Deep Recurrent Multi-instance Learning with Spatio-temporal Features for Engagement Intensity Prediction | |
Jianfei Yang; Kai Wang; Xiaojiang Peng; Yu Qiao | |
2018 | |
会议日期 | 2018 |
会议地点 | 美国 |
英文摘要 | This paper elaborates the winner approach for engagement inten- sity prediction in the EmotiW Challenge 2018. The task is to predict the engagement level of a subject when he or she is watching an educational video in diverse conditions and different environments. Our approach formulates the prediction task as a multi-instance re- gression problem. We divide an input video sequence into segments and calculate the temporal and spatial features of each segment for regressing the intensity. Subject engagement, that is intuitively related with body and face changes in time domain, can be char- acterized by long short-term memory (LSTM) network. Hence, we build a multi-modal regression model based on multi-instance mech- anism as well as LSTM. To make full use of training and validation data, we train different models for different data split and conduct model ensemble finally. Experimental results show that our method achieves mean squared error (MSE) of 0.0717 in the validation set, which improves the baseline results by 28%. Our methods finally win the challenge with MSE of 0.0626 on the testing set. |
URL标识 | 查看原文 |
内容类型 | 会议论文 |
源URL | [http://ir.siat.ac.cn:8080/handle/172644/13697] |
专题 | 深圳先进技术研究院_集成所 |
推荐引用方式 GB/T 7714 | Jianfei Yang,Kai Wang,Xiaojiang Peng,et al. Deep Recurrent Multi-instance Learning with Spatio-temporal Features for Engagement Intensity Prediction[C]. 见:. 美国. 2018. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论