Multi-task based Image Aesthetics Quality Evaluation

被引：1
|
作者：
Jiang, Min [1 ,2 ]
Chen, Zhe [1 ,2 ]
Jiang, Jiajun [1 ,2 ]
Liu, Xiaoming [1 ,2 ]
Hu, Wei [1 ,2 ]
机构：
[1] Wuhan Univ Sci & Technol, Dept Comp Sci & Engn, Wuhan 430065, Hubei, Peoples R China
[2] Wuhan Univ Sci & Technol, Hubei Prov Key Lab Intelligent Informat Proc & Re, Wuhan 430065, Hubei, Peoples R China
来源：
2021 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC) | 2021年
基金：
中国国家自然科学基金;
关键词：
Deep Learning; Multi-task; Image Aesthetics quality evaluation;
D O I：
10.1109/SMC52423.2021.9659217
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
Image aesthetics quality evaluation, which allows computers to judge "beauty and ugliness", is widely used in fields of image recommendation and image editing etc.. Most aesthetic evaluation methods can only output one type of evaluation result, thus, the scope of their application scenarios is limited. To solve this problem, we proposed a multi-task based aesthetic evaluation system, which can output the image style label and three forms of the aesthetic evaluation results for a image. The training procedure is divided into two stages to realize the aesthetic evaluation tasks from coarse to fine. Experiments on AVA dataset show that it can accomplish an efficient and comprehensive image aesthetic quality evaluation.
引用
收藏
页码：2755 / 2760
页数：6
相关论文
共 50 条
  • [1] Deep learning-driven multi-view multi-task image quality assessment method for chest CT image
    Jialin Su
    Meifang Li
    Yongping Lin
    Liu Xiong
    Caixing Yuan
    Zhimin Zhou
    Kunlong Yan
    BioMedical Engineering OnLine, 22
  • [2] Deep learning-driven multi-view multi-task image quality assessment method for chest CT image
    Su, Jialin
    Li, Meifang
    Lin, Yongping
    Xiong, Liu
    Yuan, Caixing
    Zhou, Zhimin
    Yan, Kunlong
    BIOMEDICAL ENGINEERING ONLINE, 2023, 22 (01)
  • [3] Semantic-aware multi-task learning for image aesthetic quality assessment
    Yan, Weiliang
    Li, Yuqing
    Yang, Huan
    Huang, Baoxiang
    Pan, Zhenkuan
    CONNECTION SCIENCE, 2022, 34 (01) : 2689 - 2713
  • [4] MTNet: A multi-task cascaded network for underwater image enhancement
    Ju Moran
    Hu Qing
    Multimedia Tools and Applications, 2024, 83 : 17629 - 17643
  • [5] MTNet: A multi-task cascaded network for underwater image enhancement
    Moran, Ju
    Qing, Hu
    MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (06) : 17629 - 17643
  • [6] Multi-task Deep Learning for Image Understanding
    Yu, Bo
    Lane, Ian
    2014 6TH INTERNATIONAL CONFERENCE OF SOFT COMPUTING AND PATTERN RECOGNITION (SOCPAR), 2014, : 37 - 42
  • [7] Breast cancer pathological image classification based on multi-task model
    Yu L.
    Xia Y.
    Wang P.
    Yan Y.
    Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition), 2021, 49 (08): : 53 - 57
  • [8] A MULTI-TASK ARCHITECTURE FOR REMOTE SENSING BY JOINT SCENE CLASSIFICATION AND IMAGE QUALITY ASSESSMENT
    Zhang, Cong
    Wang, Qi
    Li, Xuelong
    2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019), 2019, : 10051 - 10054
  • [9] MTQ-Caps: A Multi-task Capsule Network for Blind Image Quality Assessment
    Wei, Yijie
    Wang, Bincheng
    Liang, Fangfang
    Liu, Bo
    PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT VII, 2024, 14431 : 296 - 308
  • [10] Nested Dilation Network (NDN) for Multi-Task Medical Image Segmentation
    Wang, Liansheng
    Chen, Rongzhen
    Wang, Shuxin
    Zeng, Nianyin
    Huang, Xiaoyang
    Liu, Changhua
    IEEE ACCESS, 2019, 7 : 44676 - 44685
12345