? 基于加权协同训练的跨领域图像情感分类
Journal of Computer Science and Technology
Quick Search in JCST
 Advanced Search 
      Home | PrePrint | SiteMap | Contact Us | Help
 
Indexed by   SCIE, EI ...
Bimonthly    Since 1986
Journal of Computer Science and Technology 2017, Vol. 32 Issue (4) :714-725    DOI: 10.1007/s11390-017-1753-8
Special Issue on Deep Learning << Previous Articles | Next Articles >>
基于加权协同训练的跨领域图像情感分类
Meng Chen1,2, Lin-Lin Zhang1, Xiaohui Yu1,2, Member, CCF, IEEE, Yang Liu1,*, Member, CCF, IEEE
1 School of Computer Science and Technology, Shandong University, Jinan 250101, China;
2 School of Information Technology, York University, Toronto, M3J 1P3, Canada
Weighted Co-Training for Cross-Domain Image Sentiment Classification
Meng Chen1,2, Lin-Lin Zhang1, Xiaohui Yu1,2, Member, CCF, IEEE,Yang Liu1,*, Member, CCF, IEEE
1 School of Computer Science and Technology, Shandong University, Jinan 250101, China;
2 School of Information Technology, York University, Toronto, M3J 1P3, Canada

摘要
参考文献
相关文章
Download: [PDF 1276KB]  
摘要 图像情感分类,其目的是预测图像传达的情感极性,得到了很多关注。大多数现有的方法利用特定的视觉特征训练通用分类器来解决这个问题,但是其忽略了不同领域间的差异。在本文中,针对跨领域的图像情感分类,我们提出了一种新的加权协同训练方法,通过引入新的高置信度分类样本来迭代扩大标记集,以减少两个领域之间的差异。我们分别利用图像和其对应的文本训练两个情感分类器,并将源领域和目标领域之间的相似度设置为分类器的权重。我们在一个真实的Flickr数据集上进行实验来评估所提出的方法,实验结果表明我们提出的加权训练方法明显优于一些基准方法。
关键词情感分类   跨领域   加权协同训练     
Abstract: Image sentiment classification, which aims to predict the polarities of sentiments conveyed by the images, has gained a lot of attention. Most existing methods address this problem by training a general classifier with certain visual features, ignoring the discrepancies across domains. In this paper, we propose a novel weighted co-training method for cross-domain image sentiment classification, which iteratively enlarges the labeled set by introducing new high-confidence classified samples to reduce the gap between the two domains. We train two sentiment classifiers with both the images and the corresponding textual comments separately, and set the similarity between the source domain and the target domain as the weight of a classifier. We perform extensive experiments on a real Flickr dataset to evaluate the proposed method, and the empirical study reveals that the weighted co-training method significantly outperforms some baseline solutions.
Keywordssentiment classification   cross-domain   weighted co-training     
Received 2016-12-20;
本文基金:

This work was supported in part by the National Basic Research 973 Program of China under Grant No. 2015CB352502, the National Natural Science Foundation of China under Grant Nos. 61272092 and 61572289, the Natural Science Foundation of Shandong Province of China under Grant No. ZR2015FM002, the Science and Technology Development Program of Shandong Province of China under Grant No. 2014GGE27178, and the NSERC (Natural Sciences and Engineering Research Council of Canada) Discovery Grants.

通讯作者: Yang Liu     Email: yliu@sdu.edu.cn
About author: Meng Chen received his Ph.D. degree in computer science and technology in 2016 from Shandong University, Jinan. He is currently a postdoctoral fellow in the School of Information Technology, York University, Toronto. His research interest is in the area of data mining.
引用本文:   
Meng Chen, Lin-Lin Zhang, Xiaohui Yu, Yang Liu.基于加权协同训练的跨领域图像情感分类[J]  Journal of Computer Science and Technology , 2017,V32(4): 714-725
Meng Chen, Lin-Lin Zhang, Xiaohui Yu, Yang Liu.Weighted Co-Training for Cross-Domain Image Sentiment Classification[J]  Journal of Computer Science and Technology, 2017,V32(4): 714-725
链接本文:  
http://jcst.ict.ac.cn:8080/jcst/CN/10.1007/s11390-017-1753-8
Copyright 2010 by Journal of Computer Science and Technology