mlsanityData to 14 Oct 2026

3D Pose Based Feedback for Physical Exercises

arXiv 2208.03257 ↗First posted 5 Aug 2022cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Unsupervised self-rehabilitation exercises and physical training can cause serious injuries if performed incorrectly. We introduce a learning-based framework that identifies the mistakes made by a user and proposes corrective measures for easier and safer individual training. Our framework does not rely on hard-coded, heuristic rules. Instead, it learns them from data, which facilitates its adaptation to specific user needs. To this end, we use a Graph Convolutional Network (GCN) architecture acting on the user's pose sequence to model the relationship between the body joints trajectories. To evaluate our approach, we introduce a dataset with 3 different physical exercises. Our approach yields 90.9% mistake identification accuracy and successfully corrects 94.2% of the mistakes.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 28 of its 43 references that are in the map. First posted on arXiv 5 Aug 2022.

Builds on

28 of 43 references.

References · 28

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  3. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 803
  4. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 686
  5. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  6. 2017On human motion prediction using recurrent neural networkscited by 338
  7. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
  8. 2017Soft-DTW: a Differentiable Loss Function for Time-Seriescited by 271
  9. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 246
  10. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
  11. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
  12. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
16 more
  1. 2020History Repeats Itself: Human Motion Prediction via Motion Attentioncited by 165
  2. 2016Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognitioncited by 143
  3. 2019Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognitioncited by 135
  4. 2020A Spatio-temporal Transformer for 3D Human Motion Predictioncited by 133
  5. 2016An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Datacited by 126
  6. 2018Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregationcited by 106
  7. 2017Deep representation learning for human motion prediction and classificationcited by 98
  8. 2018View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognitioncited by 84
  9. 2021Multi-Person Extreme Motion Predictioncited by 75
  10. 2017Learning Human Motion Models for Long-term Predictionscited by 67
  11. 2019Imitation Learning for Human Pose Predictioncited by 44
  12. 2022PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervisioncited by 25
  13. 2020Pose Trainer: Correcting Exercise Posture using Pose Estimationcited by 18
  14. 2020Motion Prediction Using Temporal Inception Modulecited by 10
  15. 2021Dyadic Human Motion Predictioncited by 9
  16. 2020Long Term Motion Prediction Using Keyposescited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 4; 2025: 3; 2026: 1.

11 papers.

  1. 2023PoseFix: Correcting 3D Human Poses with Natural Languagecited by 40
  2. 2022FLAG3D: A 3D Fitness Activity Dataset with Language Instructioncited by 23
  3. 2024ExpertAF: Expert Actionable Feedback from Videocited by 17
  4. 2025Video Action Differencingcited by 14
  5. 2025Mojito: LLM-Aided Motion Instructor with Jitter-Reduced Inertial Tokenscited by 4
  6. 2023MAAIG: Motion Analysis And Instruction Generationcited by 1
  7. 2024Rehabilitation Exercise Quality Assessment through Supervised Contrastive Learning with Hard and Soft Negativescited by 1
  8. 2024Online Action Representation using Change Detection and Symbolic Programmingcited by 1
  9. 2025Real-Time Feedback and Benchmark Dataset for Isometric Pose Evaluationcited by 1
  10. 2026FitAQA: A Benchmark of Fitness Action Quality Assessment for Multimodal Large Language Modelscited by 1
  11. 2024Video-based Exercise Classification and Activated Muscle Group Prediction with Hybrid X3D-SlowFast Networkcited by 0