CASIA OpenIR  > 模式识别国家重点实验室  > 语音交互
Long Short Term Memory Recurrent Neural Network based Encoding Method for Emotion Recognition in Video
Linlin Chao; Jianhua Tao; Minghao Yang; Ya Li; Zhengqi Wen
2016
会议名称IEEE International Conference on Acoustic, Speech and Signal Processing(ICASSP)
会议录名称ICASSP2016
会议日期2016-3
会议地点Shanghai, China
摘要Human emotion is a temporally dynamic event which can be inferred from both audio and video feature sequences. In this paper we investigate the long short term memory recurrent neural network (LSTM-RNN) based encoding method for category emotion recognition in the video. LSTM-RNN is able to incorporate knowledge about how emotion evolves over long range successive frames and emotion clues from isolated frame. After encoding, each video clip can be represented by a vector for each input feature sequence. The vectors contain both frame level and sequence level emotion information. These vectors are then concatenated and fed into support vector machine (SVM) to get the final prediction result. Extensive evaluations on Emotion Challenge in the Wild (EmotiW2015) dataset show the efficiency of the proposed encoding method and competitive results are obtained.  The final recognition accuracy achieves 46.38% for audio-video emotion recognition sub-challenge, where the challenge baseline is 39.33%.
关键词Emotion Recognition
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/11843
专题模式识别国家重点实验室_语音交互
通讯作者Linlin Chao
作者单位中科院自动化研究所
推荐引用方式
GB/T 7714
Linlin Chao,Jianhua Tao,Minghao Yang,et al. Long Short Term Memory Recurrent Neural Network based Encoding Method for Emotion Recognition in Video[C],2016.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
ICASSP2016_1230.pdf(387KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Linlin Chao]的文章
[Jianhua Tao]的文章
[Minghao Yang]的文章
百度学术
百度学术中相似的文章
[Linlin Chao]的文章
[Jianhua Tao]的文章
[Minghao Yang]的文章
必应学术
必应学术中相似的文章
[Linlin Chao]的文章
[Jianhua Tao]的文章
[Minghao Yang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: ICASSP2016_1230.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。