Multi-modal Learnable Queries for Image Aesthetics Assessment
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929333881274368 |
|---|---|
| author | Xiong, Zhiwei Zhang, Yunfan Shen, Zhiqi Ren, Peiran Yu, Han |
| author_facet | Xiong, Zhiwei Zhang, Yunfan Shen, Zhiqi Ren, Peiran Yu, Han |
| contents | Image aesthetics assessment (IAA) is attracting wide interest with the prevalence of social media. The problem is challenging due to its subjective and ambiguous nature. Instead of directly extracting aesthetic features solely from the image, user comments associated with an image could potentially provide complementary knowledge that is useful for IAA. With existing large-scale pre-trained models demonstrating strong capabilities in extracting high-quality transferable visual and textual features, learnable queries are shown to be effective in extracting useful features from the pre-trained visual features. Therefore, in this paper, we propose MMLQ, which utilizes multi-modal learnable queries to extract aesthetics-related features from multi-modal pre-trained features. Extensive experimental results demonstrate that MMLQ achieves new state-of-the-art performance on multi-modal IAA, beating previous methods by 7.7% and 8.3% in terms of SRCC and PLCC, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_01326 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-modal Learnable Queries for Image Aesthetics Assessment Xiong, Zhiwei Zhang, Yunfan Shen, Zhiqi Ren, Peiran Yu, Han Computer Vision and Pattern Recognition Image aesthetics assessment (IAA) is attracting wide interest with the prevalence of social media. The problem is challenging due to its subjective and ambiguous nature. Instead of directly extracting aesthetic features solely from the image, user comments associated with an image could potentially provide complementary knowledge that is useful for IAA. With existing large-scale pre-trained models demonstrating strong capabilities in extracting high-quality transferable visual and textual features, learnable queries are shown to be effective in extracting useful features from the pre-trained visual features. Therefore, in this paper, we propose MMLQ, which utilizes multi-modal learnable queries to extract aesthetics-related features from multi-modal pre-trained features. Extensive experimental results demonstrate that MMLQ achieves new state-of-the-art performance on multi-modal IAA, beating previous methods by 7.7% and 8.3% in terms of SRCC and PLCC, respectively. |
| title | Multi-modal Learnable Queries for Image Aesthetics Assessment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.01326 |