CASIA OpenIR  > 模式识别国家重点实验室  > 多媒体计算
Attention-based Multi-patch Aggregation for Image Aesthetic Assessment
Kekai, Sheng1,2; Weiming, Dong1; Chongyang, Ma3; Xing, Mei3; Feiyue, Huang4; Bao-Gang, Hu1
2018-10
会议名称ACM International Conference on Multimedia
会议日期2018-10-22 2018-10-26
会议地点Seoul, Republic of Korea
摘要

Aggregation structures with explicit information, such as image attributes and scene semantics, are effective and popular for intelligent systems for assessing aesthetics of visual data. However, useful information may not be available due to the high cost of manual annotation and expert design. In this paper, we present a novel multi-patch (MP) aggregation method for image aesthetic assessment. Different from state-of-the-art methods, which augment an MP aggregation network with various visual attributes, we train the model in an end-to-end manner with aesthetic labels only (i.e., aesthetically positive or negative). We achieve the goal by resorting to an attention-based mechanism that adaptively adjusts the weight of each patch during the training process to improve learning efficiency. In addition, we propose a set of objectives with three typical attention mechanisms (i.e., average, minimum, and adaptive) and evaluate their effectiveness on the Aesthetic Visual Analysis (AVA) benchmark. Numerical results show that our approach outperforms existing methods by a large margin. We further verify the effectiveness of the proposed attention-based objectives via ablation studies and shed light on the design of aesthetic assessment systems.

关键词Image Aesthetic Assessment Attention Mechanism Deep Learning
收录类别SCI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/23891
专题模式识别国家重点实验室_多媒体计算
通讯作者Weiming, Dong
作者单位1.NLPR, Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.Snap Inc.
4.Tencent
第一作者单位模式识别国家重点实验室
通讯作者单位模式识别国家重点实验室
推荐引用方式
GB/T 7714
Kekai, Sheng,Weiming, Dong,Chongyang, Ma,et al. Attention-based Multi-patch Aggregation for Image Aesthetic Assessment[C],2018.
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
AttentionBasedMultiP(3181KB)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
[Kekai, Sheng]的文章
[Weiming, Dong]的文章
[Chongyang, Ma]的文章
百度学术
百度学术中相似的文章
[Kekai, Sheng]的文章
[Weiming, Dong]的文章
[Chongyang, Ma]的文章
必应学术
必应学术中相似的文章
[Kekai, Sheng]的文章
[Weiming, Dong]的文章
[Chongyang, Ma]的文章
相关权益政策
暂无数据
收藏/分享
文件名: AttentionBasedMultiPatchAggregationForImageAestheticAssessment_MM2018.pdf
格式: Adobe PDF
此文件暂不支持浏览
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。