Coarse-to-Fine Image Aesthetics Assessment With Dynamic Attribute Selection

计算机科学 选择(遗传算法) 感知 二进制数 计算机视觉 过程(计算) 图像(数学) 人工智能 美学 审美体验 简单(哲学) 机制(生物学)
作者
Yipo Huang,Leida Li,Pengfei Chen,Jinjian Wu,Yuzhe Yang,Yaqian Li,Guangming Shi
出处
期刊:IEEE Transactions on Multimedia [Institute of Electrical and Electronics Engineers]
卷期号:26: 9316-9329 被引量:19
标识
DOI:10.1109/tmm.2024.3389452
摘要

Image aesthetics assessment (IAA) is an interesting but challenging task, owing to the ineffable nature of human sense of beauty. The study of IAA has evolved from simple binary classification to more complex score regression and distribution prediction. It is effortless for people to perform aesthetic binary classification, i.e. , aesthetically pleasing or not. However, further judgment on the fine-level scalar aesthetic score is complex and typically determined by aesthetic attributes presented in the image, such as content, lighting and color. Motivated by the above facts, this paper presents a Coarse-to-fine image Aesthetics assessment model guided by Dynamic Attribute Selection, dubbed CADAS. The underlying idea is to simulate the process of human aesthetic perception by performing coarse-to-fine aesthetic reasoning. Specifically, a hierarchical AttributeNet is first pre-trained by imitating the staged mechanism of human aesthetic experience, producing the candidate aesthetic attributes. Then, an AestheticNet is introduced to perform the coarse-level binary classification, based on which a confidence-based attribute selection strategy is designed to dynamically pick out the dominant aesthetic attributes from the candidate ones. Finally, a self-attention-based FusionNet is designed to explore the interaction between dominant aesthetic attributes and aesthetic features, producing the fine-level aesthetic prediction. Extensive experiments demonstrate that the proposed model is superior to the state-of-the-arts. Furthermore, CADAS is also able to output the dominant aesthetic attributes in images, facilitating model explainability.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
伶俐子默发布了新的文献求助10
刚刚
万能图书馆的应助被sincerely采纳,获得10
刚刚
刚刚
刚刚
1秒前
2秒前
阿呸完成签到,获得积分10
2秒前
yuxyu完成签到 ,获得积分10
2秒前
huhuhaoshuai发布了新的文献求助10
2秒前
2秒前
2秒前
杪春发布了新的文献求助10
3秒前
林读书发布了新的文献求助10
3秒前
阿杳完成签到 ,获得积分10
3秒前
王旭完成签到,获得积分10
4秒前
ZZ完成签到,获得积分20
4秒前
时s完成签到,获得积分10
4秒前
5秒前
5秒前
感谢大家完成签到,获得积分10
5秒前
001发布了新的文献求助10
5秒前
bbllxyl完成签到,获得积分10
6秒前
清爽乐蓉完成签到,获得积分10
7秒前
项空月完成签到,获得积分10
7秒前
purplish完成签到 ,获得积分10
8秒前
8秒前
fantasy的应助被drizzle采纳,获得10
9秒前
9秒前
10秒前
十安完成签到,获得积分10
11秒前
achilles发布了新的文献求助10
12秒前
蛋堡完成签到,获得积分10
12秒前
haha发布了新的文献求助10
13秒前
魏伯安发布了新的文献求助10
13秒前
13秒前
标致诗霜完成签到,获得积分10
13秒前
sincerely发布了新的文献求助10
14秒前
zn完成签到 ,获得积分10
15秒前
自觉的聋完成签到 ,获得积分10
16秒前
友好天蓝完成签到,获得积分10
16秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Boundaries and Bodhisattvas 500
高分子基功能界面水蒸发材料与应用研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8181949
求助须知:如何正确求助?哪些是违规求助? 9571702
关于积分的说明 21819272
捐赠科研通 7778399
什么是DOI,文献DOI怎么找? 3433572
关于科研通互助平台的介绍 2557769
邀请新用户注册赠送积分活动 2479630