面向听视觉信息的多模态人格识别研究进展

人格识别分析是人格计算研究中一个重要的研究内容，在人类行为分析、人工智能、人机交互、个性化推荐等方面具有重要的应用价值，是近年来心理学、认知学、计算机科学等领域中的一个多学科交叉的热点研究课题。本文介绍了与人格识别相关的各种人格类型表示理论和人格识别数据库，阐述了面向听视觉信息的各种听视觉人格特征提取技术，如手工特征和深度特征，并在此基础上对面向听视觉信息人格识别的多模态融合方法做了详细的分类和归纳，最后概括了面向听视觉信息的多模态人格识别发展趋势，并进行了展望。

Research advance of multimodal personality recognition based on audio and visual cues

Personality recognition analysis is an important research topic in personality computing, which has important applications in human behavior analysis, artificial intelligence, human-computer interaction, and personalized recommendation. In recent years, personality recognition analysis has become an active research topic in psychology, cognition, and computer science. This study introduces different types of personality representation theories and databases related to personality recognition and presents various audio-visual cue feature extraction technologies for personality recognition, such as handcrafted and depth features. Then, multimodal fusion methods integrating audio and visual cues for personality recognition are classified and summarized in detail. Finally, the development trend of multimodal personality recognition integrating audio and visual cues is explored and summarized.