Pith. sign in

REVIEW 12 cited by

BlazePose: On-device Real-time Body Pose tracking

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2006.10204 v1 pith:5BKTZVFU submitted 2020-06-17 cs.CV

Valentin Bazarevsky , Ivan Grishchenko , Karthik Raveendran , Tyler Zhu , Fan Zhang , Matthias Grundmann This is my paper · ORCID
classification cs.CV
keywords bodyposenetworkreal-timetrackingblazeposeestimationinference
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 86 citations worldwide. Full citation record

  1. RSC-GestureNet: Reliability-Aware Selective Causal Recognition of Chinese Traffic Police Gestures

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A reliability-aware causal recognizer with selective output outperforms prior models on Chinese traffic-police gesture recognition and on a new corruption benchmark.

  2. CG-MER: A Card Game-based Multimodal dataset for Emotion Recognition

    cs.AI 2025-01 reject novelty 6.0 of 10

    CG-MER is a new French multimodal emotion recognition dataset built from emotional card game sessions, offering RGB, depth, audio, and skeleton data with three annotation perspectives.

  3. Impact Detection in Fall Events: Leveraging Spatio-Temporal Graph Convolutional Networks and Recurrent Neural Networks Using 3D Skeletons Data

    cs.CV 2026-07 reject novelty 5.0 of 10

    A STGCN-GRU-BiLSTM model detects the frame of ground impact in falls from 3D skeleton data, reaching a reported 97.5% accuracy on a relabeled UP-Fall subset.

  4. Video-based detection of cessation of breathing in pre-term infants using machine learning

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Video-derived respiratory signals from 30 pre-term infants detect cessation of breathing with 76.9% balanced accuracy alone and 90.6% when fused with impedance pneumography.

  5. SEZ-HARN: Self-Explainable Zero-shot Human Activity Recognition Network

    cs.AI 2025-06 reject novelty 5.0 of 10

    SEZ-HARN recognizes unseen activities from IMU data and generates skeleton videos as explanations, but the videos are class-conditional renderings rather than faithful explanations of the decision.

  6. Metamorphic Testing for Pose Estimation Systems

    cs.SE 2025-02 conditional novelty 5.0 of 10

    MET-POSE uses metamorphic rules to test pose-estimation systems without ground-truth labels, and on Mediapipe Holistic it detects faults at similar or higher rates than classic labeled testing.

  7. Classifying Simulated Gait Impairments using Privacy-preserving Explainable Artificial Intelligence and Mobile Phone Videos

    cs.CV 2024-12 conditional novelty 5.0 of 10

    A mobile-phone pose-estimation pipeline with classic ML classifiers distinguishes seven simulated gait patterns at 86.5% accuracy on a new dataset, pending clinical validation.

  8. Real-Time Fitness Exercise Classification and Counting from Video Frames

    cs.CV 2024-11 conditional novelty 5.0 of 10

    A BiLSTM using 30-frame windows of joint angles plus raw coordinates reports 99% test accuracy on four exercises, with 95% and 88% accuracy on two additional real-world test sets.

  9. Toward Real-Time Sentence-Level Sign Language Translation

    cs.CL 2026-07 conditional novelty 4.0 of 10

    Streaming optimizations on a SHuBERT-ByT5 stack cut mean post-finalization SLT latency 27.7% to 1.35 s (P95 2.13 s) while scoring BLEU 15.9 on a How2Sign subset.

  10. Integrating Skeleton Based Representations for Robust Yoga Pose Classification Using Deep Learning Models

    cs.CV 2025-11 conditional novelty 4.0 of 10

    Skeleton-based inputs beat raw photos for yoga pose classification, with VGG16 plus MediaPipe skeletons reaching 96.09% on the new 16-class Yoga-16 dataset.

  11. WiFi based Human Fall and Activity Recognition using Transformer based Encoder Decoder and Graph Neural Networks

    cs.CV 2025-04 conditional novelty 4.0 of 10

    Wi-Fi CSI can be converted into 2D skeleton poses by a transformer encoder-decoder, and those poses support fall detection with about 90% accuracy in a 20-person in-house dataset.

  12. Robustifying Long-term Human-Robot Collaboration through a Multimodal and Hierarchical Framework

    cs.RO 2024-11 conditional novelty 4.0 of 10

    A vision-plus-speech, hierarchy-based robot assistant reduces assembly time by about 16% and reaches a 92% success rate in a 10-person long-term toy-car co-assembly study, though the reported gains lack statistical tests.

Pith tools