From methods to datasets: a detailed study on facial emotion recognition

Nidhi,; Verma, Bindu

doi:10.1007/s10489-023-05052-y

Cited by 4 publications

(1 citation statement)

References 205 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The creation of the Intensity-based Facial Expression Dataset (EIDB-13) lays the foundation for evaluating teaching states objectively. The proposed hierarchical deep learning model, combining appearance and geometric features, showcases promising results, indicating its potential for fine-grained facial expression classification [9].…”

Section: A Introductionmentioning

confidence: 93%

Facial Expression Recognition Based on Deep Learning: A Review

Jajan,

Abdulazeez

2024

ijcs

View full text Add to dashboard Cite

This review paper provides a comprehensive analysis of recent advancements in Facial Expression Recognition (FER) through various deep learning models. Seven state-of-the-art models are scrutinized, each offering unique contributions to the field. The MBCC-CNN model demonstrates improved recognition rates on diverse datasets, addressing the challenges of facial expression recognition through multiple branches and cross-connected convolutional neural networks. The Deep Graph Fusion model introduces a novel approach for predicting viewer expressions from videos, showcasing superior performance on the EEV database. Multimodal emotion recognition is explored in the EEG and facial expression fusion model, achieving high accuracy on the DEAP dataset. The Spark-based LDSP-TOP descriptor, coupled with a 1-D CNN and LSTM Autoencoder, excels in capturing temporal dynamics for facial expression understanding. Vision transformers for micro-expression recognition exhibit outstanding accuracy on datasets like CASMEI, CASME-II, and SAMM. Additionally, a hierarchical deep learning model is proposed for evaluating teaching states based on facial expressions. Lastly, a visionary transformer model achieves remarkable recognition accuracy of 100% on SAMM dataset, showcasing the potential of combining convolutional and transformer architectures. This review synthesizes key findings, highlights model performances, and outlines directions for future research in FER.

show abstract

Section: A Introductionmentioning

confidence: 93%

Facial Expression Recognition Based on Deep Learning: A Review

Jajan,

Abdulazeez

2024

ijcs

View full text Add to dashboard Cite

show abstract

A lightweight convolutional swin transformer with cutmix augmentation and CBAM attention for compound emotion recognition

Nidhi,

Verma

2024

Appl Intell

View full text Add to dashboard Cite

Less can be more: representational vs. stereotypical gender bias in facial expression recognition

Dominguez-Catena,

Paternain,

Jurio

et al. 2024

Prog Artif Intell

View full text Add to dashboard Cite

Machine learning models can inherit biases from their training data, leading to discriminatory or inaccurate predictions. This is particularly concerning with the increasing use of large, unsupervised datasets for training foundational models. Traditionally, demographic biases within these datasets have not been well-understood, limiting our ability to understand how they propagate to the models themselves. To address this issue, this paper investigates the propagation of demographic biases from datasets into machine learning models. We focus on the gender demographic component, analyzing two types of bias: representational and stereotypical. For our analysis, we consider the domain of facial expression recognition (FER), a field known to exhibit biases in most popular datasets. We use Affectnet, one of the largest FER datasets, as our baseline for carefully designing and generating subsets that incorporate varying strengths of both representational and stereotypical bias. Subsequently, we train several models on these biased subsets, evaluating their performance on a common test set to assess the propagation of bias into the models’ predictions. Our results show that representational bias has a weaker impact than expected. Models exhibit a good generalization ability even in the absence of one gender in the training dataset. Conversely, stereotypical bias has a significantly stronger impact, primarily concentrated on the biased class, although it can also influence predictions for unbiased classes. These results highlight the need for a bias analysis that differentiates between types of bias, which is crucial for the development of effective bias mitigation strategies.

show abstract

From methods to datasets: a detailed study on facial emotion recognition

Cited by 4 publications

References 205 publications

Facial Expression Recognition Based on Deep Learning: A Review

Facial Expression Recognition Based on Deep Learning: A Review

A lightweight convolutional swin transformer with cutmix augmentation and CBAM attention for compound emotion recognition

Less can be more: representational vs. stereotypical gender bias in facial expression recognition

Contact Info

Product

Resources

About