Related papers: ExeChecker: Where Did I Go Wrong?

ExeChecker: Where Did I Go Wrong?

URL: http://arxiv.org/abs/2412.10573v1
Date: Fri, 13 Dec 2024 21:34:54 GMT
Title: ExeChecker: Where Did I Go Wrong?
Authors: Yiwen Gu, Mahir Patel, Margrit Betke,
Abstract summary: We present a contrastive learning based framework, ExeChecker, for the interpretation of rehabilitation exercises. Our work builds upon state-of-the-art advances in the area of human pose estimation, graph-attention neural networks, and transformer interpretablity.
Score: 6.8870493335438105
License:
Abstract: In this paper, we present a contrastive learning based framework, ExeChecker, for the interpretation of rehabilitation exercises. Our work builds upon state-of-the-art advances in the area of human pose estimation, graph-attention neural networks, and transformer interpretablity. The downstream task is to assist rehabilitation by providing informative feedback to users while they are performing prescribed exercises. We utilize a contrastive learning strategy during training. Given a tuple of correctly and incorrectly executed exercises, our model is able to identify and highlight those joints that are involved in an incorrect movement and thus require the user's attention. We collected an in-house dataset, ExeCheck, with paired recordings of both correct and incorrect execution of exercises. In our experiments, we tested our method on this dataset as well as the UI-PRMD dataset and found ExeCheck outperformed the baseline method using pairwise sequence alignment in identifying joints of physical relevance in rehabilitation exercises.

Related papers

Learning Hand State Estimation for a Light Exoskeleton [50.05509088121445]
We propose a machine learning-based estimator of the hand state for rehabilitation purposes, using light exoskeletons. We build a supervised approach using information from the muscular activity of the forearm and the motion of the exoskeleton to reconstruct the hand's opening degree and compliance level. Our approach is validated with a real light exoskeleton.
arXiv Detail & Related papers (2024-11-14T09:12:38Z)
Efficient Grammatical Error Correction Via Multi-Task Training and Optimized Training Schedule [55.08778142798106]
We propose auxiliary tasks that exploit the alignment between the original and corrected sentences. We formulate each task as a sequence-to-sequence problem and perform multi-task training. We find that the order of datasets used for training and even individual instances within a dataset may have important effects on the final performance.
arXiv Detail & Related papers (2023-11-20T14:50:12Z)
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)
Finding Similar Exercises in Retrieval Manner [11.694650259195756]
How to find similar exercises for a given exercise becomes a crucial technical problem. We define similar exercises'' as a retrieval process of finding a set of similar exercises based on recall, ranking and re-rank procedures. comprehensive representation of the semantic information of exercises was obtained through representation learning.
arXiv Detail & Related papers (2023-03-15T01:40:32Z)
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)
Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment [12.040334568268445]
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.
arXiv Detail & Related papers (2022-02-28T18:40:02Z)
An Empirical Study of Finding Similar Exercises [0.0]
We release a Chinese education pre-trained language model BERT$_Edu$ for the label-scarce dataset. We propose a very effective MoE enhanced multi-task model for FSE task to attain better understanding of exercises.
arXiv Detail & Related papers (2021-11-16T09:39:14Z)
Learning to Reweight with Deep Interactions [104.68509759134878]
We propose an improved data reweighting algorithm, in which the student model provides its internal states to the teacher model. Experiments on image classification with clean/noisy labels and neural machine translation empirically demonstrate that our algorithm makes significant improvement over previous methods.
arXiv Detail & Related papers (2020-07-09T09:06:31Z)
How Useful is Self-Supervised Pretraining for Visual Tasks? [133.1984299177874]
We evaluate various self-supervised algorithms across a comprehensive array of synthetic datasets and downstream tasks. Our experiments offer insights into how the utility of self-supervision changes as the number of available labels grows.
arXiv Detail & Related papers (2020-03-31T16:03:22Z)
DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction [96.90215318875859]
We show that bootstrapping-based Q-learning algorithms do not necessarily benefit from corrective feedback. We propose a new algorithm, DisCor, which computes an approximation to this optimal distribution and uses it to re-weight the transitions used for training.
arXiv Detail & Related papers (2020-03-16T16:18:52Z)

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