RETRACTED ARTICLE: Construction and evaluation of the human behavior recognition model in kinematics under deep learning

Liu, Xiao; Qi, Deyu; Xiao, Haibin

doi:10.1007/s12652-020-02335-x

Cited by 3 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MPII data set shows 16 kinds of human joints and the total of 15 key coordinates output by a thermal diagram. MPII data sets are challenging, including more samples with complex background, severe occlusion, and poor lighting conditions [ 25 ].…”

Section: Experiments and Analysismentioning

confidence: 99%

Analysis and Research on Human Movement in Sports Scene

Wang

Zhang

Shen

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

As a whole-body sport, skipping rope plays an increasingly important role in daily life. In rope-skipping education, due to the lack of professional teachers, the training efficiency of students is low. The rope-skipping monitoring device is heavy and expensive, and the cost of labor statistics and energy consumption are high. In order to quickly analyze the movement process of students and provide correct guidance, this article implements the movement analysis method of the human body movement process. The problem of limb posture analysis in rope skipping is transformed into a multilabel classification problem, a real-time human motion analysis method based on mobile vision is proposed, and the algorithm model is verified in the rope-skipping scene. The experimental results prove that this paper proposes the improved algorithm, which achieved the expected effect. In the analysis of rope-skipping action, the choice of hyperparameters during the experiment is introduced, and it is verified that the proposed ALSTM-LSTM can solve the problem of multilabel classification in the rope-skipping process. The accuracy rate reaches 95.1%, and it can provide the best in all indicators and good performance. It is of great significance for movement analysis and movement quality evaluation during exercise.

show abstract

Section: Experiments and Analysismentioning

confidence: 99%

Analysis and Research on Human Movement in Sports Scene

Wang

Zhang

Shen

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

An information-rich sampling technique over spatio-temporal CNN for classification of human actions in videos

Basha

Pulabaigari

Mukherjee

2022

Multimed Tools Appl

View full text Add to dashboard Cite

We propose a novel video sampling scheme for human action recognition in videos, using Gaussian Weighing Function. Traditionally in deep learning-based human activity recognition approaches, either a few random frames or every k t h frame of the video is considered for training the 3D CNN, where k is a small positive integer, like 4, 5, or 6. This kind of sampling reduces the volume of the input data, which speeds-up the training network and also avoids overfitting to some extent, thus enhancing the performance of the 3D CNN model. In the proposed video sampling technique, consecutive k frames of a video are aggregated into a single frame by computing a Gaussian-weighted summation of the k frames. The resulting frame preserves the information in a better way than the conventional approaches and experimentally shown to perform better. In this paper, a 3-Dimensional deep CNN is proposed to extract the spatio-temporal features and follows Long Short-Term Memory (LSTM) to recognize human actions. The proposed 3D CNN architecture is capable of handling the videos where the camera is placed at a distance from the performer. Experiments are performed with KTH, WEIZMANN, and CASIA-B Human Activity and Gait datasets, whereby it is shown to outperform state-of-the-art deep learning based techniques. We achieve 95.78%, 95.27%, and 95.27% over the KTH, WEIZMANN, and CASIA-B human action and gait recognition datasets, respectively.

show abstract

TransNet: A Transfer Learning-Based Network for Human Action Recognition

Alomar,

Cai

2023

2023 International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

RETRACTED ARTICLE: Construction and evaluation of the human behavior recognition model in kinematics under deep learning

Cited by 3 publications

References 29 publications

Analysis and Research on Human Movement in Sports Scene

Analysis and Research on Human Movement in Sports Scene

An information-rich sampling technique over spatio-temporal CNN for classification of human actions in videos

TransNet: A Transfer Learning-Based Network for Human Action Recognition

Contact Info

Product

Resources

About