Understanding Naturalistic Facial Expressions with Deep Learning and Multimodal Large Language Models

Abstract

This paper provides a comprehensive overview of affective computing systems for facial expression recognition (FER) research in naturalistic contexts. The first section presents an updated account of user-friendly FER toolboxes incorporating state-of-the-art deep learning models and elaborates on their neural architectures, datasets, and performances across domains. These sophisticated FER toolboxes can robustly address a variety of challenges encountered in the wild such as variations in illumination and head pose, which may otherwise impact recognition accuracy. The second section of this paper discusses multimodal large language models (MLLMs) and their potential applications in affective science. MLLMs exhibit human-level capabilities for FER and enable the quantification of various contextual variables to provide context-aware emotion inferences. These advancements have the potential to revolutionize current methodological approaches for studying the contextual influences on emotions, leading to the development of contextualized emotion models.

Artificial Intelligence-Based Management of Adult Chronic Myeloid Leukemia: Where Are We and Where Are We Going?

“…However, at present, this sphere remains the prerogative of humans and is difficult to elicit because it is closely tied to personal experience, making sharing challenging. Large Language Models (LLM), can provide a promising approach [ 83 ] to help capturing some of the non-numeric traits of patients, but nowadays their application in medicine is still largely unexplored. Faster and faster.…”

Chuqur o‘rganishga asoslangan yuz tahlili: xususiyatlarni ajratib olish va his-tuyg‘ularni tushunish

“…Chuqur konvolyutsion neyron tarmoqlarikuchli chuqur o'rganish arxitekturalari bo'lib, ular etiketli yuzlarning katta ma'lumotlar to'plamidan yuz teksturalari va ifodalari o'rtasidagi murakkab munosabatlarni o'rganishi mumkin. KNTlar yuz ko'rinishi ma'lumotlaridagi murakkab, chiziqli bo'lmagan naqshlarni olishda ustunlik qiladi, bu esa ifodani aniq aniqlashga olib keladi (4-rasm) [12,13].…”

TPRO-NET: an EEG-based emotion recognition method reflecting subtle changes in emotion

“…Positive emotions have a beneficial impact on people's physical and mental health, while negative emotions have the opposite effect 2 . In recent years, there has been a growing interest in applications related to emotion recognition, such as human–computer interaction 3 and psychological disease rehabilitation 4 . Due to the excellent characteristics of Electroencephalogram (EEG) signals in terms of their inability to be falsified, high time resolution, and sensitivity to emotional changes 5 , 6 , emotion recognition based on EEG signals has received attention from both the academic and industrial communities.…”