{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T13:02:59Z","timestamp":1780923779892,"version":"3.54.1"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.knosys.2026.116298","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T06:51:31Z","timestamp":1779346291000},"page":"116298","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MUSE: a multimodal unified sketch evaluator for comprehensive aesthetic assessment"],"prefix":"10.1016","volume":"347","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8279-2499","authenticated-orcid":false,"given":"Shuai","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4820-6558","authenticated-orcid":false,"given":"Guangao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2792-8728","authenticated-orcid":false,"given":"Yongzhen","family":"Ke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116298_bib0001","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9726","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"issue":"26","key":"10.1016\/j.knosys.2026.116298_bib0002","first-page":"429","article-title":"Theory of communication. Part 1: the analysis of information","volume":"93","author":"Gabor","year":"1946","journal-title":"J. Inst. Electr. Eng. Part III"},{"key":"10.1016\/j.knosys.2026.116298_bib0003","series-title":"2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905): Vol. 1","first-page":"886","article-title":"Histograms of oriented gradients for human detection","author":"Dalal","year":"2005"},{"key":"10.1016\/j.knosys.2026.116298_bib0004","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"13708","article-title":"Coordinate attention for efficient mobile network design","author":"Hou","year":"2021"},{"key":"10.1016\/j.knosys.2026.116298_bib0005","series-title":"Computer Vision \u2013 ECCV 2006","first-page":"288","article-title":"Studying aesthetics in photographic images using a computational approach","author":"Datta","year":"2006"},{"key":"10.1016\/j.knosys.2026.116298_bib0006","series-title":"2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1 (CVPR\u201906)","first-page":"419","article-title":"The design of high-level features for photo quality assessment","volume":"1","author":"Yan","year":"2006"},{"key":"10.1016\/j.knosys.2026.116298_bib0007","first-page":"33","article-title":"Aesthetic quality classification of photographs based on color harmony","volume":"2011","author":"Nishiyama","year":"2011","journal-title":"CVPR"},{"key":"10.1016\/j.knosys.2026.116298_bib0008","series-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2408","article-title":"AVA: a large-scale database for aesthetic visual analysis","author":"Murray","year":"2012"},{"key":"10.1016\/j.knosys.2026.116298_bib0009","series-title":"Computer Vision \u2013 ECCV 2016","first-page":"662","article-title":"Photo aesthetics ranking network with attributes and content adaptation","author":"Kong","year":"2016"},{"issue":"8","key":"10.1016\/j.knosys.2026.116298_bib0010","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 Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116298_bib0011","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9367","article-title":"Effective aesthetics prediction with multi-level spatially pooled features","author":"Hosu","year":"2019"},{"key":"10.1016\/j.knosys.2026.116298_bib0012","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"8471","article-title":"Hierarchical layout-aware graph convolutional network for unified aesthetics assessment","author":"She","year":"2021"},{"key":"10.1016\/j.knosys.2026.116298_bib0013","series-title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","first-page":"942","article-title":"Rethinking image aesthetics assessment: models, datasets and benchmarks","author":"He","year":"2022"},{"key":"10.1016\/j.knosys.2026.116298_bib0014","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"22388","article-title":"Towards artistic image aesthetics assessment: a large-scale dataset and a new method","author":"Yi","year":"2023"},{"key":"10.1016\/j.knosys.2026.116298_bib0015","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10041","article-title":"VILA: learning image aesthetics from user comments with vision-language pretraining","author":"Ke","year":"2023"},{"key":"10.1016\/j.knosys.2026.116298_bib0016","series-title":"Datasets and Benchmarks Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"21838","article-title":"Thinking image color aesthetics assessment: models","author":"He","year":"2023"},{"key":"10.1016\/j.knosys.2026.116298_bib0017","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"5709","article-title":"Revisiting image aesthetic assessment via self-supervised feature learning","volume":"34","author":"Sheng","year":"2020"},{"key":"10.1016\/j.knosys.2026.116298_bib0018","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","first-page":"816","article-title":"Self-supervised multi-task pretraining improves image aesthetic assessment","author":"Pfister","year":"2021"},{"key":"10.1016\/j.knosys.2026.116298_bib0019","unstructured":"D. Ha, D. Eck, A neural representation of sketch drawings, in: International Conference on Learning Representations, 2018."},{"key":"10.1016\/j.knosys.2026.116298_bib0020","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence: Vol. 33","first-page":"2564","article-title":"AI-sketcher : a deep generative model for producing high-quality sketches","author":"Cao","year":"2019"},{"issue":"6","key":"10.1016\/j.knosys.2026.116298_bib0021","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3414685.3417840","article-title":"Pixelor: a competitive sketching AI agent. So you think you can sketch?","volume":"39","author":"Bhunia","year":"2020","journal-title":"ACM Trans. Graph"},{"key":"10.1016\/j.knosys.2026.116298_bib0022","series-title":"Computer Vision \u2013 ECCV 2020","first-page":"632","article-title":"B\u00e9zierSketch: a generative model for scalable vector sketches","author":"Das","year":"2020"},{"issue":"1","key":"10.1016\/j.knosys.2026.116298_bib0023","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.vrih.2022.06.006","article-title":"IAACS: image aesthetic assessment through color composition and space formation","volume":"5","author":"Yang","year":"2023","journal-title":"Virtual Real. Intell. Hardw."},{"key":"10.1016\/j.knosys.2026.116298_bib0024","series-title":"2015 IEEE International Conference on Image Processing (ICIP)","first-page":"4828","article-title":"Spatial matching of sketches without point correspondence","author":"Wang","year":"2015"},{"key":"10.1016\/j.knosys.2026.116298_bib0025","series-title":"Computer Vision \u2013 ECCV 2016 Workshops","first-page":"798","article-title":"Adversarial training for sketch retrieval","author":"Creswell","year":"2016"},{"key":"10.1016\/j.knosys.2026.116298_bib0026","series-title":"Computer Vision \u2013 ECCV 2010","first-page":"420","article-title":"Lighting and pose robust face sketch synthesis","author":"Hutchison","year":"2010"},{"key":"10.1016\/j.knosys.2026.116298_bib0027","series-title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","first-page":"1163","article-title":"Robust face sketch synthesis via generative adversarial fusion of priors and parametric sigmoid","author":"Zhang","year":"2018"},{"key":"10.1016\/j.knosys.2026.116298_bib0028","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"23315","article-title":"Learning geometry-aware representations by sketching","author":"Lee","year":"2023"},{"key":"10.1016\/j.knosys.2026.116298_bib0029","first-page":"9","article-title":"Application of deep convolutional features in sketch works classification and evaluation","volume":"29","author":"Li","year":"2017","journal-title":"J. Comput.-Aided Des. Comput. Graph."},{"issue":"25","key":"10.1016\/j.knosys.2026.116298_bib0030","doi-asserted-by":"crossref","first-page":"33663","DOI":"10.1007\/s11042-021-11305-0","article-title":"Sketch works ranking based on improved transfer learning model","volume":"80","author":"Yu","year":"2021","journal-title":"Multimed. Tools Appl."},{"key":"10.1016\/j.knosys.2026.116298_bib0031","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.knosys.2026.116298_bib0032","series-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","first-page":"34892","article-title":"Visual instruction tuning[C]","author":"Liu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116298_bib0033","unstructured":"A. Grattafiori, A. Dubey, A. Jauhri, et al., The Llama 3 Herd of Models, arXiv:2407.21783 (2024)."},{"key":"10.1016\/j.knosys.2026.116298_bib0034","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.knosys.2026.116298_bib0035","doi-asserted-by":"crossref","unstructured":"J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, BERT: pre-training of deep bidirectional transformers for language understanding, in: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, 2019, pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.knosys.2026.116298_bib0036","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9726","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.knosys.2026.116298_bib0037","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"13708","article-title":"Coordinate attention for efficient mobile network design","author":"Hou","year":"2021"},{"key":"10.1016\/j.knosys.2026.116298_bib0038","series-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","first-page":"6000","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.knosys.2026.116298_bib0039","doi-asserted-by":"crossref","unstructured":"G. Huang, Z. Liu, L. Van Der Maaten, K.Q. Weinberger, Densely connected convolutional networks, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2261\u20132269. doi:10.1109\/CVPR.2017.243.","DOI":"10.1109\/CVPR.2017.243"},{"key":"10.1016\/j.knosys.2026.116298_bib0040","unstructured":"I. Loshchilov, F. Hutter, Decoupled weight decay regularization, in: 7th International Conference on Learning Representations (ICLR 2019), New Orleans, LA, USA, 2019."},{"key":"10.1016\/j.knosys.2026.116298_bib0041","series-title":"Proceedings of the 41st International Conference on Machine Learning","first-page":"31106","article-title":"ELTA: an enhancer against long-tail for aesthetics-oriented models","author":"Liu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116298_bib0042","series-title":"Computer Vision \u2013 ECCV 2018","first-page":"3","article-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018"},{"key":"10.1016\/j.knosys.2026.116298_bib0043","unstructured":"Y. Liu, Z. Shao, N. Hoffmann, Global attention mechanism: retain information to enhance channel-spatial interactions, arXiv preprint arXiv:2112.05561, 2021."},{"key":"10.1016\/j.knosys.2026.116298_bib0044","doi-asserted-by":"crossref","unstructured":"Y. Xue, Z. Yuan, HDAM: Heuristic Difference Attention Module for Convolutional Neural Networks, J. Internet Things 4 (2022) 57\u201367. doi:10.32604\/jiot.2022.025327.","DOI":"10.32604\/jiot.2022.025327"},{"key":"10.1016\/j.knosys.2026.116298_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128659","article-title":"A novel framework for aesthetic assessment of portrait sketches via multi-feature integration and self-supervised learning","volume":"292","author":"Wang","year":"2025","journal-title":"Expert Syst Appl"},{"key":"10.1016\/j.knosys.2026.116298_bib0046","series-title":"Computer Vision \u2013 ECCV 2024","first-page":"217","article-title":"Do generalised classifiers really work on Human drawn sketches?","author":"Bandyopadhyay","year":"2025"},{"key":"10.1016\/j.knosys.2026.116298_bib0047","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111749","article-title":"Personalized image aesthetics assessment based on Graph Neural network and collaborative filtering","volume":"294","author":"Shi","year":"2024","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.116298_bib0048","series-title":"Computer Vision \u2013 ECCV 2024","article-title":"Teach CLIP to develop a number sense for ordinal regression","author":"Yao","year":"2024"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126010245?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126010245?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T12:18:53Z","timestamp":1780921133000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126010245"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":48,"alternative-id":["S0950705126010245"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116298","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MUSE: a multimodal unified sketch evaluator for comprehensive aesthetic assessment","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116298","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116298"}}