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.
- [1] . 2012. The impact of visual appearance on user response in online display advertising. In 21st International Conference on World Wide Web. 457–458.Google Scholar
Digital Library
- [2] . 2016. Inside-Outside Net: Detecting objects in context with skip pooling and recurrent neural networks. In IEEE Conference on Computer Vision and Pattern Recognition. 2874–2883.Google Scholar
Cross Ref
- [3] . 2017. Computational and experimental approaches to visual aesthetics. Front. Computat. Neurosci. 11 (2017), 102.Google Scholar
Cross Ref
- [4] . 2017. Aesthetic critiques generation for photos. In IEEE International Conference on Computer Vision. 3514–3523.Google Scholar
- [5] . 2006. Studying aesthetics in photographic images using a computational approach. In European Conference on Computer Vision. Springer, 288–301.Google Scholar
Digital Library
- [6] . 2018. Aesthetic-driven image enhancement by adversarial learning. In 26th ACM International Conference on Multimedia. 870–878.Google Scholar
Digital Library
- [7] . 2020. Perceptual quality assessment of smartphone photography. In IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3677–3686.Google Scholar
Cross Ref
- [8] . 2020. Deep Hough transform for semantic line detection. In European Conference on Computer Vision (ECCV). 249–265.
DOI: Google ScholarDigital Library
- [9] . 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 2, 7 (2015).Google Scholar
- [10] . 2017. Densely connected convolutional networks. In IEEE Conference on Computer Vision and Pattern Recognition. 4700–4708.Google Scholar
Cross Ref
- [11] . 2018. Predicting aesthetic radar map using a hierarchical multi-task network. In Chinese Conference on Pattern Recognition and Computer Vision (PRCV). Springer, 41–50.Google Scholar
Cross Ref
- [12] . 2019. Incremental learning of multi-tasking networks for aesthetic radar map prediction. IEEE Access 7 (2019), 183647–183655.Google Scholar
Cross Ref
- [13] . 2019. Beauty is in the eye of the beholder: Demographically oriented analysis of aesthetics in photographs. ACM Trans. Multim. Comput., Commun. Applic. 15, 2s (2019), 1–21.Google Scholar
Digital Library
- [14] . 2020. EVA: An explainable visual aesthetics dataset. In Joint Workshop on Aesthetic and Technical Quality Assessment of Multimedia and Media Analytics for Societal Trends. 5–13.Google Scholar
Digital Library
- [15] . 2015. Visual aesthetic quality assessment with a regression model. In IEEE International Conference on Image Processing (ICIP). IEEE, 1583–1587.Google Scholar
Digital Library
- [16] . 2006. The design of high-level features for photo quality assessment. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06). IEEE, 419–426.Google Scholar
- [17] . 2016. Photo aesthetics ranking network with attributes and content adaptation. In European Conference on Computer Vision. Springer, 662–679.Google Scholar
Cross Ref
- [18] . 2016. HyperNet: Towards accurate region proposal generation and joint object detection. In IEEE Conference on Computer Vision and Pattern Recognition. 845–853.Google Scholar
Cross Ref
- [19] . 2018. SCUT-FBP5500: A diverse benchmark dataset for multi-paradigm facial beauty prediction. In 24th International Conference on Pattern Recognition (ICPR). IEEE, 1598–1603.Google Scholar
Cross Ref
- [20] . 2017. Feature pyramid networks for object detection. In IEEE Conference on Computer Vision and Pattern Recognition. 2117–2125.Google Scholar
Cross Ref
- [21] . 2020. Dynamic feature integration for simultaneous detection of salient object, edge, and skeleton. IEEE Trans. Image Process. 29 (2020), 8652–8667.Google Scholar
Digital Library
- [22] . 2016. SSD: Single shot multibox detector. In European Conference on Computer Vision. Springer, 21–37.Google Scholar
Cross Ref
- [23] . 2008. Photo and video quality evaluation: Focusing on the subject. In European Conference on Computer Vision. Springer, 386–399.Google Scholar
Digital Library
- [24] . 2017. A-Lamp: Adaptive layout-aware multi-patch deep convolutional neural network for photo aesthetic assessment. In IEEE Conference on Computer Vision and Pattern Recognition. 4535–4544.Google Scholar
Cross Ref
- [25] . 2011. Assessing the aesthetic quality of photographs using generic image descriptors. In International Conference on Computer Vision. IEEE, 1784–1791.Google Scholar
Digital Library
- [26] . 2022. Retrieved from https://www.mindspore.cn/.Google Scholar
- [27] . 2012. AVA: A large-scale database for aesthetic visual analysis. In IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2408–2415.Google Scholar
Digital Library
- [28] . 2011. Aesthetic quality classification of photographs based on color harmony. In IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 33–40.Google Scholar
Digital Library
- [29] 2020. ECA-Net: Efficient channel attention for deep convolutional neural networks. (2020), 11531–11539.Google Scholar
- [30] . 2021. Hierarchical layout-aware graph convolutional network for unified aesthetics assessment. In IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8475–8484.Google Scholar
Cross Ref
- [31] . 1969. Interhemispheric relationships: The neocortical commissures; syndromes of hemisphere disconnection. Handb. Clin. Neurol. 4 (1969), 145–153.Google Scholar
- [32] . 2019. EfficientNet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning. PMLR, 6105–6114.Google Scholar
- [33] . 2004. Classification of digital photos taken by photographers or home users. In Pacific-Rim Conference on Multimedia. Springer, 198–205.Google Scholar
Digital Library
- [34] . 2022. Software escalation prediction based on deep learning in the cognitive internet of vehicles. IEEE Trans. Intell. Transport. Syst. (2022).Google Scholar
- [35] . 2022. Time-varying-aware network traffic prediction via deep learning in IIoT. IEEE Trans. Industr. Inform. (2022).Google Scholar
- [36] . 2022. MFGAN: Multi-modal feature-fusion for CT metal artifact reduction using GANs. ACM Trans. Multim. Comput., Commun. Applic. (2022).Google Scholar
- [37] . 2020. PSAC: Proactive sequence-aware content caching via deep learning at the network edge. IEEE Trans. Netw. Sci. Eng. 7, 4 (2020), 2145–2154.Google Scholar
Cross Ref
- [38] . 2022. Towards accurate oriented object detection in aerial images with adaptive multi-level feature fusion. ACM Trans. Multim. Comput., Commun. Applic. (2022).Google Scholar
- [39] . 2022. Contextual ensemble network for semantic segmentation. Pattern Recog. 122 (2022), 108290.Google Scholar
Digital Library
- [40] . 2019. Multi-scale deep context convolutional neural networks for semantic segmentation. World Wide Web 22, 2 (2019), 555–570.Google Scholar
Digital Library
- [41] . 2022. Double attention based on graph attention network for image multi-label classification. ACM Trans. Multim. Comput., Commun. Applic. (2022).Google Scholar
Index Terms
Aesthetic Attribute Assessment of Images Numerically on Mixed Multi-attribute Datasets
Recommendations
Aesthetic Attributes Assessment of Images
MM '19: Proceedings of the 27th ACM International Conference on MultimediaImage aesthetic quality assessment has been a relatively hot topic during the last decade. Most recently, comments type assessment (aesthetic captions) has been proposed to describe the general aesthetic impression of an image using text. In this paper, ...
Multiple Aesthetic Attribute Assessment by Exploiting Relations Among Aesthetic Attributes
ICMR '15: Proceedings of the 5th ACM on International Conference on Multimedia RetrievalCurrent research of aesthetic assessment for images assumes one aesthetic score or one aesthetic label for an image, ignoring the relations of multiple aesthetic-related attributes. However, most images can be described by multiple aesthetic attributes ...
Learning image aesthetic subjectivity from attribute-aware relational reasoning network
Highlights- An attribute-aware relational reasoning network for image aesthetic assessment.
AbstractPeople’s various visual preferences lead to subjectivity in their aesthetic perception of images. Hence, learning image aesthetic subjectivity has attracted great interest in the computer vision community. People with different ...






Comments