Bridging the semantic gap in multimedia emotion/mood recognition for ubiquitous computing environment |
| |
Authors: | Seungmin Rho Sang-Soo Yeo |
| |
Affiliation: | 1. School of Electrical Engineering, Korea University, Anam-Dong, Seongbuk-Gu, Seoul, 136-713, Korea 2. Division of Computer Engineering, Mokwon University, Do-An-dong, Seo-gu, Daejeon, 302-729, Korea
|
| |
Abstract: | With the advent of the ubiquitous era, multimedia emotion/mood could be used as an important clue in multimedia understanding, retrieval, recommendation, and some other multimedia applications. Many issues for multimedia emotion recognition have been addressed by different disciplines such as physiology, psychology, cognitive science, and musicology. Recently, many researchers have tried to uncover the relationship between multimedia contents such as image or music and emotion in many applications. In this paper, we introduce the existing emotion models and acoustic features. We also present a comparison of different emotion/mood recognition methods. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|