Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Aesthetic Attribute Assessment of Images Numerically on Mixed Multi-attribute Datasets

Aesthetic Attribute Assessment of Images Numerically on Mixed Multi-attribute Datasets With the continuous development of social software and multimedia technology, images have become a kind of important carrier for spreading information and socializing. How to evaluate an image comprehensively has become the focus of recent researches. The traditional image aesthetic assessment methods often adopt single numerical overall assessment scores, which has certain subjectivity and can no longer meet the higher aesthetic requirements. In this article, we construct an new image attribute dataset called aesthetic mixed dataset with attributes (AMD-A) and design external attribute features for fusion. Besides, we propose an efficient method for image aesthetic attribute assessment on mixed multi-attribute dataset and construct a multitasking network architecture by using the EfficientNet-B0 as the backbone network. Our model can achieve aesthetic classification, overall scoring, and attribute scoring. In each sub-network, we improve the feature extraction through ECA channel attention module. As for the final overall scoring, we adopt the idea of the teacher-student network and use the classification sub-network to guide the aesthetic overall fine-grain regression. Experimental results, using the MindSpore, show that our proposed method can effectively improve the performance of the aesthetic overall and attribute assessment. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Multimedia Computing Communications and Applications (TOMCCAP) Association for Computing Machinery

Aesthetic Attribute Assessment of Images Numerically on Mixed Multi-attribute Datasets

Download PDF
16 pages

Loading next page...
 
/lp/association-for-computing-machinery/aesthetic-attribute-assessment-of-images-numerically-on-mixed-multi-aHqnki8qiJ
Publisher
Association for Computing Machinery
Copyright
Copyright © 2022 Copyright held by the owner/author(s). Publication rights licensed to ACM.
ISSN
1551-6857
eISSN
1551-6865
DOI
10.1145/3547144
Publisher site
See Article on Publisher Site

Abstract

With the continuous development of social software and multimedia technology, images have become a kind of important carrier for spreading information and socializing. How to evaluate an image comprehensively has become the focus of recent researches. The traditional image aesthetic assessment methods often adopt single numerical overall assessment scores, which has certain subjectivity and can no longer meet the higher aesthetic requirements. In this article, we construct an new image attribute dataset called aesthetic mixed dataset with attributes (AMD-A) and design external attribute features for fusion. Besides, we propose an efficient method for image aesthetic attribute assessment on mixed multi-attribute dataset and construct a multitasking network architecture by using the EfficientNet-B0 as the backbone network. Our model can achieve aesthetic classification, overall scoring, and attribute scoring. In each sub-network, we improve the feature extraction through ECA channel attention module. As for the final overall scoring, we adopt the idea of the teacher-student network and use the classification sub-network to guide the aesthetic overall fine-grain regression. Experimental results, using the MindSpore, show that our proposed method can effectively improve the performance of the aesthetic overall and attribute assessment.

Journal

ACM Transactions on Multimedia Computing Communications and Applications (TOMCCAP) – Association for Computing Machinery

Published: Mar 20, 2023

Keywords: Aesthetic mixed dataset with attributes

References

  • The impact of visual appearance on user response in online display advertising
    [,
  • Inside-Outside Net: Detecting objects in context with skip pooling and recurrent neural networks
    [,
  • Computational and experimental approaches to visual aesthetics
    [,
  • Aesthetic critiques generation for photos
    [,
  • Studying aesthetics in photographic images using a computational approach
    [,
  • Aesthetic-driven image enhancement by adversarial learning
    [,
  • Perceptual quality assessment of smartphone photography
    [,
  • Deep Hough transform for semantic line detection
    [,
  • Distilling the knowledge in a neural network
    [,
  • Densely connected convolutional networks
    [,
  • Predicting aesthetic radar map using a hierarchical multi-task network
    [,
  • Incremental learning of multi-tasking networks for aesthetic radar map prediction
    [,
  • Beauty is in the eye of the beholder: Demographically oriented analysis of aesthetics in photographs
    [,
  • EVA: An explainable visual aesthetics dataset
    [,
  • Visual aesthetic quality assessment with a regression model
    [,
  • The design of high-level features for photo quality assessment
    [,
  • Photo aesthetics ranking network with attributes and content adaptation
    [,
  • HyperNet: Towards accurate region proposal generation and joint object detection
    [,
  • SCUT-FBP5500: A diverse benchmark dataset for multi-paradigm facial beauty prediction
    [,
  • Feature pyramid networks for object detection
    [,
  • Dynamic feature integration for simultaneous detection of salient object, edge, and skeleton
    [,
  • SSD: Single shot multibox detector
    [,
  • Photo and video quality evaluation: Focusing on the subject
    [,
  • A-Lamp: Adaptive layout-aware multi-patch deep convolutional neural network for photo aesthetic assessment
    [,
  • Assessing the aesthetic quality of photographs using generic image descriptors
    [,
  • Retrieved from https://www
    [,
  • AVA: A large-scale database for aesthetic visual analysis
    [,
  • Aesthetic quality classification of photographs based on color harmony
    [,
  • ECA-Net: Efficient channel attention for deep convolutional neural networks
    [,
  • Hierarchical layout-aware graph convolutional network for unified aesthetics assessment
    [,
  • Interhemispheric relationships: The neocortical commissures; syndromes of hemisphere disconnection
    [,
  • EfficientNet: Rethinking model scaling for convolutional neural networks
    [,
  • Classification of digital photos taken by photographers or home users
    [,
  • Software escalation prediction based on deep learning in the cognitive internet of vehicles
    [,
  • Time-varying-aware network traffic prediction via deep learning in IIoT
    [,
  • MFGAN: Multi-modal feature-fusion for CT metal artifact reduction using GANs
    [,
  • PSAC: Proactive sequence-aware content caching via deep learning at the network edge
    [,
  • Towards accurate oriented object detection in aerial images with adaptive multi-level feature fusion
    [,
  • Contextual ensemble network for semantic segmentation
    [,
  • Multi-scale deep context convolutional neural networks for semantic segmentation
    [,
  • Double attention based on graph attention network for image multi-label classification
    [,
  • Double Attention based on Graph Attention Network for Image Multi-Label Classification
    Zhou, Wei; Xia, Zhiwu; Dou, Peng; Su, Tao; Hu, Haifeng