{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:41:31Z","timestamp":1791913291990,"version":"4.3.4"},"reference-count":42,"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"}],"funder":[{"DOI":"10.13039\/501100017596","name":"Natural Science Basic Research Program of Shaanxi Province","doi-asserted-by":"publisher","award":["2025SYS-SYSZD-049"],"award-info":[{"award-number":["2025SYS-SYSZD-049"]}],"id":[{"id":"10.13039\/501100017596","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114549","type":"journal-article","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T18:55:36Z","timestamp":1785696936000},"page":"114549","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PE","title":["Describe-to-Score: A text-guided framework for image complexity assessment"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7211-5865","authenticated-orcid":false,"given":"Shipeng","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dengfeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhonglin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114549_b1","series-title":"International Conference on Engineering Psychology and Cognitive Ergonomics","first-page":"158","article-title":"Visual complexity: Is that all there is?","author":"Forsythe","year":"2009"},{"key":"10.1016\/j.patcog.2026.114549_b2","first-page":"246","article-title":"A review on various measures for finding image complexity","author":"Singh","year":"2017","journal-title":"Int. J. Sci. Res. Eng. Technol. ISSN"},{"issue":"7","key":"10.1016\/j.patcog.2026.114549_b3","first-page":"8577","article-title":"IC9600: A benchmark dataset for automatic image complexity assessment","volume":"45","author":"Feng","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114549_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.firesaf.2021.103306","article-title":"Evaluation of image fire detection algorithms based on image complexity","volume":"121","author":"Li","year":"2021","journal-title":"Fire Saf. J."},{"issue":"2","key":"10.1016\/j.patcog.2026.114549_b5","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1007\/s00371-020-02023-z","article-title":"Visual complexity of shapes: a hierarchical perceptual learning model","volume":"38","author":"Dai","year":"2022","journal-title":"Vis. Comput."},{"key":"10.1016\/j.patcog.2026.114549_b6","series-title":"CLICv2: Image complexity representation via content invariance contrastive learning","author":"Liu","year":"2025"},{"key":"10.1016\/j.patcog.2026.114549_b7","series-title":"2015 International Conference on Machine Learning and Cybernetics","first-page":"295","article-title":"Research on the image complexity based on neural network","volume":"Vol. 1","author":"Chen","year":"2015"},{"key":"10.1016\/j.patcog.2026.114549_b8","unstructured":"T. Shen, S.S. Nath, A. Brielmann, P. Dayan, Simplicity in Complexity: Explaining Visual Complexity using Deep Segmentation Models, in: Proceedings of the Annual Meeting of the Cognitive Science Society, Vol. 46, 2024."},{"key":"10.1016\/j.patcog.2026.114549_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2025.103131","article-title":"Unlocking implicit motion for evaluating image complexity","volume":"90","author":"Li","year":"2025","journal-title":"Displays"},{"key":"10.1016\/j.patcog.2026.114549_b10","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"},{"key":"10.1016\/j.patcog.2026.114549_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.cosrev.2023.100548","article-title":"Visual language integration: A survey and open challenges","volume":"48","author":"Park","year":"2023","journal-title":"Comput. Sci. Rev."},{"issue":"2","key":"10.1016\/j.patcog.2026.114549_b12","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1109\/TFUZZ.2017.2692203","article-title":"A feature-reduction fuzzy clustering algorithm based on feature-weighted entropy","volume":"26","author":"Yang","year":"2017","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"10.1016\/j.patcog.2026.114549_b13","article-title":"Rademacher complexity bounds for non-iid processes","volume":"21","author":"Mohri","year":"2008","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"12","key":"10.1016\/j.patcog.2026.114549_b14","doi-asserted-by":"crossref","first-page":"4695","DOI":"10.1109\/TIP.2012.2214050","article-title":"No-reference image quality assessment in the spatial domain","volume":"21","author":"Mittal","year":"2012","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114549_b15","series-title":"2019 Eleventh International Conference on Quality of Multimedia Experience","first-page":"1","article-title":"KADID-10k: A large-scale artificially distorted IQA database","author":"Lin","year":"2019"},{"key":"10.1016\/j.patcog.2026.114549_b16","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.patcog.2026.114549_b17","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"vol. 139","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.114549_b18","series-title":"International Conference on Machine Learning","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.patcog.2026.114549_b19","doi-asserted-by":"crossref","unstructured":"K. He, H. Fan, Y. Wu, S. Xie, R. Girshick, Momentum contrast for unsupervised visual representation learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"issue":"8","key":"10.1016\/j.patcog.2026.114549_b20","doi-asserted-by":"crossref","first-page":"1249","DOI":"10.1016\/j.jspi.2013.03.018","article-title":"Energy statistics: A class of statistics based on distances","volume":"143","author":"Sz\u00e9kely","year":"2013","journal-title":"J. Statist. Plann. Inference"},{"key":"10.1016\/j.patcog.2026.114549_b21","series-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2019"},{"key":"10.1016\/j.patcog.2026.114549_b22","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.patcog.2026.114549_b23","series-title":"PyTorch image models","author":"Wightman","year":"2019"},{"key":"10.1016\/j.patcog.2026.114549_b24","series-title":"International Conference on Learning Representations","article-title":"A method for stochastic optimization","volume":"Vol. 5","author":"Kinga","year":"2015"},{"key":"10.1016\/j.patcog.2026.114549_b25","unstructured":"I. Loshchilov, F. Hutter, SGDR: Stochastic Gradient Descent with Warm Restarts, in: International Conference on Learning Representations, 2017."},{"issue":"5","key":"10.1016\/j.patcog.2026.114549_b26","doi-asserted-by":"crossref","DOI":"10.1098\/rsos.191487","article-title":"Predicting human complexity perception of real-world scenes","volume":"7","author":"Nagle","year":"2020","journal-title":"Royal Soc. Open Sci."},{"key":"10.1016\/j.patcog.2026.114549_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2020.102949","article-title":"Visual complexity analysis using deep intermediate-layer features","volume":"195","author":"Saraee","year":"2020","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.patcog.2026.114549_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.cognition.2022.105319","article-title":"Characterising and dissecting human perception of scene complexity","volume":"231","author":"Kyle-Davidson","year":"2023","journal-title":"Cognition"},{"key":"10.1016\/j.patcog.2026.114549_b29","doi-asserted-by":"crossref","unstructured":"K. Zhao, K. Yuan, M. Sun, M. Li, X. Wen, Quality-aware pre-trained models for blind image quality assessment, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 22302\u201322313.","DOI":"10.1109\/CVPR52729.2023.02136"},{"key":"10.1016\/j.patcog.2026.114549_b30","doi-asserted-by":"crossref","unstructured":"L. Agnolucci, L. Galteri, M. Bertini, A. Del Bimbo, Arniqa: Learning distortion manifold for image quality assessment, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2024, pp. 189\u2013198.","DOI":"10.1109\/WACV57701.2024.00026"},{"key":"10.1016\/j.patcog.2026.114549_b31","doi-asserted-by":"crossref","first-page":"2404","DOI":"10.1109\/TIP.2024.3378466","article-title":"Topiq: A top-down approach from semantics to distortions for image quality assessment","volume":"33","author":"Chen","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114549_b32","doi-asserted-by":"crossref","first-page":"7089","DOI":"10.1109\/TMM.2024.3360697","article-title":"CDINet: Content distortion interaction network for blind image quality assessment","volume":"26","author":"Zheng","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114549_b33","doi-asserted-by":"crossref","unstructured":"K. Xu, L. Liao, J. Xiao, C. Chen, H. Wu, Q. Yan, W. Lin, Boosting image quality assessment through efficient transformer adaptation with local feature enhancement, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 2662\u20132672.","DOI":"10.1109\/CVPR52733.2024.00257"},{"key":"10.1016\/j.patcog.2026.114549_b34","series-title":"2024 IEEE International Conference on Image Processing","first-page":"1260","article-title":"Attention down-sampling transformer, relative ranking and self-consistency for blind image quality assessment","author":"Alsaafin","year":"2024"},{"key":"10.1016\/j.patcog.2026.114549_b35","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2025.3527930","article-title":"Visual state space model with graph-based feature aggregation for blind image quality assessment","author":"Shi","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114549_b36","series-title":"Content-distortion high-order interaction for blind image quality assessment","author":"Liu","year":"2025"},{"key":"10.1016\/j.patcog.2026.114549_b37","series-title":"DGIQA: Depth-guided feature attention and refinement for generalizable image quality assessment","author":"Ramesh","year":"2025"},{"key":"10.1016\/j.patcog.2026.114549_b38","series-title":"Segmenting and understanding: Region-aware semantic attention for fine-grained image quality assessment with large language models","author":"Song","year":"2025"},{"key":"10.1016\/j.patcog.2026.114549_b39","series-title":"CLIC: Contrastive learning framework for unsupervised image complexity representation","author":"Liu","year":"2024"},{"key":"10.1016\/j.patcog.2026.114549_b40","doi-asserted-by":"crossref","unstructured":"S. Su, Q. Yan, Y. Zhu, C. Zhang, X. Ge, J. Sun, Y. Zhang, Blindly assess image quality in the wild guided by a self-adaptive hyper network, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 3667\u20133676.","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"10.1016\/j.patcog.2026.114549_b41","doi-asserted-by":"crossref","unstructured":"Z. Ying, H. Niu, P. Gupta, D. Mahajan, D. Ghadiyaram, A. Bovik, From patches to pictures (PaQ-2-PiQ): Mapping the perceptual space of picture quality, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 3575\u20133585.","DOI":"10.1109\/CVPR42600.2020.00363"},{"key":"10.1016\/j.patcog.2026.114549_b42","series-title":"Chinese Conference on Pattern Recognition and Computer Vision","first-page":"199","article-title":"Image visual complexity evaluation based on deep ordinal regression","author":"Guo","year":"2023"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032601513X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032601513X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T13:27:34Z","timestamp":1788182854000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S003132032601513X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":42,"alternative-id":["S003132032601513X"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114549","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Describe-to-Score: A text-guided framework for image complexity assessment","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114549","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":"114549"}}