{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T17:13:46Z","timestamp":1783790026941,"version":"3.55.0"},"reference-count":58,"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\/501100006407","name":"Henan Province Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006407","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Displays"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.displa.2026.103611","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T23:20:38Z","timestamp":1783639238000},"page":"103611","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Text-Guided Adaptive-Balance Distortion-Sensitive Multi-Modal Pre-Trained Model for Blind Image Quality Assessment"],"prefix":"10.1016","volume":"95","author":[{"given":"Yang","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaohui","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoheng","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingliang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"22","key":"10.1016\/j.displa.2026.103611_b1","article-title":"No-reference quality assessment based on dual-channel convolutional neural network for underwater image enhancement","volume":"13","author":"Hu","year":"2024","journal-title":"Electron. (2079-9292)"},{"key":"10.1016\/j.displa.2026.103611_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2023.102432","article-title":"No-reference quality assessment for low-light image enhancement: Subjective and objective methods","volume":"78","author":"Lin","year":"2023","journal-title":"Displays"},{"key":"10.1016\/j.displa.2026.103611_b3","doi-asserted-by":"crossref","unstructured":"S. Yang, T. Wu, S. Shi, S. Lao, Y. Gong, M. Cao, J. Wang, Y. Yang, Maniqa: Multi-dimension attention network for no-reference image quality assessment, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 1191\u20131200.","DOI":"10.1109\/CVPRW56347.2022.00126"},{"key":"10.1016\/j.displa.2026.103611_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2021.102058","article-title":"No-reference stereoscopic image quality assessment using quaternion wavelet transform and heterogeneous ensemble learning","volume":"69","author":"Wang","year":"2021","journal-title":"Displays"},{"issue":"11","key":"10.1016\/j.displa.2026.103611_b5","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-019-2757-1","article-title":"Perceptual image quality assessment: A survey","volume":"63","author":"Zhai","year":"2020","journal-title":"Sci. China Inf. Sci."},{"issue":"12","key":"10.1016\/j.displa.2026.103611_b6","article-title":"Universal blind image quality assessment metrics via natural scene statistics and multiple kernel learning","volume":"24","author":"Gao","year":"2013","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"12","key":"10.1016\/j.displa.2026.103611_b7","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."},{"issue":"8","key":"10.1016\/j.displa.2026.103611_b8","doi-asserted-by":"crossref","first-page":"3339","DOI":"10.1109\/TIP.2012.2191563","article-title":"Blind image quality assessment: A natural scene statistics approach in the DCT domain","volume":"21","author":"Saad","year":"2012","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.displa.2026.103611_b9","series-title":"European Conference on Computer Vision","first-page":"288","article-title":"Studying aesthetics in photographic images using a computational approach","author":"Datta","year":"2006"},{"issue":"12","key":"10.1016\/j.displa.2026.103611_b10","doi-asserted-by":"crossref","first-page":"3350","DOI":"10.1109\/TIP.2011.2147325","article-title":"Blind image quality assessment: From natural scene statistics to perceptual quality","volume":"20","author":"Moorthy","year":"2011","journal-title":"IEEE Trans. Image Process."},{"issue":"11","key":"10.1016\/j.displa.2026.103611_b11","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"2002","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.displa.2026.103611_b12","doi-asserted-by":"crossref","unstructured":"Y. Fang, H. Zhu, Y. Zeng, K. Ma, Z. Wang, Perceptual quality assessment of smartphone photography, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 3677\u20133686.","DOI":"10.1109\/CVPR42600.2020.00373"},{"issue":"1","key":"10.1016\/j.displa.2026.103611_b13","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1109\/TIP.2015.2500021","article-title":"Massive online crowdsourced study of subjective and objective picture quality","volume":"25","author":"Ghadiyaram","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.displa.2026.103611_b14","doi-asserted-by":"crossref","first-page":"4041","DOI":"10.1109\/TIP.2020.2967829","article-title":"KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment","volume":"29","author":"Hosu","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.displa.2026.103611_b15","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"},{"issue":"10","key":"10.1016\/j.displa.2026.103611_b16","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.displa.2026.103611_b17","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"},{"issue":"8","key":"10.1016\/j.displa.2026.103611_b18","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation learning: A review and new perspectives","volume":"35","author":"Bengio","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"11","key":"10.1016\/j.displa.2026.103611_b19","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-019-2757-1","article-title":"Perceptual image quality assessment: A survey","volume":"63","author":"Zhai","year":"2020","journal-title":"Sci. China Inf. Sci."},{"key":"10.1016\/j.displa.2026.103611_b20","doi-asserted-by":"crossref","unstructured":"K. He, X. Chen, S. Xie, Y. Li, P. Doll\u00e1r, R. Girshick, Masked autoencoders are scalable vision learners, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16000\u201316009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"10.1016\/j.displa.2026.103611_b21","article-title":"Distortion-sensitive masked autoencoder for omnidirectional video quality assessment","author":"Hu","year":"2026","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.displa.2026.103611_b22","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.displa.2026.103611_b23","series-title":"Controlling vision-language models for universal image restoration","author":"Luo","year":"2023"},{"key":"10.1016\/j.displa.2026.103611_b24","first-page":"2555","article-title":"Exploring clip for assessing the look and feel of images","volume":"vol. 37","author":"Wang","year":"2023"},{"key":"10.1016\/j.displa.2026.103611_b25","doi-asserted-by":"crossref","unstructured":"W. Zhang, G. Zhai, Y. Wei, X. Yang, K. Ma, Blind image quality assessment via vision-language correspondence: A multitask learning perspective, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 14071\u201314081.","DOI":"10.1109\/CVPR52729.2023.01352"},{"issue":"3","key":"10.1016\/j.displa.2026.103611_b26","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","article-title":"Making a \u201ccompletely blind\u201d image quality analyzer","volume":"20","author":"Mittal","year":"2012","journal-title":"IEEE Signal Process. Lett."},{"issue":"8","key":"10.1016\/j.displa.2026.103611_b27","doi-asserted-by":"crossref","first-page":"2579","DOI":"10.1109\/TIP.2015.2426416","article-title":"A feature-enriched completely blind image quality evaluator","volume":"24","author":"Zhang","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.displa.2026.103611_b28","doi-asserted-by":"crossref","unstructured":"L. Kang, P. Ye, Y. Li, D. Doermann, Convolutional neural networks for no-reference image quality assessment, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 1733\u20131740.","DOI":"10.1109\/CVPR.2014.224"},{"key":"10.1016\/j.displa.2026.103611_b29","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.displa.2026.103611_b30","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.displa.2026.103611_b31","doi-asserted-by":"crossref","unstructured":"J. Ke, Q. Wang, Y. Wang, P. Milanfar, F. Yang, Musiq: Multi-scale image quality transformer, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 5148\u20135157.","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"10.1016\/j.displa.2026.103611_b32","series-title":"Blind image quality assessment using a deep bilinear convolutional neural network","author":"Network","year":"2022"},{"key":"10.1016\/j.displa.2026.103611_b33","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"},{"issue":"6","key":"10.1016\/j.displa.2026.103611_b34","doi-asserted-by":"crossref","first-page":"1178","DOI":"10.1109\/JSTSP.2023.3270621","article-title":"Blind quality assessment for in-the-wild images via hierarchical feature fusion and iterative mixed database training","volume":"17","author":"Sun","year":"2023","journal-title":"IEEE J. Sel. Top. Signal Process."},{"issue":"2","key":"10.1016\/j.displa.2026.103611_b35","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1109\/TBC.2022.3221689","article-title":"Deep neural network for blind visual quality assessment of 4K content","volume":"69","author":"Lu","year":"2022","journal-title":"IEEE Trans. Broadcast."},{"key":"10.1016\/j.displa.2026.103611_b36","doi-asserted-by":"crossref","first-page":"3700","DOI":"10.1109\/TMM.2020.3029891","article-title":"Comparative perceptual assessment of visual signals using free energy features","volume":"23","author":"Zhai","year":"2020","journal-title":"IEEE Trans. Multimed."},{"issue":"1","key":"10.1016\/j.displa.2026.103611_b37","doi-asserted-by":"crossref","first-page":"8","DOI":"10.3390\/vehicles7010008","article-title":"No-reference image quality assessment with moving spectrum and laplacian filter for autonomous driving environment","volume":"7","author":"Nam","year":"2025","journal-title":"Vehicles"},{"key":"10.1016\/j.displa.2026.103611_b38","article-title":"Robustness of panoptic segmentation for degraded automotive cameras data","author":"Wang","year":"2025","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.displa.2026.103611_b39","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.displa.2026.103611_b40","series-title":"International Conference on Machine Learning","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021"},{"key":"10.1016\/j.displa.2026.103611_b41","series-title":"Language-driven semantic segmentation","author":"Li","year":"2022"},{"key":"10.1016\/j.displa.2026.103611_b42","doi-asserted-by":"crossref","unstructured":"J. Xu, S. De Mello, S. Liu, W. Byeon, T. Breuel, J. Kautz, X. Wang, Groupvit: Semantic segmentation emerges from text supervision, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 18134\u201318144.","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"10.1016\/j.displa.2026.103611_b43","series-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021"},{"key":"10.1016\/j.displa.2026.103611_b44","unstructured":"L.H. Li, P. Zhang, H. Zhang, J. Yang, C. Li, Y. Zhong, L. Wang, L. Yuan, L. Zhang, J.-N. Hwang, et al., Grounded language-image pre-training, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10965\u201310975."},{"key":"10.1016\/j.displa.2026.103611_b45","series-title":"Multi-modal prompt learning on blind image quality assessment","author":"Pan","year":"2024"},{"key":"10.1016\/j.displa.2026.103611_b46","first-page":"3985","article-title":"DR. Experts: Differential refinement of distortion-aware experts for blind image quality assessment","volume":"vol. 40","author":"Fu","year":"2026"},{"key":"10.1016\/j.displa.2026.103611_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2025.103045","article-title":"Multi-layer cross-modal prompt fusion for no-reference image quality assessment","volume":"88","author":"Lu","year":"2025","journal-title":"Displays"},{"key":"10.1016\/j.displa.2026.103611_b48","doi-asserted-by":"crossref","unstructured":"T. Li, L. Wang, Z. Xu, L. Zhu, W. Lu, H. Huang, Positive2negative: Breaking the information-lossy barrier in self-supervised single image denoising, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 17924\u201317934.","DOI":"10.1109\/CVPR52734.2025.01670"},{"key":"10.1016\/j.displa.2026.103611_b49","unstructured":"T. Li, K. He, Back to basics: Let denoising generative models denoise, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2026, pp. 36115\u201336125."},{"key":"10.1016\/j.displa.2026.103611_b50","series-title":"European Conference on Computer Vision","first-page":"74","article-title":"Microsoft COCO: Common objects in context","author":"Lin","year":"2014"},{"issue":"11","key":"10.1016\/j.displa.2026.103611_b51","doi-asserted-by":"crossref","first-page":"3440","DOI":"10.1109\/TIP.2006.881959","article-title":"A statistical evaluation of recent full reference image quality assessment algorithms","volume":"15","author":"Sheikh","year":"2006","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"10.1016\/j.displa.2026.103611_b52","doi-asserted-by":"crossref","first-page":"011006","DOI":"10.1117\/1.3267105","article-title":"Most apparent distortion: Full-reference image quality assessment and the role of strategy","volume":"19","author":"Larson","year":"2010","journal-title":"J. Electron. Imaging"},{"issue":"2","key":"10.1016\/j.displa.2026.103611_b53","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1109\/TBC.2018.2816783","article-title":"Blind image quality estimation via distortion aggravation","volume":"64","author":"Min","year":"2018","journal-title":"IEEE Trans. Broadcast."},{"key":"10.1016\/j.displa.2026.103611_b54","doi-asserted-by":"crossref","first-page":"3474","DOI":"10.1109\/TIP.2021.3061932","article-title":"Uncertainty-aware blind image quality assessment in the laboratory and wild","volume":"30","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.displa.2026.103611_b55","doi-asserted-by":"crossref","unstructured":"S.A. Golestaneh, S. Dadsetan, K.M. Kitani, No-reference image quality assessment via transformers, relative ranking, and self-consistency, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 1220\u20131230.","DOI":"10.1109\/WACV51458.2022.00404"},{"key":"10.1016\/j.displa.2026.103611_b56","series-title":"Local distortion aware efficient transformer adaptation for image quality assessment","author":"Xu","year":"2023"},{"key":"10.1016\/j.displa.2026.103611_b57","series-title":"QMamba: On first exploration of vision mamba for image quality assessment","author":"Guan","year":"2024"},{"key":"10.1016\/j.displa.2026.103611_b58","series-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"}],"container-title":["Displays"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S014193822600274X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S014193822600274X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:29:34Z","timestamp":1783787374000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S014193822600274X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":58,"alternative-id":["S014193822600274X"],"URL":"https:\/\/doi.org\/10.1016\/j.displa.2026.103611","relation":{},"ISSN":["0141-9382"],"issn-type":[{"value":"0141-9382","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Text-Guided Adaptive-Balance Distortion-Sensitive Multi-Modal Pre-Trained Model for Blind Image Quality Assessment","name":"articletitle","label":"Article Title"},{"value":"Displays","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.displa.2026.103611","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":"103611"}}