Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment

• URL: http://arxiv.org/abs/2202.14019v1
• Date: Mon, 28 Feb 2022 18:40:02 GMT
• Title: Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment
• Authors: Paritosh Parmar, Amol Gharat, Helge Rhodin
• Abstract summary: We propose to learn exercise-specific representations from unlabeled samples. In particular, our domain knowledge-informed self-supervised approaches exploit the harmonic motion of the exercise actions. We show that our self-supervised representations outperform off-the-shelf 2D- and 3D-pose estimators.
• Score: 12.040334568268445
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Maintaining proper form while exercising is important for preventing injuries and maximizing muscle mass gains. While fitness apps are becoming popular, they lack the functionality to detect errors in workout form. Detecting such errors naturally requires estimating users' body pose. However, off-the-shelf pose estimators struggle to perform well on the videos recorded in gym scenarios due to factors such as camera angles, occlusion from gym equipment, illumination, and clothing. To aggravate the problem, the errors to be detected in the workouts are very subtle. To that end, we propose to learn exercise-specific representations from unlabeled samples such that a small dataset annotated by experts suffices for supervised error detection. In particular, our domain knowledge-informed self-supervised approaches exploit the harmonic motion of the exercise actions, and capitalize on the large variances in camera angles, clothes, and illumination to learn powerful representations. To facilitate our self-supervised pretraining, and supervised finetuning, we curated a new exercise dataset, Fitness-AQA, comprising of three exercises: BackSquat, BarbellRow, and OverheadPress. It has been annotated by expert trainers for multiple crucial and typically occurring exercise errors. Experimental results show that our self-supervised representations outperform off-the-shelf 2D- and 3D-pose estimators and several other baselines.

Related papers

• Intelligent Repetition Counting for Unseen Exercises: A Few-Shot Learning Approach with Sensor Signals [0.4998632546280975]
  This study develops a method to automatically count exercise repetitions by analyzing IMU signals. We propose a repetition counting technique utilizing a deep metric-based few-shot learning approach. We show an 86.8% probability of accurately counting ten or more repetitions within a single set across 28 different exercises.
  arXiv  Detail & Related papers  (2024-10-01T05:04:40Z)
• Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective [80.51463286812314]
  Adversarial Training (AT) has become arguably the state-of-the-art algorithm for extracting robust features. AT suffers from severe robust overfitting problems, particularly after learning rate (LR) decay. We show how LR decay breaks the balance between the minimax game by empowering the trainer with a stronger memorization ability.
  arXiv  Detail & Related papers  (2023-10-30T09:00:11Z)
• Using Learnable Physics for Real-Time Exercise Form Recommendations [2.1548132286330453]
  We present an algorithmic pipeline that can diagnose problems in exercise techniques and offer corrective recommendations. We use MediaPipe for pose recognition, count repetitions using peak-prominence detection, and use a learnable physics simulator to track motion evolution.
  arXiv  Detail & Related papers  (2023-10-11T06:11:11Z)
• 3D Pose Based Feedback for Physical Exercises [87.35086507661227]
  We introduce a learning-based framework that identifies the mistakes made by a user. Our framework does not rely on hard-coded rules, instead, it learns them from data. Our approach yields 90.9% mistake identification accuracy and successfully corrects 94.2% of the mistakes.
  arXiv  Detail & Related papers  (2022-08-05T16:15:02Z)
• On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation [57.766049538913926]
  Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant. Much of the recent attention has shifted towards semi and (or) weakly supervised learning. We propose to impose multi-view geometrical constraints by means of a differentiable triangulation and to use it as form of self-supervision during training when no labels are available.
  arXiv  Detail & Related papers  (2022-03-29T19:11:54Z)
• PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision [102.48681650013698]
  Existing self-supervised 3D human pose estimation schemes have largely relied on weak supervisions to guide the learning. We propose a novel self-supervised approach that allows us to explicitly generate 2D-3D pose pairs for augmenting supervision. This is made possible via introducing a reinforcement-learning-based imitator, which is learned jointly with a pose estimator alongside a pose hallucinator.
  arXiv  Detail & Related papers  (2022-03-29T14:45:53Z)
• Deep Learning for Fitness [0.0]
  Fitness tutor is an application for maintaining correct posture during workout exercises or doing yoga. Inspired by healthcare innovations like robotic surgery, we design a novel application Fitness tutor which can guide the workouts using pose estimation.
  arXiv  Detail & Related papers  (2021-09-03T08:42:07Z)
• Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation [58.72192168935338]
  Generalizability of human pose estimation models developed using supervision on large-scale in-studio datasets remains questionable. We propose a novel kinematic-structure-preserved unsupervised 3D pose estimation framework, which is not restrained by any paired or unpaired weak supervisions. Our proposed model employs three consecutive differentiable transformations named as forward-kinematics, camera-projection and spatial-map transformation.
  arXiv  Detail & Related papers  (2020-06-24T23:56:33Z)
• Pose Trainer: Correcting Exercise Posture using Pose Estimation [7.005458308454871]
  Pose Trainer is an application that detects the user's exercise pose and provides personalized, detailed recommendations on how the user can improve their form. We record a dataset of over 100 exercise videos of correct and incorrect form, based on personal training guidelines, and build geometric-heuristic and machine learning algorithms for evaluation.
  arXiv  Detail & Related papers  (2020-06-21T05:51:37Z)
• Human Motion Transfer from Poses in the Wild [61.6016458288803]
  We tackle the problem of human motion transfer, where we synthesize novel motion video for a target person that imitates the movement from a reference video. It is a video-to-video translation task in which the estimated poses are used to bridge two domains. We introduce a novel pose-to-video translation framework for generating high-quality videos that are temporally coherent even for in-the-wild pose sequences unseen during training.
  arXiv  Detail & Related papers  (2020-04-07T05:59:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.