GYMetricPose: A light-weight angle-based graph adaptation for action quality assessment

计算机科学 适应(眼睛) 图形 质量(理念) 质量评定 动作(物理) 人工智能 理论计算机科学 可靠性工程 光学 工程类 物理 评价方法 量子力学
作者
Ulises Gallardo,Fernando Caro,Eluney Hernández,Ricardo Espinosa,Gilberto Ochoa‐Ruiz
标识
DOI:10.1109/cbms61543.2024.00016
摘要

Improving the overall quality of exercise is crucial for achieving effective and safe techniques during gym workouts. Moreover, identifying errors during workouts can optimize training benefits and minimize the risk of injury. In this paper, we propose a cross-domain method to exploit angle information in human pose skeletons, aiming to detect fine-grained posture problems in complex real-world environments. Specifically, we integrate the Geometric Representation Extraction (GRE) module along with transformer-based pose estimation. Our approach demonstrates efficacy on the Fitness-AQA dataset, which comprises authentic exercise samples captured in real-world gym settings. This performance is achieved after pose estimation with approximately 164k parameters in its base configuration. The experimental results highlight that our method is a competitive approach compared to self-supervised video/image approaches in complex environments. In the Back Squat exercise, our method outperforms Motion Disentangling (MD) in detecting Knee Inward Error (KIE) with an F1-score of 0.4398. For Static Shallow Squat Error, it achieved the second-best F1-score of 0.8677, just 0.0017 below Cross-View Cross-Subject Pose Contrastive Learning (CVCSPC). In the Overhead Press exercise, the method significantly improved the detection of Knee error, achieving an F1-score of 0.8160, surpassing CVCSPC and other methods. Overall, these results demonstrate that the proposed method provides competitive performance compared to the state-of-the-art models while using ≈ 187x fewer parameters than the model with the highest performance in the AQA dataset, the Motion Disentangling (MD) approach. Code will be available at: https://github.com/CaroFernando/GymPose
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
yxb完成签到 ,获得积分20
刚刚
wanci的应助被钟梓袄采纳,获得10
1秒前
秋风的应助被钟梓袄采纳,获得10
1秒前
顾矜的应助被钟梓袄采纳,获得10
1秒前
领导范儿的应助被钟梓袄采纳,获得10
1秒前
香蕉觅云的应助被0911采纳,获得10
1秒前
嘻嘻哈哈发布了新的文献求助210
1秒前
卓矢完成签到 ,获得积分10
2秒前
苹果初阳完成签到,获得积分10
3秒前
5秒前
明理含之发布了新的文献求助50
5秒前
5秒前
6秒前
传奇3的应助被坚强孤容采纳,获得10
6秒前
6秒前
7秒前
7秒前
彩色的冬日完成签到 ,获得积分10
9秒前
充电宝的应助被qwer123456采纳,获得10
9秒前
yyy完成签到,获得积分10
9秒前
277发布了新的文献求助10
9秒前
从南到北发布了新的文献求助10
10秒前
lawrencewong发布了新的文献求助10
10秒前
哈哈哈发布了新的文献求助10
11秒前
昵称吧发布了新的文献求助10
11秒前
11秒前
cdercder的应助被July采纳,获得30
13秒前
20完成签到,获得积分10
14秒前
银月葱头完成签到,获得积分10
14秒前
Ava的应助被Lily采纳,获得10
14秒前
Fei完成签到,获得积分10
14秒前
gyyyy完成签到,获得积分10
15秒前
cdercder的应助被My_magnum_opus采纳,获得10
15秒前
16秒前
16秒前
orixero的应助被we采纳,获得10
17秒前
18秒前
高山发布了新的文献求助10
19秒前
天天快乐的应助被张佳琪采纳,获得10
19秒前
19秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183204
求助须知:如何正确求助?哪些是违规求助? 9572434
关于积分的说明 21825655
捐赠科研通 7779988
什么是DOI,文献DOI怎么找? 3433852
关于科研通互助平台的介绍 2558060
邀请新用户注册赠送积分活动 2480148