[1]江佳俊,蒋 旻*,杨晓雨,等.基于注意力机制的个性化图像美学质量评估[J].计算机技术与发展,2021,31(10):56-62.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 010]
　JIANG Jia-jun,JIANG Min*,YANG Xiao-yu,et al.Research on Evaluation of Personalized Image Aesthetic Quality Based on Attention Mechanism[J].,2021,31(10):56-62.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 010]
点击复制

基于注意力机制的个性化图像美学质量评估()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年10期
页码:
56-62
栏目:
图形与图像
出版日期:
2021-10-10

文章信息/Info

Title:
Research on Evaluation of Personalized Image Aesthetic Quality Based on Attention Mechanism
文章编号:
1673-629X(2021)10-0056-07
作者:
江佳俊1; 2 ; 蒋 旻1; 2* ; 杨晓雨1 ; 郭 嘉1; 2
1. 武汉科技大学 计算机科学与技术学院,湖北 武汉 430065;
2. 智能信息处理与实时工业系统湖北省重点实验室(武汉科技大学),湖北 武汉 430065
Author(s):
JIANG Jia-jun1; 2 ; JIANG Min1; 2* ; YANG Xiao-yu1 ; GUO Jia1; 2
1. School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,China;
2. Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System ( Wuhan University of Science and Technology) ,Wuhan 430065,China
关键词:
图像美学质量评估; 注意力机制; 残差网络; 个性化; 深度学习
Keywords:
image aesthetics quality evaluation; attention mechanism; residual network; personalized; deep learning
分类号:
TP391.4
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 10. 010
摘要:
图像美学质量评估在图像推荐和图像编辑美学等行业具有良好的应用前景。 大部分美学质量评估方法存在两个问题:第一,只建立了通用美学评估模型,而忽略了个性化审美,这样的评估方法只适用于大众审美的评估,无法区分出不用用户之间的差异;第二,往往只从图像本身特征和整体布局进行评估,没有考虑主体的突出性和位置合理性,由于主体特征对评估结果有较大的影响,以致忽视主体的做法会使得评估结果具有较差的完备性。 针对这些问题,文中设计了一种基于注意力机制的个性化图像美学质量评估方法。 该方法在个性化残差网络的基础之上引入了注意力机制,既保持了个人在美学质量评估的主观偏好,又将主体的显著性因素加入评分过程。 在 Flickr 数据集上的实验中,该算法的平均SROCC 相关系数表现为 0. 667,相较于单一的图像美学质量评估在 Flickr 数据集上的表现,性能提升了 3% 。
Abstract:
Image aesthetic quality assessment has a good application prospect in image recommendation and image editing aesthetics.There are two problems in most aesthetic quality assessment methods. On the one hand,only the general aesthetic assessment model is established,while? ? ?the individual aesthetic assessment is ignored. Such an assessment method is only applicable to the public aesthetic assessment and cannot distinguish the differences between users. On the other hand,the evaluation is usually conducted only from the features of the image itself and? the overall layout,without considering the prominence and rationality of the subject. Since the subject features have a great impact on the evaluation results,the practice of ignoring the subject will make the evaluation results have poor completeness. Aiming at these problems,we design a personalized image aesthetic quality evaluation method based on attention mechanism.This method introduces the attention mechanism on the basis of the personalized residual network,which not only maintains the subjective preference of the individual in the aesthetic quality assessment,but also adds the significance factor of the subject into the scoring process.In experiments on Flickr data sets,the average SROCC correlation coefficient of this algorithm is 0. 667,which is 3% better than the performance of a single image aesthetic quality assessment on Flickr data sets.

相似文献/References:

[1]李梦洁,董峦.基于 PyTorch 的机器翻译算法的实现[J].计算机技术与发展,2018,28(10):160.[doi:10.3969/ j. issn.1673-629X.2018.10.033]
　LI Meng-jie,DONG Luan.Implementation of Machine Translation Algorithm Based on PyTorch[J].,2018,28(10):160.[doi:10.3969/ j. issn.1673-629X.2018.10.033]
[2]李东欣,禹 龙,田生伟,等.注意力机制的 LSTM-DBN 维语人称代词指代消解[J].计算机技术与发展,2019,29(07):33.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 007]
　LI Dong-xin,YU Long,TIAN Sheng-wei,et al.Attention Mechanism of LSTM-DBN Uyghur Personal Pronoun Anaphora Resolution[J].,2019,29(10):33.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 007]
[3]尹 鹏,周 林,郭 强,等.基于短语级注意力机制的关系抽取方法[J].计算机技术与发展,2019,29(09):24.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 005]
　YIN Peng,ZHOU Lin,GUO Qiang,et al.Relation Extraction Based on Phrase-level Attention[J].,2019,29(10):24.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 005]
[4]钟 诚,周浩杰,韦海亮.一种基于注意力机制的三维点云物体识别方法[J].计算机技术与发展,2020,30(04):41.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 008]
　ZHONG Cheng,ZHOU Hao-jie,WEI Hai-liang.A 3D Point Cloud Object Recognition Method Based on Attention Mechanism[J].,2020,30(10):41.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 008]
[5]王乾铭,李 吟.基于深度学习的个性化聊天机器人研究[J].计算机技术与发展,2020,30(04):79.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 015]
　WANG Qian-ming,LI Yin.Research on Personalized Chatbot Based on Deep Learning[J].,2020,30(10):79.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 015]
[6]朱立倩.基于深度学习的数显仪表字符识别[J].计算机技术与发展,2020,30(06):141.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 027]
　ZHU Li-qian.Character Recognition of Digital Display Instrument Based on Deep Learning[J].,2020,30(10):141.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 027]
[7]申静波,李井辉,孙丽娜.注意力机制在评论文本情感分析中的应用研究[J].计算机技术与发展,2020,30(07):169.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 036]
　SHEN Jing-bo,LI Jing-hui,SUN Li-na.Research on Application of Attention Mechanism in Comment Text Emotional Analysis[J].,2020,30(10):169.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 036]
[8]张亚飞.基于注意力的权重分配机制[J].计算机技术与发展,2020,30(09):49.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 009]
　ZHANG Ya-fei.Attention-based Weight Allocation Mechanism[J].,2020,30(10):49.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 009]
[9]王振业,叶成绪*,王文韬,等.基于 LSTM-Att 方法的音乐流行趋势预测[J].计算机技术与发展,2020,30(09):188.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 034]
　WANG Zhen-ye,YE Cheng-xu*,WANG Wen-tao,et al.Music Trend Forecast Based on LSTM-Att Method[J].,2020,30(10):188.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 034]
[10]陈 琛,刘小云,方玉华.融合注意力机制的电子病历命名实体识别[J].计算机技术与发展,2020,30(10):216.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 038]
　CHEN Chen,LIU Xiao-yun,FANG Yu-hua.Named Entity Recognition in Electronic Medical Record Introducing Attention Mechanisms[J].,2020,30(10):216.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 038]

更新日期/Last Update: 2021-10-10