{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T07:36:41Z","timestamp":1774510601364,"version":"3.50.1"},"reference-count":48,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:00:00Z","timestamp":1774310400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Fundamental Research Funds for the Safety Special Project of the Civil Aviation Administration of China (CAAC)\n\t\t\t\t\t\t              https:\/\/ror.org\/05gfwht30","award":["KG2025007"],"award-info":[{"award-number":["KG2025007"]}]},{"name":"Sichuan Science and Technology Program","award":["2025YFHZ0023"],"award-info":[{"award-number":["2025YFHZ0023"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["PHD2023-043"],"award-info":[{"award-number":["PHD2023-043"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["25CAFUC04057"],"award-info":[{"award-number":["25CAFUC04057"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Sichuan Flight Engineering Technology Research Center Foundation","award":["GY2024-22C"],"award-info":[{"award-number":["GY2024-22C"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Blind image quality assessment (BIQA) without reference images remains significantly challenging due to the fact that perceptual quality is largely determined by subtle, spatially localized distortions. However, existing Contrastive Language\u2013Image Pre-training (CLIP)-based methods exhibit limited sensitivity to fine-grained degradations such as local blur, noise, compression artifacts, and exposure inconsistencies, since they are optimized for global semantic alignment. To overcome these limitations, we propose a fine-grained vision\u2013language framework that enhances distortion-aware representation by considering both fine-grained visual and detailed textual domains. Specially, our method employs a fine-grained CLIP architecture in conjunction with explicit textual descriptions to enable the effective identification of subtle regional degradations. Furthermore, a parameter-efficient prompt-tuning strategy is utilized to facilitate the learning of task-adaptive prompt representations tailored to image quality assessment (IQA). Extensive experiments on three widely used in-the-wild IQA benchmarks show that the proposed method achieves strong consistency with human subjective judgments: our training-free FGCLIP-IQA reaches a maximum SROCC of 0.732 on KonIQ-10k, outperforming the vanilla CLIP-IQA baseline, while the prompt-tuned FGCLIP-IQA+ further achieves a maximum SROCC of 0.909 on KonIQ-10k with only a small number of learnable parameters and exhibits robust cross-dataset generalization capabilities. These results demonstrate that the fine-grained vision\u2013language alignment shows great potential for future development, and provides an efficient and accurate solution for the BIQA task.<\/jats:p>","DOI":"10.3390\/info17040316","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T10:07:13Z","timestamp":1774433233000},"page":"316","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Grained Vision-Language Method with Prompt Tuning for Blind Image Quality Assessment"],"prefix":"10.3390","volume":"17","author":[{"given":"Kai","family":"Tan","sequence":"first","affiliation":[{"name":"College of Air Traffic Management, Civil Aviation Flight University of China, 46 Nanchang Road, Guanghan 618307, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wang","family":"Luo","sequence":"additional","affiliation":[{"name":"State Grid Electric Power Research Institute Co., Ltd., Nanjing 210003, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaqing","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Air Traffic Management, Civil Aviation Flight University of China, 46 Nanchang Road, Guanghan 618307, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"He","sequence":"additional","affiliation":[{"name":"College of Air Traffic Management, Civil Aviation Flight University of China, 46 Nanchang Road, Guanghan 618307, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7723-3492","authenticated-orcid":false,"given":"Yumei","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Air Traffic Management, Civil Aviation Flight University of China, 46 Nanchang Road, Guanghan 618307, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Qingdao International Airport Group, Qingdao 266317, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Air Traffic Management, Civil Aviation Flight University of China, 46 Nanchang Road, Guanghan 618307, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1109\/TIP.2005.859378","article-title":"Image information and visual quality","volume":"15","author":"Sheikh","year":"2006","journal-title":"IEEE Trans. Image Process."},{"key":"ref_2","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."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Fang, Y., Zhu, H., Zeng, Y., Ma, K., and Wang, Z. (2020, January 13\u201319). Perceptual quality assessment of smartphone photography. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Kim, J.-H., and Sung, S.-M. (2024). Quality Analysis of Unmanned Aerial Vehicle Images Using a Resolution Target. Appl. Sci., 14.","DOI":"10.3390\/app14052154"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Ludwig, M., M. Runge, C., Friess, N., Koch, T.L., Richter, S., Seyfried, S., Wraase, L., Lobo, A., Sebasti\u00e0, M.-T., and Reudenbach, C. (2020). Quality Assessment of Photogrammetric Methods\u2014A Workflow for Reproducible UAS Orthomosaics. Remote Sens., 12.","DOI":"10.3390\/rs12223831"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Zhang, Y., Han, J., and Wang, Y. (2021). Analysis of Image Quality Assessment Methods for Aerial Images. The 10th International Conference on Computer Engineering and Networks. CENet 2020, Springer. Advances in Intelligent Systems and Computing.","DOI":"10.1007\/978-981-15-8462-6_19"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Yang, Y., Lei, Z., and Li, C. (2024). No-Reference Image Quality Assessment Combining Swin-Transformer and Natural Scene Statistics. Sensors, 24.","DOI":"10.3390\/s24165221"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Dugonik, B., Dugonik, A., Marovt, M., and Golob, M. (2020). Image Quality Assessment of Digital Image Capturing Devices for Melanoma Detection. Appl. Sci., 10.","DOI":"10.3390\/app10082876"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Herath, H.M.S.S., Herath, H.M.K.K.M.B., Madusanka, N., and Lee, B.-I. (2025). A Systematic Review of Medical Image Quality Assessment. Imaging, 11.","DOI":"10.3390\/jimaging11040100"},{"key":"ref_10","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":"ref_11","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":"ref_12","doi-asserted-by":"crossref","first-page":"8614","DOI":"10.1109\/TCSVT.2024.3387451","article-title":"Robust unpaired image dehazing via adversarial deformation constraint","volume":"34","author":"Wei","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ye, P., Kumar, J., Kang, L., and Doermann, D. (2013, January 23\u201328). Real-time no-reference image quality assessment based on filter learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.","DOI":"10.1109\/CVPR.2013.132"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process. (TIP)"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"103046","DOI":"10.1016\/j.displa.2025.103046","article-title":"Causal perception inspired representation learning for trustworthy image quality assessment","volume":"88","author":"Wang","year":"2025","journal-title":"Displays"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1109\/MSP.2008.930649","article-title":"Mean squared error: Love it or leave it? A new look at Signal Fidelity Measures","volume":"26","author":"Wang","year":"2009","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_17","first-page":"1398","article-title":"Multiscale structural similarity for image quality assessment","volume":"Volume 2","author":"Wang","year":"2003","journal-title":"The Thirty-Seventh Asilomar Conference on Signals, Systems & Computers"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"5617","DOI":"10.1109\/TMM.2025.3543014","article-title":"Learning with noisy low-cost mos for image quality assessment via dual-bias calibration","volume":"27","author":"Wang","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"102955","DOI":"10.1016\/j.displa.2024.102955","article-title":"Scoring structure regularized gradient boosting network for blind image quality assessment","volume":"87","author":"Wang","year":"2025","journal-title":"Displays"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Hu, L., Peng, J., Zhao, T., Yu, W., and Hu, B. (2023). A Blind Image Quality Index for Synthetic and Authentic Distortions with Hierarchical Feature Fusion. Appl. Sci., 13.","DOI":"10.3390\/app13063591"},{"key":"ref_21","first-page":"2555","article-title":"Exploring CLIP for assessing the look and feel of images","volume":"37","author":"Wang","year":"2023","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhang, B., Zhang, P., Dong, X., Zang, Y., and Wang, J. (2024). Long-CLIP: Unlocking the long-text capability of CLIP. European Conference on Computer Vision, Springer Nature.","DOI":"10.1007\/978-3-031-72983-6_18"},{"key":"ref_23","unstructured":"Xie, C., Wang, B., Kong, F., Li, J., Liang, D., Zhang, G., Leng, D., and Yin, Y. (2025). FG-CLIP: Fine-Grained Visual and Textual Alignment. arXiv."},{"key":"ref_24","unstructured":"Xie, C., Wang, B., Kong, F., Li, J., Liang, D., Ao, J., Leng, D., and Yin, Y. (2025). FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., and Liu, Z. (2022, January 18\u201324). Conditional prompt learning for vision-language models. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref_26","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":"ref_27","doi-asserted-by":"crossref","first-page":"123788","DOI":"10.1109\/ACCESS.2019.2938900","article-title":"A survey of dnn methods for blind image quality assessment","volume":"7","author":"Yang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ye, P., Kumar, J., Kang, L., and Doermann, D. (2012). Unsupervised feature learning framework for no-reference image quality assessment. IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2013.132"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Su, S., Yan, Q., Zhu, Y., Zhang, C., Ge, X., Sun, J., and Zhang, Y. (2020). Blindly assess image quality in the wild guided by a self-adaptive hyper network. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chen, F., Fu, H., Yu, H., and Chu, Y. (2023). No-reference image quality assessment based on a multitask image restoration network. Appl. Sci., 13.","DOI":"10.20944\/preprints202304.0723.v1"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Kang, L., Ye, P., Li, Y., and Doermann, D. (2014). Convolutional neural networks for no-reference image quality assessment. IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2014.224"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1109\/TIP.2017.2760518","article-title":"Deep neural networks for no-reference and full-reference image quality assessment","volume":"27","author":"Bosse","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Sun, W., Duan, H., Min, X., Zhai, G., and Yang, X. (2022). Blind Quality Assessment for In-the-wild Images via Hierarchical Feature Fusion Strategy. International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB), IEEE.","DOI":"10.1109\/BMSB55706.2022.9828590"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Lin, W., Kwan-Yee, K., and Wang, G. (2018, January 18\u201323). Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00083"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Ke, J., Wang, Q., Wang, Y., Milanfar, P., and Yang, F. (2021, January 10\u201317). MUSIQ: Multi-scale image quality transformer. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Yang, S., Wu, T., Shi, S., Lao, S., Gong, Y., Cao, M., Wang, J., and Yang, Y. (2022, January 18\u201324). MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPRW56347.2022.00126"},{"key":"ref_37","unstructured":"Wu, H., Zhang, Z., Zhang, W., Chen, C., Liao, L., Li, C., Gao, Y., and Lin, W. (2023). Q-Align: Teaching LMMs for visual scoring via discrete text-defined levels. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"You, Z., Cai, X., Gu, J., Xue, T., and Dong, C. (2025, January 11\u201315). Teaching large language models to regress accurate image quality scores using score distribution. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.01350"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Wu, T., Ma, K., Liang, J., Yang, Y., and Zhang, L. (2024). A comprehensive study of multimodal large language models for image quality assessment. European Conference on Computer Vision, Springer Nature.","DOI":"10.1007\/978-3-031-72904-1_9"},{"key":"ref_40","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., and Clark, J. (2021). Learning transferable visual models from natural language supervision. International Conference on Machine Learning, PMLR."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Yang, J., Zhang, P., Li, C., Codella, N., Li, L.H., Zhou, L., Dai, X., Yuan, L., and Li, Y. (2022, January 18\u201324). RegionCLIP: Region-based language-image pretraining. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref_42","first-page":"27896","article-title":"FineCLIP: Self-distilled region-based CLIP for better fine-grained understanding","volume":"37","author":"Jing","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"102992","DOI":"10.1016\/j.displa.2025.102992","article-title":"Adversarially Regularized Tri-Transformer Fusion for continual multimodal egocentric activity recognition","volume":"88","author":"Zhou","year":"2025","journal-title":"Displays"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/TMM.2024.3521746","article-title":"Cross-modal cognitive consensus guided audio-visual segmentation","volume":"27","author":"Shi","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"ref_45","first-page":"5576","article-title":"Relation-aware hierarchical prompt for open-vocabulary scene graph generation","volume":"39","author":"Liu","year":"2025","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"112735","DOI":"10.1016\/j.patcog.2025.112735","article-title":"Zero-Shot Egocentric Action Recognition via Chain-of-Imagination Prompts and Inertial Strengthening Adaptor","volume":"172","author":"He","year":"2025","journal-title":"Pattern Recognit."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1109\/LSP.2010.2043888","article-title":"A two-step framework for constructing blind image quality indices","volume":"17","author":"Moorthy","year":"2010","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_48","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."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/4\/316\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T05:42:55Z","timestamp":1774503775000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/4\/316"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,24]]},"references-count":48,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["info17040316"],"URL":"https:\/\/doi.org\/10.3390\/info17040316","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,24]]}}}