@inproceedings{47c46331af564282856adc093d9e29d7,
title = "Visual and Audio Aware Bi-Modal Video Emotion Recognition",
abstract = "With rapid increase in the size of videos online, analysis and prediction of affective impact that video content will have on viewers has attracted much attention in the community. To solve this challenge several different kinds of information about video clips are exploited. Traditional methods normally focused on single modality, either audio or visual. Later on some researchers tried to establish multi-modal schemes and spend a lot of time choosing and extracting features by different fusion strategy. In this research, we proposed an end-to-end model which can automatically extract features and target an emotional classification task by integrating audio and visual features together and also adding the temporal characteristics of the video. The experimental study on commonly used MediaEval 2015 Affective Impact of Movies has shown this method's potential and it is expected that this work could provide some insight for future video emotion recognition from feature fusion perspective.",
keywords = "end-to-end, modal fusion, multi-modal scheme, temporal characteristics, videos",
author = "Siqi Xiang and Wenge Rong and Zhang Xiong and Min Gao and Qingyu Xiong",
note = "Publisher Copyright: {\textcopyright} CogSci 2017.; 39th Annual Meeting of the Cognitive Science Society: Computational Foundations of Cognition, CogSci 2017 ; Conference date: 26-07-2017 Through 29-07-2017",
year = "2017",
language = "英语",
series = "CogSci 2017 - Proceedings of the 39th Annual Meeting of the Cognitive Science Society: Computational Foundations of Cognition",
publisher = "The Cognitive Science Society",
pages = "3554--3559",
booktitle = "CogSci 2017 - Proceedings of the 39th Annual Meeting of the Cognitive Science Society",
}