Results 1 to 10 of about 2,559,992 (157)

Skeleton-Based Action Quality Assessment with Anomaly-Aware DTW Optimization for Intelligent Sports Education [PDF]

Sensors
In intelligent sports education, current action quality assessment (AQA) methods face significant limitations: regression-based methods are heavily dependent on high-quality annotated data, while unsupervised methods lack sufficient accuracy and degrade ...
Wen Fu, Wenze Fang, Jiahao Huang, Kexin Zhu, Renguang Chen, Chen Feng   +5 more
doaj   +2 more sources

Dual-Stream STGCN with Motion-Aware Grouping for Rehabilitation Action Quality Assessment [PDF]

Sensors
Action quality assessment automates the evaluation of human movement proficiency, which is vital for applications like sports training and rehabilitation, where objective feedback enhances patient outcomes.
Zhejun Kuang, Zhaotin Yin, Yuheng Yang, Jian Zhao, Lei Sun   +4 more
doaj   +2 more sources

Enhancing Long-Term Action Quality Assessment: A Dual-Modality Dataset and Causal Cross-Modal Framework for Trampoline Gymnastics [PDF]

Sensors
Action quality assessment (AQA) plays a pivotal role in intelligent sports analysis, aiding athlete training and refereeing decisions. However, existing datasets and methods are limited to short-term actions, lacking comprehensive spatiotemporal modeling
Fengyan Lin, Jiahao Huang, Zhide Chen, Kexin Zhu, Chen Feng   +4 more
doaj   +2 more sources

LLM-FMS: A fine-grained dataset for functional movement screen action quality assessment. [PDF]

PLoS ONE
The Functional Movement Screen (FMS) is a critical tool for assessing an individual's basic motor abilities, aiming to prevent sports injuries. However, current automated FMS evaluation is based on deep learning methods, and the evaluation of actions is ...
Qingjun Xing, Xuyang Xing, Ping Guo, Zhenhui Tang, Yanfei Shen   +4 more
doaj   +3 more sources

Semantic-aware self-supervised learning using progressive sub-action regression for action quality assessment [PDF]

Scientific Reports
Action Quality Assessment (AQA) is a growing field in computer vision that focuses on objectively evaluating human actions from videos, with applications across various domains.
Marjan Mazruei, Ehsan Fazl-Ersi, Abedin Vahedian, Ahad Harati   +3 more
doaj   +2 more sources

Deep spatio-temporal graph convolutional network for police combat action recognition and training assessment [PDF]

Scientific Reports
Traditional police combat training relies heavily on subjective evaluation by human instructors, which lacks consistency and comprehensive coverage of complex movement patterns in real-world scenarios. This paper presents an enhanced deep spatio-temporal
Yan Wang
doaj   +2 more sources

Survey on Action Quality Assessment Methods in Video Understanding [PDF]

Jisuanji kexue, 2022
Action quality assessment refers to evaluate the action quality performed by human in video,such as calculating the quality score,level and evaluating the performance of different people.It is an important direction in video understanding and computer ...
ZHANG Hong-bo, DONG Li-jia, PAN Yu-biao, HSIAO Tsung-chih, ZHANG Hui-zhen, DU Ji-xiang
doaj   +1 more source

A Contrastive Learning Network for Performance Metric and Assessment of Physical Rehabilitation Exercises

IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023
Human activity analysis in the legal monitoring environment plays an important role in the physical rehabilitation field, as it helps patients with physical injuries improve their postoperative conditions and reduce their medical costs. Recently, several
Long Yao, Qing Lei, Hongbo Zhang, Jixiang Du, Shangce Gao   +4 more
doaj   +1 more source

Who danced better? ranked tiktok dance video dataset and pairwise action quality assessment method

IJAIN (International Journal of Advances in Intelligent Informatics), 2023
Video-based action quality assessment (AQA) is a non-trivial task due to the subtle visual differences between data produced by experts and non-experts.
Irwandi Hipiny, Hamimah Ujir, Aidil Azli Alias, Musdi Shanat, Mohamad Khairi Ishak   +4 more
doaj   +1 more source

HalluciNet-ing Spatiotemporal Representations Using a 2D-CNN

Signals, 2021
Spatiotemporal representations learned using 3D convolutional neural networks (CNN) are currently used in state-of-the-art approaches for action-related tasks. However, 3D-CNN are notorious for being memory and compute resource intensive as compared with
Paritosh Parmar, Brendan Morris
doaj   +1 more source