{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T15:19:47Z","timestamp":1770045587007,"version":"3.49.0"},"reference-count":15,"publisher":"SAGE Publications","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2021,9,15]]},"abstract":"<jats:p>Computational aesthetics, which uses computers to learn human aesthetic habits and ultimately replace humans in scoring images, has become a hot topic in recent years due to its wide application. Most of the initial research is to manually extract features and use classifiers such as support vector machines to score images. With the development of deep learning, traditional manual feature extraction methods are gradually replaced by convolutional neural networks to extract more comprehensive features. However, it is a huge challenge to artificially design an aesthetic neural network. Recently, Neural Architecture Search has upsurged to find suitable neural networks for many tasks in deep learning. In this paper, we first attempt to combine Neural Architecture Search with computational aesthetics. We design and apply a customized progressive differentiable architecture search strategy to obtain a light-weighted and efficient aesthetic baseline model. In addition, we simulate the multi-person rating mechanism by outputting the distribution of the aesthetic value of the image, replacing the previous classification scheme of judging the beauty and unbeauty of the image by the threshold value, and propose a self-weighted Earth Mover\u2019s Distance loss to better fit human subjective scoring. Based on the baseline model, we further introduce several strategies including an attention mechanism, the dilated convolution, and adaptive pooling, to enhance the performance. Finally, we design several groups of comparative experiments to demonstrate the effectiveness of our baseline aesthetic model and the introduced improvement strategies.<\/jats:p>","DOI":"10.3233\/jifs-210026","type":"journal-article","created":{"date-parts":[[2021,7,20]],"date-time":"2021-07-20T12:52:42Z","timestamp":1626785562000},"page":"2953-2967","source":"Crossref","is-referenced-by-count":0,"title":["Research on aesthetic models based on neural architecture search"],"prefix":"10.1177","volume":"41","author":[{"given":"Lingyun","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}]},{"given":"Pingjian","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-210026_ref1","doi-asserted-by":"crossref","unstructured":"Ma S. , Liu J. and Wen Chen C. , A-lamp: Adaptive layout-aware multi-patch deep convolutional neural network for photo aesthetic assessment, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017), 4535\u20134544.","DOI":"10.1109\/CVPR.2017.84"},{"key":"10.3233\/JIFS-210026_ref4","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1016\/j.neucom.2020.04.142","article-title":"Learning with privileged information for photo aesthetic assessment","volume":"404","author":"Shu","year":"2020","journal-title":"Neurocomputing"},{"key":"10.3233\/JIFS-210026_ref5","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.neucom.2020.10.046","article-title":"MSCAN: multimodal selfand-collaborative attention network for image aesthetic prediction tasks","volume":"430","author":"Zhang","year":"2021","journal-title":"Neurocomputing"},{"key":"10.3233\/JIFS-210026_ref9","first-page":"3","article-title":"CBAM: convolutional block attention module","volume":"11211","author":"Woo","year":"2018","journal-title":"Proceedings of the European conference on computer vision (ECCV)"},{"key":"10.3233\/JIFS-210026_ref10","first-page":"288","article-title":"Studying aesthetics in photographic images using a computational approach","volume":"3953","author":"Datta","year":"2006","journal-title":"A. Leonardis, H. Bischof, A. Pinz (Eds.), European Conference on Computer"},{"issue":"8","key":"10.3233\/JIFS-210026_ref11","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1109\/TMM.2013.2269899","article-title":"Content-based photo quality assessment","volume":"15","author":"Tang","year":"2013","journal-title":"IEEE Trans Multim"},{"key":"10.3233\/JIFS-210026_ref12","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.neucom.2014.06.029","article-title":"Image esthetic assessment using both hand-crafting and semantic features","volume":"143","author":"Guo","year":"2014","journal-title":"Neurocomputing"},{"issue":"8","key":"10.3233\/JIFS-210026_ref14","doi-asserted-by":"crossref","first-page":"3998","DOI":"10.1109\/TIP.2018.2831899","article-title":"Nima: Neural image assessment","volume":"27","author":"Talebi","year":"2018","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.3233\/JIFS-210026_ref17","doi-asserted-by":"crossref","first-page":"3898","DOI":"10.1109\/TIP.2020.2968285","article-title":"Personality-assisted multi-task learning for generic and personalized image aesthetics assessment","volume":"29","author":"Li","year":"2020","journal-title":"IEEE Trans Image Process"},{"issue":"1","key":"10.3233\/JIFS-210026_ref18","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1080\/08839514.2020.1839197","article-title":"Image aesthetics assessment based on multi-stream CNN architecture and saliency features","volume":"35","author":"Takimoto","year":"2021","journal-title":"Appl Artif Intell"},{"issue":"3","key":"10.3233\/JIFS-210026_ref25","doi-asserted-by":"crossref","first-page":"1482","DOI":"10.1109\/TIP.2017.2651399","article-title":"Deep aesthetic quality assessment with semantic information","volume":"26","author":"Kao","year":"2017","journal-title":"IEEE Trans Image Process"},{"key":"10.3233\/JIFS-210026_ref28","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.image.2018.05.006","article-title":"Visual aesthetic understanding: Sample-specific aesthetic classification and deep activation map visualization","volume":"67","author":"Zhang","year":"2018","journal-title":"Signal Process Image Commun"},{"key":"10.3233\/JIFS-210026_ref29","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.image.2019.05.021","article-title":"Fusion global and local deep representations with neural attention for aesthetic quality assessment","volume":"78","author":"Zhang","year":"2019","journal-title":"Signal Process Image Commun"},{"key":"10.3233\/JIFS-210026_ref31","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1007\/978-981-16-1092-9_8","article-title":"Image aesthetic assessment: A deep learning approach using class activation map","volume":"1377","author":"Sherashiya","year":"2020","journal-title":"Computer Vision and Image Processing - 5th International Conference, CVIP"},{"issue":"6","key":"10.3233\/JIFS-210026_ref34","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1109\/MSP.2017.2736018","article-title":"Deep convolutional neural models for picture-quality prediction: Challenges and solutions to data-driven image quality assessment","volume":"34","author":"Kim","year":"2017","journal-title":"IEEE Signal Process Mag"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-210026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T03:52:02Z","timestamp":1770004322000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-210026"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,15]]},"references-count":15,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.3233\/jifs-210026","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,15]]}}}