Enhancing full-reference image quality assessment via dual-attention fusion of global–local features and CLIP-based text prior.
Saved in:
| Title: | Enhancing full-reference image quality assessment via dual-attention fusion of global–local features and CLIP-based text prior. |
|---|---|
| Authors: | Huang, Mengyao1 (AUTHOR) hmy0605@stu.xjtu.edu.cn, Zhang, Yi1 (AUTHOR) yi.zhang.osu@xjtu.edu.cn, Chandler, Damon M.2 (AUTHOR) chandler@fc.ritsumei.ac.jp, Leszczuk, Mikołaj3 (AUTHOR) mikolaj.leszczuk@agh.edu.pl, Farias, Mylène C. Q.4 (AUTHOR) mylene@txstate.edu |
| Source: | EURASIP Journal on Image & Video Processing. 3/11/2026, Vol. 2026 Issue 1, p1-26. 26p. |
| Subjects: | Image quality analysis, Feature extraction, Deep learning, Artificial neural networks |
| Abstract: | Image quality assessment (IQA) is a field that focuses on evaluating the quality of images, playing a crucial role in various image processing and/or computer vision applications. Traditional full-reference (FR) IQA algorithms struggle with an accurate perceptual quality evaluation due in part to their reliance on handcrafted features and simple mathematical functions to calculate the elementwise distance between the reference and distorted images. Although deep-learning-based FR IQA methods have shown advantages in providing a certain degree of tolerance to texture resampling, their performances are still limited by the redundant model parameters and ineffective quality-aware feature extraction/representation. To address this issue, in this paper, we propose a multi-modal dual-attention FR IQA algorithm based on combining a global-and-local image structure analysis with text information interpreted by the widely used large language model. Specifically, the proposed multi-modal dual-attention network consists of four modules. First, a global-and-local feature extraction module was employed to extract the quality-aware features from the reference and distorted images, which were then realigned along the spatial and channel dimensions by a feature fusion module. To take into account both the channel and spatial attentions and thus increase the model capacity in representing long-range dependencies among different image areas, a feature enhancement module was designed to encode the spatial information along two directions, based on which the direction-aware attention maps with position information were generated. Finally, the text prior knowledge interpreted by the contrastive language-image pre-training (CLIP) model was embedded to assist the attention-based prediction module for quality estimation. Experimental results on four benchmark datasets demonstrate the effectiveness of our model as compared with other state-of-the-art FR IQA methods. The code is available at https://vinelab.jp/m2da/. [ABSTRACT FROM AUTHOR] |
| Copyright of EURASIP Journal on Image & Video Processing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 193005332 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Enhancing full-reference image quality assessment via dual-attention fusion of global–local features and CLIP-based text prior. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Huang%2C+Mengyao%22">Huang, Mengyao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> hmy0605@stu.xjtu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Zhang%2C+Yi%22">Zhang, Yi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> yi.zhang.osu@xjtu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Chandler%2C+Damon+M%2E%22">Chandler, Damon M.</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> chandler@fc.ritsumei.ac.jp</i><br /><searchLink fieldCode="AR" term="%22Leszczuk%2C+Mikołaj%22">Leszczuk, Mikołaj</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> mikolaj.leszczuk@agh.edu.pl</i><br /><searchLink fieldCode="AR" term="%22Farias%2C+Mylène+C%2E+Q%2E%22">Farias, Mylène C. Q.</searchLink><relatesTo>4</relatesTo> (AUTHOR)<i> mylene@txstate.edu</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22EURASIP+Journal+on+Image+%26+Video+Processing%22">EURASIP Journal on Image & Video Processing</searchLink>. 3/11/2026, Vol. 2026 Issue 1, p1-26. 26p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Image+quality+analysis%22">Image quality analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Feature+extraction%22">Feature extraction</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Image quality assessment (IQA) is a field that focuses on evaluating the quality of images, playing a crucial role in various image processing and/or computer vision applications. Traditional full-reference (FR) IQA algorithms struggle with an accurate perceptual quality evaluation due in part to their reliance on handcrafted features and simple mathematical functions to calculate the elementwise distance between the reference and distorted images. Although deep-learning-based FR IQA methods have shown advantages in providing a certain degree of tolerance to texture resampling, their performances are still limited by the redundant model parameters and ineffective quality-aware feature extraction/representation. To address this issue, in this paper, we propose a multi-modal dual-attention FR IQA algorithm based on combining a global-and-local image structure analysis with text information interpreted by the widely used large language model. Specifically, the proposed multi-modal dual-attention network consists of four modules. First, a global-and-local feature extraction module was employed to extract the quality-aware features from the reference and distorted images, which were then realigned along the spatial and channel dimensions by a feature fusion module. To take into account both the channel and spatial attentions and thus increase the model capacity in representing long-range dependencies among different image areas, a feature enhancement module was designed to encode the spatial information along two directions, based on which the direction-aware attention maps with position information were generated. Finally, the text prior knowledge interpreted by the contrastive language-image pre-training (CLIP) model was embedded to assist the attention-based prediction module for quality estimation. Experimental results on four benchmark datasets demonstrate the effectiveness of our model as compared with other state-of-the-art FR IQA methods. The code is available at https://vinelab.jp/m2da/. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of EURASIP Journal on Image & Video Processing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=193005332 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1186/s13640-026-00687-6 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 26 StartPage: 1 Subjects: – SubjectFull: Image quality analysis Type: general – SubjectFull: Feature extraction Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Artificial neural networks Type: general Titles: – TitleFull: Enhancing full-reference image quality assessment via dual-attention fusion of global–local features and CLIP-based text prior. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Huang, Mengyao – PersonEntity: Name: NameFull: Zhang, Yi – PersonEntity: Name: NameFull: Chandler, Damon M. – PersonEntity: Name: NameFull: Leszczuk, Mikołaj – PersonEntity: Name: NameFull: Farias, Mylène C. Q. IsPartOfRelationships: – BibEntity: Dates: – D: 11 M: 03 Text: 3/11/2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 16875176 Numbering: – Type: volume Value: 2026 – Type: issue Value: 1 Titles: – TitleFull: EURASIP Journal on Image & Video Processing Type: main |
| ResultId | 1 |
