T2W-CogLoadNet: a framework for cognitive load assessment of dance movements based on deep learning-powered human
1Shenyang Conservatory of Music, Dance Academy, Shenyang, Liaoning, China.
Frontiers in Psychology
|February 6, 2026
Summary
This study introduces T²W-CogLoadNet for 3D dance posture estimation and cognitive load assessment, outperforming existing methods. The model enhances dance training and rehabilitation by accurately analyzing movement and cognitive states.
Area of Science:
- Computer Vision
- Biomedical Engineering
- Machine Learning
Background:
- Traditional dance posture estimation and cognitive load assessment methods lack accuracy and temporal modeling.
- Subjective judgment and insufficient temporal feature analysis limit current approaches in dance training and rehabilitation.
Purpose of the Study:
- To develop an advanced model for precise 3D dance posture estimation and indirect cognitive load measurement.
- To overcome limitations of existing methods by integrating sophisticated temporal feature extraction and hyperparameter optimization.
Main Methods:
- Proposed T²W-CogLoadNet model combining Temporal Convolutional Network (TCN) and Transformer for temporal feature extraction.
- Utilized Whale Optimization (WOA) for simultaneous optimization of feature subsets and model parameters.
- Validated on AIST++ and Kinetics 400 datasets, comparing against High Resolution Network (HRNet) and OpenPose.
Main Results:
- T²W-CogLoadNet significantly outperformed baseline models in 3D dance posture estimation and cognitive load modeling.
- Achieved low error rates: MAE of 0.23, RMSE of 0.26 for cognitive load, and MPJPE of 0.45 for 3D joints on AIST++.
- Demonstrated robust performance under noise and temporal scaling, maintaining lower MAE than baseline models.
Conclusions:
- The T²W-CogLoadNet model offers a significant advancement in analyzing dance movements and cognitive states.
- The model shows promise for enhancing dance training, rehabilitation, and motion analysis applications.
- Future work includes multimodal integration and real-time applications for broader adoption.
Related Concept Videos
01:21Cognitive Learning
1.2K
Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
1.2K
01:38Cognitive Dissonance
37.5K
Social psychologists have documented that feeling good about ourselves and maintaining positive self-esteem is a powerful motivator of human behavior (Tavris & Aronson, 2008). In the United States, members of the predominant culture typically think very highly of themselves and view themselves as good people who are above average on many desirable traits (Ehrlinger, Gilovich, & Ross, 2005). Often, our behavior, attitudes, and beliefs are affected when we experience a threat to our...
37.5K
01:06What are Estimates?
8.8K
It isn't easy to measure a parameter such as the mean height or the mean weight of a population. So, we draw samples from the population and calculate the mean height or mean weight of the individuals in the sample. This sample data acts as a representative measure of the population parameter. These sample statistics are known as estimates.
The estimate for the mean of a sample is denoted by ͞x, whereas the mean of the population is designated as μ. Further, parameters such...
The estimate for the mean of a sample is denoted by ͞x, whereas the mean of the population is designated as μ. Further, parameters such...
8.8K
01:08Power
13.1K
The concept of work involves force and displacement; meanwhile, the work-energy theorem relates the net work done on a body to the difference in its kinetic energy, calculated between two points on its trajectory. While none of these quantities or relations involves time explicitly, we know that the time available to accomplish work is often just as important as the amount of work itself. For example, sprinters in a race may have achieved the same velocity at the finish, therefore,...
13.1K
00:51Anatomical Movements
16.1K
Anatomical movements refer to the various actions or motions that can be performed by the body's joints and muscles. These movements are described using specific terms to provide a standardized way of discussing and understanding the range of motion at different joints.
Here are some common anatomical movements:
Flexion and extension motions are in the sagittal (anterior–posterior) plane of motion. These movements take place at the shoulder, hip, elbow, knee, wrist,...
Here are some common anatomical movements:
Flexion and extension motions are in the sagittal (anterior–posterior) plane of motion. These movements take place at the shoulder, hip, elbow, knee, wrist,...
16.1K
01:20Estimation of k and VD of Aminoglycosides
248
Aminoglycosides are a class of antibiotics used to treat various bacterial infections. Clinicians must determine the elimination rate constant (k) and volume of distribution (VD) to optimize therapeutic efficacy and minimize toxicity. The k value represents the rate at which the drug is removed from the body, and the VD reflects the degree to which the drug distributes into body tissues. Accurately estimating these parameters allows healthcare professionals to tailor drug dosing to individual...
248