中国科学院深圳先进技术研究院机构知识库(SIAT OpenIR): Group Emotion Recognition with Individual Facial Emotion CNNs and Global Image Based CNNs
SIAT OpenIR  > 集成所
Group Emotion Recognition with Individual Facial Emotion CNNs and Global Image Based CNNs
Lianzhi Tan; Kaipeng Zhang; Kai Wang; Xiaoxing Zeng; Xiaojiang Peng; Yu Qiao
2017
Conference Namein ACM International Conference on Multimodal Interaction (ICMI), 2017
Conference Place中国澳门
AbstractThis paper presents our approach for group-level emotion recognition in the Emotion Recognition in the Wild Challenge 2017. The task is to classify an image into one of the group emotion such as positive, neutral or negative. Our approach is based on two types of Convolutional Neural Networks (CNNs), namely individual facial emotion CNNs and global image based CNNs. For the individual facial emotion CNNs, we first extract all the faces in an image, and assign the image label to all faces for training. In particular, we utilize a large-margin softmax loss for discriminative learning and we train two CNNs on both aligned and non-aligned faces. For the global image based CNNs, we compare several recent state-of-theart network structures and data augmentation strategies to boost performance. For a test image, we average the scores from all faces and the image to predict the final group emotion category. We win the challenge with accuracies 83.9% and 80.9% on the validation set and testing set respectively, which improve the baseline results by about 30%.
Department多媒体集成技术研究中心
Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.siat.ac.cn/handle/172644/11764
Collection集成所
Affiliation2017
Recommended Citation
GB/T 7714
Lianzhi Tan,Kaipeng Zhang,Kai Wang,et al. Group Emotion Recognition with Individual Facial Emotion CNNs and Global Image Based CNNs[C],2017.
Files in This Item: Download All
File Name/Size DocType Version Access License
集成-多媒体2017017.pdf(1595KB) 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Lianzhi Tan]'s Articles
[Kaipeng Zhang]'s Articles
[Kai Wang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Lianzhi Tan]'s Articles
[Kaipeng Zhang]'s Articles
[Kai Wang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Lianzhi Tan]'s Articles
[Kaipeng Zhang]'s Articles
[Kai Wang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 集成-多媒体2017017.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.