{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T04:58:38Z","timestamp":1790485118513,"version":"4.1.0"},"reference-count":84,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100011205","name":"East China University of Technology","doi-asserted-by":"publisher","award":["DHYC-2025071"],"award-info":[{"award-number":["DHYC-2025071"]}],"id":[{"id":"10.13039\/501100011205","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62266001"],"award-info":[{"award-number":["62266001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62261001"],"award-info":[{"award-number":["62261001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Signal Processing"],"published-print":{"date-parts":[[2027,2]]},"DOI":"10.1016\/j.sigpro.2026.110859","type":"journal-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:45:37Z","timestamp":1785858337000},"page":"110859","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["DARRA: A distortion-aware residual recalibration adapter for MLLM-based no-reference image quality assessment"],"prefix":"10.1016","volume":"251","author":[{"given":"Tonghan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunfeng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huizhen","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.sigpro.2026.110859_bib0001","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"14071","article-title":"Blind image quality assessment via vision-language correspondence: a multitask learning perspective","author":"Zhang","year":"2023"},{"key":"10.1016\/j.sigpro.2026.110859_bib0002","series-title":"Proc. AAAI Conf. Artif. Intell.","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.sigpro.2026.110859_bib0003","series-title":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","first-page":"1","article-title":"Q-boost: on visual quality assessment ability of low-level multi-modality foundation models","author":"Zhang","year":"2024"},{"key":"10.1016\/j.sigpro.2026.110859_bib0004","series-title":"Computer Vision - ACCV 2024","first-page":"284","article-title":"ATTIQA: generalizable image quality feature extractor using attribute-aware pretraining","author":"Kwon","year":"2025"},{"key":"10.1016\/j.sigpro.2026.110859_bib0005","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.sigpro.2026.110859_bib0006","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."},{"issue":"11","key":"10.1016\/j.sigpro.2026.110859_bib0007","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.sigpro.2026.110859_bib0008","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/j.jvcir.2018.11.038","article-title":"Blind image quality assessment with semantic information","volume":"58","author":"Ji","year":"2019","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.sigpro.2026.110859_bib0009","series-title":"Proceedings of the Winter Conference on Applications of Computer Vision (WACV) Workshops","first-page":"207","article-title":"A distortion aware image quality assessment model","author":"Nguyen","year":"2025"},{"key":"10.1016\/j.sigpro.2026.110859_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2026.104768","article-title":"Multi-dimensional human preference assessment for AI-generated images with supervised contrastive learning","volume":"117","author":"Wei","year":"2026","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.sigpro.2026.110859_bib0011","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","first-page":"6327","article-title":"AIGIQA-20K: a large database for AI-generated image quality assessment","author":"Li","year":"2024"},{"issue":"8","key":"10.1016\/j.sigpro.2026.110859_bib0012","doi-asserted-by":"crossref","first-page":"6833","DOI":"10.1109\/TCSVT.2023.3319020","article-title":"AGIQA-3K: an open database for AI-generated image quality assessment","volume":"34","author":"Li","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.sigpro.2026.110859_bib0013","series-title":"2019 Eleventh International Conference on Quality of Multimedia Experience (QoMEX)","first-page":"1","article-title":"KADID-10k: a large-scale artificially distorted IQA database","author":"Lin","year":"2019"},{"key":"10.1016\/j.sigpro.2026.110859_bib0014","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.image.2014.10.009","article-title":"Image database TID2013: peculiarities, results and perspectives","volume":"30","author":"Ponomarenko","year":"2015","journal-title":"Signal Process. Image Commun."},{"key":"10.1016\/j.sigpro.2026.110859_bib0015","series-title":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","first-page":"6677","article-title":"Multimodal language models see better when they look shallower","author":"Chen","year":"2025"},{"key":"10.1016\/j.sigpro.2026.110859_bib0016","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9568","article-title":"Eyes wide shut? Exploring the visual shortcomings of multimodal LLMs","author":"Tong","year":"2024"},{"key":"10.1016\/j.sigpro.2026.110859_bib0017","series-title":"Advances in Neural Information Processing Systems","first-page":"27896","article-title":"FineCLIP: self-distilled region-based CLIP for better fine-grained understanding","volume":"vol. 37","author":"Jing","year":"2024"},{"key":"10.1016\/j.sigpro.2026.110859_bib0018","series-title":"ICLR 2025 Workshops: SSI-FM","article-title":"DetailCLIP: detail-oriented CLIP for fine-grained tasks","author":"Monsefi","year":"2025"},{"key":"10.1016\/j.sigpro.2026.110859_bib0019","series-title":"International Conference on Learning Representations","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.sigpro.2026.110859_bib0020","series-title":"Advances in Neural Information Processing Systems","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume":"vol. 34","author":"Raghu","year":"2021"},{"key":"10.1016\/j.sigpro.2026.110859_bib0021","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Q-Bench: a benchmark for general-purpose foundation models on low-level vision","author":"Wu","year":"2024"},{"key":"10.1016\/j.sigpro.2026.110859_bib0022","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"2662","article-title":"Boosting image quality assessment through efficient transformer adaptation with local feature enhancement","author":"Xu","year":"2024"},{"key":"10.1016\/j.sigpro.2026.110859_bib0023","series-title":"Computer Vision - ECCV 2020","first-page":"633","article-title":"PIPAL: a large-scale image quality assessment dataset for perceptual image restoration","author":"Gu","year":"2020"},{"key":"10.1016\/j.sigpro.2026.110859_bib0024","series-title":"Proceedings of the 41st International Conference on Machine Learning (ICML)","first-page":"54015","article-title":"Q-Align: teaching LMMs for visual scoring via discrete text-defined levels","volume":"vol. 235","author":"Wu","year":"2024"},{"key":"10.1016\/j.sigpro.2026.110859_bib0025","series-title":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"14483","article-title":"Teaching large language models to regress accurate image quality scores using score distribution","author":"You","year":"2025"},{"key":"10.1016\/j.sigpro.2026.110859_bib0026","series-title":"Advances in Neural Information Processing Systems","first-page":"32611","article-title":"Adaptive image quality assessment via teaching large multimodal model to compare","volume":"vol. 37","author":"Zhu","year":"2024"},{"key":"10.1016\/j.sigpro.2026.110859_bib0027","doi-asserted-by":"crossref","first-page":"6139","DOI":"10.1109\/TIP.2022.3205770","article-title":"No-reference image quality assessment by hallucinating pristine features","volume":"31","author":"Chen","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.sigpro.2026.110859_bib0028","series-title":"Proc. AAAI Conf. Artif. Intell.","first-page":"6934","article-title":"Beyond cosine similarity: magnitude-aware CLIP for no-reference image quality assessment","volume":"vol. 40","author":"Liao","year":"2026"},{"issue":"4","key":"10.1016\/j.sigpro.2026.110859_bib0029","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."},{"issue":"12","key":"10.1016\/j.sigpro.2026.110859_bib0030","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":"3","key":"10.1016\/j.sigpro.2026.110859_bib0031","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":"2013","journal-title":"IEEE Signal Process. Lett."},{"issue":"1","key":"10.1016\/j.sigpro.2026.110859_bib0032","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1109\/TCSVT.2018.2886771","article-title":"Blind image quality assessment using a deep bilinear convolutional neural network","volume":"30","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.sigpro.2026.110859_bib0033","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3664","article-title":"Blindly assess image quality in the wild guided by a self-adaptive hyper network","author":"Su","year":"2020"},{"key":"10.1016\/j.sigpro.2026.110859_bib0034","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"5128","article-title":"MUSIQ: multi-scale image quality transformer","author":"Ke","year":"2021"},{"key":"10.1016\/j.sigpro.2026.110859_bib0035","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","first-page":"1190","article-title":"MANIQA: multi-dimension attention network for no-reference image quality assessment","author":"Yang","year":"2022"},{"key":"10.1016\/j.sigpro.2026.110859_bib0036","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.119268","article-title":"ASCAM-former: blind image quality assessment based on adaptive spatial & channel attention merging transformer and image-to-patch weight sharing","volume":"215","author":"Ma","year":"2023","journal-title":"Expert Syst. Appl."},{"issue":"2","key":"10.1016\/j.sigpro.2026.110859_bib0037","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1109\/TBC.2022.3215249","article-title":"An end-to-end blind image quality assessment method using a recurrent network and self-attention","volume":"69","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Broadcast."},{"issue":"3","key":"10.1016\/j.sigpro.2026.110859_bib0038","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1109\/TBC.2023.3262163","article-title":"Multilevel feature fusion for end-to-end blind image quality assessment","volume":"69","author":"Lan","year":"2023","journal-title":"IEEE Trans. Broadcast."},{"issue":"2","key":"10.1016\/j.sigpro.2026.110859_bib0039","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1109\/TBC.2022.3231101","article-title":"Perception-oriented U-shaped transformer network for 360-degree no-reference image quality assessment","volume":"69","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Broadcast."},{"issue":"7","key":"10.1016\/j.sigpro.2026.110859_bib0040","doi-asserted-by":"crossref","first-page":"6403","DOI":"10.1109\/TCSVT.2024.3367904","article-title":"Video quality assessment for spatio-temporal resolution adaptive coding","volume":"34","author":"Zhu","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"12","key":"10.1016\/j.sigpro.2026.110859_bib0041","doi-asserted-by":"crossref","first-page":"12692","DOI":"10.1109\/TCSVT.2025.3586106","article-title":"No-reference image quality assessment: exploring intrinsic distortion characteristics via generative noise estimation with mamba","volume":"35","author":"Lan","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"6","key":"10.1016\/j.sigpro.2026.110859_bib0042","doi-asserted-by":"crossref","first-page":"3242","DOI":"10.1007\/s11263-024-02338-7","article-title":"Blind image quality assessment: exploring content fidelity perceptibility via quality adversarial learning","volume":"133","author":"Zhou","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.sigpro.2026.110859_bib0043","series-title":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"17990","article-title":"Image quality assessment: investigating causal perceptual effects with abductive counterfactual inference","author":"Shen","year":"2025"},{"issue":"1","key":"10.1016\/j.sigpro.2026.110859_bib0044","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1109\/TBC.2025.3609055","article-title":"Image quality assessment: exploring the similarity of deep features via covariance-constrained spectra","volume":"72","author":"Lang","year":"2026","journal-title":"IEEE Trans. Broadcast."},{"key":"10.1016\/j.sigpro.2026.110859_bib0045","series-title":"Computer Vision - ECCV 2024","first-page":"143","article-title":"A comprehensive study of multimodal large language models for image quality assessment","author":"Wu","year":"2025"},{"key":"10.1016\/j.sigpro.2026.110859_bib0046","series-title":"International Conference on Learning Representations (ICLR)","article-title":"MLLMs know where to look: training-free perception of small visual details with multimodal LLMs","author":"Zhang","year":"2025"},{"key":"10.1016\/j.sigpro.2026.110859_bib0047","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"25490","article-title":"Q-instruct: improving low-level visual abilities for multi-modality foundation models","author":"Wu","year":"2024"},{"key":"10.1016\/j.sigpro.2026.110859_bib0048","series-title":"Computer Vision - ECCV 2024: 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part III","first-page":"360","article-title":"Towards open-ended visual quality comparison","author":"Wu","year":"2024"},{"key":"10.1016\/j.sigpro.2026.110859_bib0049","series-title":"2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","first-page":"3383","article-title":"VQualA 2025 challenge on visual quality comparison for large multimodal models: methods and results","author":"Zhu","year":"2025"},{"key":"10.1016\/j.sigpro.2026.110859_bib0050","series-title":"Computer Vision - ECCV 2024: 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part XLVII","first-page":"259","article-title":"Depicting beyond scores: advancing image quality assessment through multi-modal language models","author":"You","year":"2024"},{"key":"10.1016\/j.sigpro.2026.110859_bib0051","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"486","article-title":"Q-ground: image quality grounding with large multi-modality models","author":"Chen","year":"2024"},{"key":"10.1016\/j.sigpro.2026.110859_bib0052","doi-asserted-by":"crossref","first-page":"8201","DOI":"10.1109\/TIP.2025.3639998","article-title":"Enhancing descriptive image quality assessment with a large-scale multi-modal dataset","volume":"34","author":"You","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.sigpro.2026.110859_bib0053","series-title":"2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","first-page":"4003","article-title":"iDETEX: empowering MLLMs for intelligent detailed explainable IQA","author":"Zhao","year":"2025"},{"key":"10.1016\/j.sigpro.2026.110859_bib0054","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","first-page":"1551","article-title":"Conv-adapter: exploring parameter efficient transfer learning for ConvNets","author":"Chen","year":"2024"},{"key":"10.1016\/j.sigpro.2026.110859_bib0055","series-title":"Advances in Neural Information Processing Systems","first-page":"16664","article-title":"AdaptFormer: adapting vision transformers for scalable visual recognition","volume":"vol. 35","author":"Chen","year":"2022"},{"key":"10.1016\/j.sigpro.2026.110859_bib0056","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"10.1016\/j.sigpro.2026.110859_bib0057","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"11863","article-title":"SimAM: a simple, parameter-free attention module for convolutional neural networks","volume":"vol. 139","author":"Yang","year":"2021"},{"key":"10.1016\/j.sigpro.2026.110859_bib0058","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"15469","article-title":"IQA-adapter: exploring knowledge transfer from image quality assessment to diffusion-based generative models","author":"Abud","year":"2025"},{"key":"10.1016\/j.sigpro.2026.110859_bib0059","first-page":"1","article-title":"IO-MOT: dual-modal feature fusion with instance embeddings and optical flow for multi-object tracking","author":"Lou","year":"2026","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.sigpro.2026.110859_bib0060","first-page":"1","article-title":"Boundary-aware feature fusion with dual-stream attention for remote sensing small object detection","volume":"63","author":"Song","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"6","key":"10.1016\/j.sigpro.2026.110859_bib0061","doi-asserted-by":"crossref","first-page":"5993","DOI":"10.1109\/TCSVT.2025.3535818","article-title":"An attention-locating algorithm for eliminating background effects in fine-grained visual classification","volume":"35","author":"Huang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"2","key":"10.1016\/j.sigpro.2026.110859_bib0062","doi-asserted-by":"crossref","first-page":"5752","DOI":"10.1109\/TCE.2025.3570181","article-title":"AFES: attention-based feature excitation and sorting for action recognition","volume":"71","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Consum. Electron."},{"issue":"11","key":"10.1016\/j.sigpro.2026.110859_bib0063","doi-asserted-by":"crossref","first-page":"8282","DOI":"10.1109\/TII.2025.3588622","article-title":"GAANet: graph aggregation alignment feature fusion for multispectral object detection","volume":"21","author":"Zheng","year":"2025","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.sigpro.2026.110859_bib0064","doi-asserted-by":"crossref","first-page":"7444","DOI":"10.1109\/TMM.2025.3599097","article-title":"COFNet: contrastive object-aware fusion using box-level masks for multispectral object detection","volume":"27","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Multimed."},{"issue":"4","key":"10.1016\/j.sigpro.2026.110859_bib0065","doi-asserted-by":"crossref","first-page":"95:1","DOI":"10.1145\/3630100","article-title":"Robust RGB-T tracking via adaptive modality weight correlation filters and cross-modality learning","volume":"20","author":"Zhou","year":"2024","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"issue":"11","key":"10.1016\/j.sigpro.2026.110859_bib0066","doi-asserted-by":"crossref","first-page":"12994","DOI":"10.1109\/TII.2024.3431044","article-title":"EF-DETR: a lightweight transformer-based object detector with an encoder-free neck","volume":"20","author":"Cheng","year":"2024","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.sigpro.2026.110859_bib0067","series-title":"Computer Vision \u2013 ECCV 2024","first-page":"143","article-title":"ClearCLIP: decomposing CLIP representations for dense vision-language inference","author":"Lan","year":"2025"},{"issue":"5","key":"10.1016\/j.sigpro.2026.110859_bib0068","doi-asserted-by":"crossref","first-page":"2200","DOI":"10.1109\/TIP.2018.2883741","article-title":"Two-stream convolutional networks for blind image quality assessment","volume":"28","author":"Yan","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.sigpro.2026.110859_bib0069","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","first-page":"4199","article-title":"Dilated convolutional transformer for high-quality image deraining","author":"Li","year":"2023"},{"key":"10.1016\/j.sigpro.2026.110859_bib0070","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Dual-kernel adapter: expanding spatial horizons for data-constrained medical image analysis","author":"Zhu","year":"2026"},{"issue":"7","key":"10.1016\/j.sigpro.2026.110859_bib0071","doi-asserted-by":"crossref","first-page":"195:1","DOI":"10.1145\/3649899","article-title":"Joint distortion restoration and quality feature learning for no-reference image quality assessment","volume":"20","author":"Yang","year":"2024","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"key":"10.1016\/j.sigpro.2026.110859_bib0072","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5846","article-title":"Re-IQA: unsupervised learning for image quality assessment in the wild","author":"Saha","year":"2023"},{"key":"10.1016\/j.sigpro.2026.110859_bib0073","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"13040","article-title":"mPLUG-Owl2: revolutionizing multi-modal large language model with modality collaboration","author":"Ye","year":"2024"},{"key":"10.1016\/j.sigpro.2026.110859_bib0074","series-title":"International Conference on Learning Representations (ICLR)","article-title":"LoRA: low-rank adaptation of large language models","author":"Hu","year":"2022"},{"key":"10.1016\/j.sigpro.2026.110859_bib0075","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.sigpro.2026.110859_bib0076","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3674","article-title":"Perceptual quality assessment of smartphone photography","author":"Fang","year":"2020"},{"issue":"1","key":"10.1016\/j.sigpro.2026.110859_bib0077","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":"2016","journal-title":"IEEE Trans. Image Process."},{"issue":"6","key":"10.1016\/j.sigpro.2026.110859_bib0078","doi-asserted-by":"crossref","first-page":"175:1","DOI":"10.1145\/2508363.2508391","article-title":"A no-reference metric for evaluating the quality of motion deblurring","volume":"32","author":"Liu","year":"2013","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.sigpro.2026.110859_bib0079","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"12742","article-title":"Toward generalized image quality assessment: relaxing the perfect reference quality assumption","author":"Chen","year":"2025"},{"key":"10.1016\/j.sigpro.2026.110859_bib0080","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.sigpro.2026.110859_bib0081","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125349","article-title":"Image quality difference perception ability: a BIQA model effectiveness metric based on model falsification method","volume":"260","author":"Zhu","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.sigpro.2026.110859_bib0082","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.sigpro.2026.110859_bib0083","doi-asserted-by":"crossref","first-page":"5092","DOI":"10.1109\/TMM.2023.3330096","article-title":"Stitched wide field of view light field image quality assessment: benchmark database and objective metric","volume":"26","author":"Cui","year":"2024","journal-title":"IEEE Trans. Multimed."},{"issue":"5","key":"10.1016\/j.sigpro.2026.110859_bib0084","doi-asserted-by":"crossref","first-page":"6783","DOI":"10.1109\/TCSVT.2026.3652641","article-title":"Multi-modal cross-attention-guided network for audio-visual quality evaluation via visual saliency and mel-spectrum features","volume":"36","author":"Lin","year":"2026","journal-title":"IEEE Trans. Circuits Syst. Video Technol."}],"container-title":["Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0165168426003725?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0165168426003725?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T04:31:42Z","timestamp":1790483502000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0165168426003725"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,2]]},"references-count":84,"alternative-id":["S0165168426003725"],"URL":"https:\/\/doi.org\/10.1016\/j.sigpro.2026.110859","relation":{},"ISSN":["0165-1684"],"issn-type":[{"value":"0165-1684","type":"print"}],"subject":[],"published":{"date-parts":[[2027,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DARRA: A distortion-aware residual recalibration adapter for MLLM-based no-reference image quality assessment","name":"articletitle","label":"Article Title"},{"value":"Signal Processing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.sigpro.2026.110859","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":"110859"}}