 Nov 2025
- 2025Puzzle: Scheduling Multiple Deep Learning Models on Mobile Device with Heterogeneous Processors25 Aug 2025
- 2025Federated Action Recognition for Smart Worker Assistance Using FastPose18 Aug 2025
- 2025SEZ-HARN: Self-Explainable Zero-shot Human Activity Recognition Network25 Jun 2025
- 2025(LiFT) Lightweight Fitness Transformer: A language-vision model for Remote Monitoring of Physical Training6 Jun 2025
- 2025WiFi based Human Fall and Activity Recognition using Transformer based Encoder Decoder and Graph Neural Networks23 Apr 2025
- 2025Action Recognition in Real-World Ambient Assisted Living Environment29 Mar 2025
- 2025Validation of Human Pose Estimation and Human Mesh Recovery for Extracting Clinically Relevant Motion Data from Videos18 Mar 2025
- 2025Analyzing Swimming Performance Using Drone Captured Aerial Videos17 Mar 2025
- 2025Clothes-Changing Person Re-identification Based On Skeleton Dynamics13 Mar 2025
- 2025DIPSER: A Dataset for In-Person Student Engagement Recognition in the Wild27 Feb 2025
- 2025Metamorphic Testing for Pose Estimation Systems13 Feb 2025
- 2025CG-MER: A Card Game-based Multimodal dataset for Emotion Recognition14 Jan 2025
- 2024Classifying Simulated Gait Impairments using Privacy-preserving Explainable Artificial Intelligence and Mobile Phone Videos2 Dec 2024
- 2024Developing Normative Gait Cycle Parameters for Clinical Analysis Using Human Pose Estimation20 Nov 2024
- 2024Real-Time Fitness Exercise Classification and Counting from Video Frames18 Nov 2024
- 2024Estimation of Psychosocial Work Environment Exposures Through Video Object Detection. Proof of Concept Using CCTV Footage6 Nov 2024
- 2024ELMO: Enhanced Real-time LiDAR Motion Capture through Upsampling9 Oct 2024
- 2024Comparison of marker-less 2D image-based methods for infant pose estimation7 Oct 2024
- 2024WheelPoser: Sparse-IMU Based Body Pose Estimation for Wheelchair Users13 Sep 2024
- 2024The Influence of Faulty Labels in Data Sets on Human Pose Estimation5 Sep 2024
- 2024GMFL-Net: A Global Multi-geometric Feature Learning Network for Repetitive Action Counting31 Aug 2024
- 2024FAKER: Full-body Anonymization with Human Keypoint Extraction for Real-time Video Deidentification6 Aug 2024
- 2024Analyzing Data Efficiency and Performance of Machine Learning Algorithms for Assessing Low Back Pain Physical Rehabilitation Exercises5 Aug 2024
- 2024Automated Romberg Test: Leveraging a CNN and Centre of Mass Analysis for Sensory Ataxia Diagnosis25 Jul 2024
- 2024Deep-Learning-Based Markerless Pose Estimation Systems in Gait Analysis: DeepLabCut Custom Training and the Refinement Function15 Jul 2024
- 2024A Medical Low-Back Pain Physical Rehabilitation Dataset for Human Body Movement Analysis29 Jun 2024
- 2024Automatic infant 2D pose estimation from videos: comparing seven deep neural network methods25 Jun 2024
50 newest of 113 All 113 (JSON)
- 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 175
- 2022Generative Neural Articulated Radiance Fieldscited by 101
- 2021HSPACE: Synthetic Parametric Humans Animated in Complex Environmentscited by 29
- 2024EventEgo3D: 3D Human Motion Capture from Egocentric Event Streamscited by 29
- 2023Vision-Based Human Pose Estimation via Deep Learning: A Surveycited by 20
- 2021COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modalitycited by 19
- 2023PoseRAC: Pose Saliency Transformer for Repetitive Action Countingcited by 17
- 2022BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimationcited by 13
- 2024Reading Between the Frames: Multi-Modal Depression Detection in Videos from Non-Verbal Cuescited by 11
- 2023Humans as Light Bulbs: 3D Human Reconstruction from Thermal Reflectioncited by 10
- 2024Biometrics and Behavior Analysis for Detecting Distractions in e-Learningcited by 10
- 2026MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generationcited by 10
12 most cited of 112 All 112 (JSON)
- 2026Robust Real-Time Monocular Human Pose Estimation with Insole-Based Sensor Fusion14 Oct 2026
- 2026Impact of Patient Orientation in Single- and Multi-View Camera Environments for AI-based Rehabilitation Monitoring28 Sep 2026
- 2026STA-TFM: Spatio-Temporal Aggregation Across Views TransForMer for Pose Estimation21 Sep 2026
- 2026GenStream: Semantic Streaming Framework for Generative Reconstruction of Human-centric Media16 Sep 2026
- 2026Frame-Synchronous Hand Gesture Detection by Projected Winding Order7 Sep 2026
- 2026FISICA: A Deployed Service for Plantar-Pressure and Posture Assessment with Ontology-Grounded Recommendation29 Aug 2026
- 2026Markerless Pose Estimation for Resistance Training Technique Assessment25 Aug 2026
- 2026RSC-GestureNet: Reliability-Aware Selective Causal Recognition of Chinese Traffic Police Gestures3 Aug 2026
- 2026SAGE-Yoga: Multi-Cue Learning for Yoga Pose Classification and Joint-Level Correction28 Jul 2026
- 2026Impact Detection in Fall Events: Leveraging Spatio-Temporal Graph Convolutional Networks and Recurrent Neural Networks Using 3D Skeletons Data28 Jul 2026
- 2026Toward Real-Time Sentence-Level Sign Language Translation10 Jul 2026
- 2026Seeing Through Occlusion: Deterministic Arm Kinematic Correction for Robot Teleoperation17 Jun 2026
12 newest of 112 All 112 (JSON)