{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:19:11Z","timestamp":1783531151885,"version":"3.55.0"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"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":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.eswa.2026.133337","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:30:57Z","timestamp":1781713857000},"page":"133337","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["MA3C: Multi-attribute aesthetic assessment and captioning"],"prefix":"10.1016","volume":"331","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0787-0014","authenticated-orcid":false,"given":"Le","family":"Ruan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5567-4575","authenticated-orcid":false,"given":"Minghua","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6506-7298","authenticated-orcid":false,"given":"Zhicheng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4245-4687","authenticated-orcid":false,"given":"Fei","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.133337_bib0001","series-title":"Proceedings of the ACL workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","author":"Banerjee","year":"2005"},{"key":"10.1016\/j.eswa.2026.133337_bib0002","doi-asserted-by":"crossref","first-page":"5009","DOI":"10.1109\/TIP.2022.3191853","article-title":"Composition and style attributes guided image aesthetic assessment","volume":"31","author":"Celona","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.133337_bib0003","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"3514","article-title":"Aesthetic critiques generation for photos","author":"Chang","year":"2017"},{"key":"10.1016\/j.eswa.2026.133337_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114502","article-title":"A multi-granularity facial aesthetic evaluation model based on image-text modality","volume":"330","author":"Chen","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.133337_bib0005","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19358","article-title":"EVA: Exploring the limits of masked visual representation learning at scale","author":"Fang","year":"2023"},{"key":"10.1016\/j.eswa.2026.133337_bib0006","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision workshops","first-page":"4550","article-title":"Aesthetic image captioning from weakly-labelled photographs","author":"Ghosal","year":"2019"},{"key":"10.1016\/j.eswa.2026.133337_bib0007","series-title":"Proceedings of the 31st 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.eswa.2026.133337_bib0008","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9375","article-title":"Effective aesthetics prediction with multi-level spatially pooled features","author":"Hosu","year":"2019"},{"key":"10.1016\/j.eswa.2026.133337_bib0009","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"5148","article-title":"Musiq: Multi-scale image quality transformer","author":"Ke","year":"2021"},{"key":"10.1016\/j.eswa.2026.133337_bib0010","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10041","article-title":"Vila: Learning image aesthetics from user comments with vision-language pretraining","author":"Ke","year":"2023"},{"key":"10.1016\/j.eswa.2026.133337_bib0011","series-title":"2006 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201906)","first-page":"419","article-title":"The design of high-level features for photo quality assessment","volume":"vol. 1","author":"Ke","year":"2006"},{"key":"10.1016\/j.eswa.2026.133337_bib0012","series-title":"Computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11\u201314, 2016, proceedings, part i 14","first-page":"662","article-title":"Photo aesthetics ranking network with attributes and content adaptation","author":"Kong","year":"2016"},{"key":"10.1016\/j.eswa.2026.133337_bib0013","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","volume":"123","author":"Krishna","year":"2017","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.eswa.2026.133337_bib0014","series-title":"International conference on machine learning","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.eswa.2026.133337_bib0015","series-title":"International conference on machine learning","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"issue":"2","key":"10.1016\/j.eswa.2026.133337_bib0016","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.1109\/TCSVT.2024.3470870","article-title":"Towards explainable image aesthetics assessment with attribute-oriented critiques generation","volume":"35","author":"Li","year":"2025","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"12","key":"10.1016\/j.eswa.2026.133337_bib0017","doi-asserted-by":"crossref","first-page":"7413","DOI":"10.1109\/TCSVT.2023.3272984","article-title":"Image aesthetics assessment with attribute-assisted multimodal memory network","volume":"33","author":"Li","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.eswa.2026.133337_bib0018","series-title":"Text summarization branches out","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.eswa.2026.133337_bib0019","series-title":"Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, September 6-12, 2014, proceedings, part v 13","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.eswa.2026.133337_bib0020","unstructured":"Liu, B., Hu, Y., Jin, S., Dou, S., Shi, G., Shao, J., Gui, T., & Huang, X. (2025). Unlocking the essence of beauty: Advanced aesthetic reasoning with relative-absolute policy optimization. arXiv preprint arXiv: 2509.21871."},{"key":"10.1016\/j.eswa.2026.133337_bib0021","doi-asserted-by":"crossref","first-page":"34892","DOI":"10.52202\/075280-1516","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133337_bib0022","series-title":"Proceedings of the 22nd ACM international conference on multimedia","first-page":"457","article-title":"Rapid: Rating pictorial aesthetics using deep learning","author":"Lu","year":"2014"},{"key":"10.1016\/j.eswa.2026.133337_bib0023","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"990","article-title":"Deep multi-patch aggregation network for image style, aesthetics, and quality estimation","author":"Lu","year":"2015"},{"key":"10.1016\/j.eswa.2026.133337_bib0024","series-title":"2011 International conference on computer vision","first-page":"2206","article-title":"Content-based photo quality assessment","author":"Luo","year":"2011"},{"key":"10.1016\/j.eswa.2026.133337_bib0025","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"4535","article-title":"A-lamp: Adaptive layout-aware multi-patch deep convolutional neural network for photo aesthetic assessment","author":"Ma","year":"2017"},{"key":"10.1016\/j.eswa.2026.133337_bib0026","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.eswa.2026.133337_bib0027","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"5514","article-title":"BMI-Net: A brain-inspired multimodal interaction network for image aesthetic assessment","author":"Nie","year":"2023"},{"issue":"3","key":"10.1016\/j.eswa.2026.133337_bib0028","doi-asserted-by":"crossref","first-page":"1487","DOI":"10.1109\/TCSVT.2022.3201510","article-title":"Comment-guided semantics-aware image aesthetics assessment","volume":"33","author":"Niu","year":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.eswa.2026.133337_bib0029","series-title":"Proceedings of the 40th annual meeting of the association for computational linguistics","first-page":"311","article-title":"Bleu: A method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.1016\/j.eswa.2026.133337_bib0030","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"24807","article-title":"The photographer\u2019s eye: Teaching multimodal large language models to see, and critique like photographers","author":"Qi","year":"2025"},{"key":"10.1016\/j.eswa.2026.133337_bib0031","series-title":"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.eswa.2026.133337_bib0032","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"1117","article-title":"AesCLIP: Multi-attribute contrastive learning for image aesthetics assessment","author":"Sheng","year":"2023"},{"issue":"8","key":"10.1016\/j.eswa.2026.133337_bib0033","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":"10.1016\/j.eswa.2026.133337_bib0034","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"4566","article-title":"Cider: Consensus-based image description evaluation","author":"Vedantam","year":"2015"},{"key":"10.1016\/j.eswa.2026.133337_bib0035","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 Systems with Applications"},{"issue":"8","key":"10.1016\/j.eswa.2026.133337_bib0036","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1049\/iet-cvi.2019.0361","article-title":"Neural aesthetic image reviewer","volume":"13","author":"Wang","year":"2019","journal-title":"IET Computer Vision"},{"key":"10.1016\/j.eswa.2026.133337_bib0037","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.116500","article-title":"A composition-oriented aesthetic view recommendation network supervised by the simplified golden ratio theory","volume":"195","author":"Wang","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133337_bib0038","series-title":"International conference on learning representations","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2022"},{"key":"10.1016\/j.eswa.2026.133337_bib0039","series-title":"Icassp 2024 - 2024 IEEE international conference on acoustics, speech and signal processing (icassp)","first-page":"2805","article-title":"Image aesthetics assessment via learnable queries","author":"Xiong","year":"2024"},{"key":"10.1016\/j.eswa.2026.133337_bib0040","doi-asserted-by":"crossref","unstructured":"Xiong, Z., Zhang, Y., Shen, Z., Ren, P., & Yu, H. (2024b). Multi-modal learnable queries for image aesthetics assessment. arXiv preprint arXiv: 2405.01326.","DOI":"10.1109\/ICME57554.2024.10687472"},{"key":"10.1016\/j.eswa.2026.133337_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.129954","article-title":"Attribute-guided aesthetic assessment for artistic images based on multimodal hybrid network","volume":"299","author":"Xu","year":"2026","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133337_bib0042","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19861","article-title":"Personalized image aesthetics assessment with rich attributes","author":"Yang","year":"2022"},{"key":"10.1016\/j.eswa.2026.133337_bib0043","series-title":"2021 IEEE International conference on image processing (ICIP)","first-page":"2523","article-title":"Generating aesthetic based critique for photographs","author":"Yeo","year":"2021"},{"key":"10.1016\/j.eswa.2026.133337_bib0044","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"10.1016\/j.eswa.2026.133337_bib0045","unstructured":"Zhang, S., Roller, S., Goyal, N., Artetxe, M., Chen, M., Chen, S., Dewan, C., Diab, M., Li, X., Lin, X. V. et al. (2022). OPT: Open pre-trained transformer language models. arXiv preprint arXiv: 2205.01068."},{"key":"10.1016\/j.eswa.2026.133337_bib0046","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1109\/TMM.2020.2985526","article-title":"Beyond vision: A multimodal recurrent attention convolutional neural network for unified image aesthetic prediction tasks","volume":"23","author":"Zhang","year":"2020","journal-title":"IEEE Transactions on Multimedia"},{"issue":"6","key":"10.1016\/j.eswa.2026.133337_bib0047","doi-asserted-by":"crossref","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","article-title":"Places: A 10 million image database for scene recognition","volume":"40","author":"Zhou","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.133337_bib0048","series-title":"Proceedings of the 24th ACM international conference on multimedia","first-page":"262","article-title":"Joint image and text representation for aesthetics analysis","author":"Zhou","year":"2016"},{"issue":"9","key":"10.1016\/j.eswa.2026.133337_bib0049","doi-asserted-by":"crossref","first-page":"2899","DOI":"10.1109\/TFUZZ.2025.3566145","article-title":"Progressively generated text-assisted image aesthetic quality assessment","volume":"33","author":"Zhu","year":"2025","journal-title":"IEEE Transactions on Fuzzy Systems"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426022463?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426022463?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:47:03Z","timestamp":1783529223000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426022463"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":49,"alternative-id":["S0957417426022463"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133337","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MA3C: Multi-attribute aesthetic assessment and captioning","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133337","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133337"}}