Facial Emotion Recognition Using Asymmetric Pyramidal Networks With Gradient Centralization

Zang, Huanyu; Foo, Simon Y.; Bernadin, Shonda; Meyer‐Baese, Anke

doi:10.1109/access.2021.3075389

Cited by 10 publications

(2 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prosodic features and phonetic features are not isolated. Literature [ 23 , 24 ] show that there is a certain correlation between prosodic features of speech signals and three emotional dimensions (valence dimension, activation dimension, and control dimension). Among them, the activation dimension is obviously related to prosodic features, and emotional states with similar activation dimensions have similar prosodic features, which are easy to be confused.…”

Section: Methodsmentioning

confidence: 99%

Research on Chorus Emotion Recognition and Intelligent Medical Application Based on Health Big Data

Chen

2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

In chorus activities, the conductor leads chorus members to recreate music works. If you want to interpret music works perfectly with sound, emotion and emotional expression are particularly important. In this paper, a cloud HBD (health big data) integration system based on ensemble learning is designed to realize the high-efficiency and high-precision integration of HBD. An emotional speech database containing three emotions such as pleasure, calmness, and boredom is established, and the corpus problems such as emotional feature analysis and extraction needed for chorus emotion recognition research are solved. It also studies the classification and decision-making in emotional changes, and a DBN (deep belief network) chorus emotion recognition algorithm based on multiple emotional features is proposed. Feature DBN (Deep Belief Network) Chorus Emotion Recognition Algorithm This paper extracts various robust low-level features according to different features' ability to describe emotions and then feeds them into the DBN network to extract high-level feature descriptors. Then, the classification results of ELM (extreme learning machine) are voted and fused with the idea of ensemble learning, and the effectiveness of the algorithm is proved on three public datasets.

show abstract

Section: Methodsmentioning

confidence: 99%

Research on Chorus Emotion Recognition and Intelligent Medical Application Based on Health Big Data

Chen

2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…Aforementioned optimization techniques operate on activation or weight vectors and hence their adoption to pre-trained models pose a great challenge. So a new method, Gradient centralization [31][32][33][34] is used which acts on gradient of weight vectors and centralizes the gradient vector to have zero mean. Thus introduction of Gradient centralization accelerate the training process and enhances the generalization performance.…”

Section: Introductionmentioning

confidence: 99%

A novel deep learning technique for medical image analysis using improved optimizer

Agarwal,

Lohani,

Bist

2024

Health Informatics J

View full text Add to dashboard Cite

Application of Convolutional neural network in spectrum of Medical image analysis are providing benchmark outputs which converges the interest of many researchers to explore it in depth. Latest preprocessing technique Real ESRGAN (Enhanced super resolution generative adversarial network) and GFPGAN (Generative facial prior GAN) are proving their efficacy in providing high resolution dataset. Objective: Optimizer plays a vital role in upgrading the functioning of CNN model. Different optimizers like Gradient descent, Stochastic Gradient descent, Adagrad, Adadelta and Adam etc. are used for classification and segmentation of Medical image but they suffer from slow processing due to their large memory requirement. Stochastic Gradient descent suffers from high variance and is computationally expensive. Dead neuron problem also proves to detrimental to the performance of most of the optimizers. A new optimization technique Gradient Centralization is providing the unparalleled result in terms of generalization and execution time. Method: Our paper explores the next factor which is the employment of new optimization technique, Gradient centralization (GC) to our integrated framework (Model with advanced preprocessing technique). Result and conclusion: Integrated Framework of Real ESRGAN and GFPGAN with Gradient centralization provides an optimal solution for deep learning models in terms of Execution time and Loss factor improvement.

show abstract

Federated Scaling of Pre-trained Models for Deep Facial Expression Recognition

Srihitha,

Verma,

Prasad

2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

Facial Emotion Recognition Using Asymmetric Pyramidal Networks With Gradient Centralization

Cited by 10 publications

References 56 publications

Research on Chorus Emotion Recognition and Intelligent Medical Application Based on Health Big Data

Research on Chorus Emotion Recognition and Intelligent Medical Application Based on Health Big Data

A novel deep learning technique for medical image analysis using improved optimizer

Federated Scaling of Pre-trained Models for Deep Facial Expression Recognition

Contact Info

Product

Resources

About