Different types of video stimuli can activate different reactions in the human brain and these signals can be captured and analyzed for emotion recognition applications. However, accurate recognition across subjects is still challenging due to non-stationary and low signal-to-noise ratio of EEG signals. Lying at the intersection of video content analysis, we make an attempt to supervise EEG features with the external evoked video features. An end-to-end framework is proposed by extracting useful emotional representations in EEG signals with the complementarity of video stimuli. For the feature obtaining, an EEG feature extractor and a video feature extractor are combined, along with a cross-modal transformer to align the distributions of the two type features, and then a self-attention mechanism is designed for fusion. The experiments on the subset of DEAP and self-collected datasets validate that the enhancement of EEG features supervised by stimulus information is a reliable solution for subject-independent emotion recognition.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/EMBC53108.2024.10781573 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Hemispheric asymmetries in face recognition in health and dysfunction.
Handb Clin Neurol
March 2025
Department of Ophthalmology, University of Pittsburgh School of Medicine, Pittsburgh, PA, United States. Electronic address:
A defining characteristic of the human brain is that, notwithstanding the clear anatomic similarities, the two cerebral hemispheres have several different functional superiorities. The focus of this chapter is on the hemispheric asymmetry associated with the function of face identity processing, a finely tuned and expert behavior for almost all humans that is acquired incidentally from birth and continues to be refined through early adulthood. The first section lays out the well-accepted doctrine that face perception is a product of the right hemisphere, a finding based on longstanding behavioral data from healthy adult human observers.
View Article and Find Full Text PDFToward the enhancement of affective brain-computer interfaces using dependence within EEG series.
J Neural Eng
March 2025
Defense Innovation Institute, Academy of Military Sciences (AMS), Beijing, Beijing, 100094, CHINA.
In recent years, electroencephalogram (EEG)-based emotion recognition technology has made remarkable advances. However, a subtle but crucial problem caused by the sliding window method has long been overlooked, which is the serious quantity mismatch between stimuli and short-term EEG frames. This may be an important factor limiting the performance of the emotion recognition systems.
View Article and Find Full Text PDFPseudobulbar affect: clinical associations, social impact and quality of life implications - Lessons from PLS.
J Neurol
March 2025
Computational Neuroimaging Group (CNG), School of Medicine, Trinity College, Pearse Street, Dublin, Ireland.
Background: Pseudobulbar affect (PBA) is a well-recognised and troublesome clinical phenomenon in a range of neuroinflammatory, neoplastic, neurovascular and neurodegenerative conditions. It is often under-recognised in the community, frequently mistaken for psychiatric manifestations, appropriate pharmacological treatment is often delayed, and may result in a sense of embarrassment or lead to social isolation. Despite its considerable quality of life (QoL) implications and the challenges associated with its effective management, it is notoriously understudied.
View Article and Find Full Text PDFIdentification of Age and Underlying Disease Characteristics in Patients with Mild to Moderate Depression Comorbid with Parkinson's Disease: A Retrospective Case-control Study.
Actas Esp Psiquiatr
March 2025
Department of Neurology, Hebei Yanda Hospital, 065201 Langfang, Hebei, China.
Background: Depression is a widely recognized neuropsychiatric condition that often occurs as a comorbidity with various medical illnesses, including neurodegenerative disorders like Parkinson's disease (PD). This study aimed to identify the age of onset and underlying disease characteristics associated with patients exhibiting mild to moderate depression comorbid with PD.
Methods: This retrospective case-control study included 114 elderly patients (age ≥65 years) diagnosed with Parkinson's disease.
Identifying palliative home care needs of patients with advanced cancer: a cross-sectional study.
Front Psychiatry
February 2025
Pediatric Neurorehabilitation Department, Shenzhen Longhua Maternity and Child Healthcare Hospital, Shenzhen, China.
Background: Home-based palliative care is an ideal model for providing continuous, effective, and timely care at the patient's home. However, the timely recognition of palliative home care needs remains a clinical challenge, and few studies have described the characteristics of palliative care needs and quality of life at home.
Objectives: To identify the palliative home care needs of patients with advanced cancer and explore the influencing factors in addressing these needs.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!