Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.02330 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910857586278400 |
|---|---|
| author | Shen, Guotao Yan, Ziheng Jin, Xin Wu, Longhai Chen, Jie Cho, Ilhyun Hahm, Cheul-Hee |
| author_facet | Shen, Guotao Yan, Ziheng Jin, Xin Wu, Longhai Chen, Jie Cho, Ilhyun Hahm, Cheul-Hee |
| contents | In the research of video quality assessment (VQA), two-branch network has emerged as a promising solution. It decouples VQA with separate technical and aesthetic branches to measure the perception of low-level distortions and high-level semantics respectively. However, we argue that while technical and aesthetic perspectives are complementary, the technical perspective itself should be measured in semantic-aware manner. We hypothesize that existing technical branch struggles to perceive the semantics of high-resolution videos, as it is trained on local mini-patches sampled from videos. This issue can be hidden by apparently good results on low-resolution videos, but indeed becomes critical for high-resolution VQA. This work introduces SiamVQA, a simple but effective Siamese network for highre-solution VQA. SiamVQA shares weights between technical and aesthetic branches, enhancing the semantic perception ability of technical branch to facilitate technical-quality representation learning. Furthermore, it integrates a dual cross-attention layer for fusing technical and aesthetic features. SiamVQA achieves state-of-the-art accuracy on high-resolution benchmarks, and competitive results on lower-resolution benchmarks. Codes will be available at: https://github.com/srcn-ivl/SiamVQA |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_02330 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring Simple Siamese Network for High-Resolution Video Quality Assessment Shen, Guotao Yan, Ziheng Jin, Xin Wu, Longhai Chen, Jie Cho, Ilhyun Hahm, Cheul-Hee Computer Vision and Pattern Recognition In the research of video quality assessment (VQA), two-branch network has emerged as a promising solution. It decouples VQA with separate technical and aesthetic branches to measure the perception of low-level distortions and high-level semantics respectively. However, we argue that while technical and aesthetic perspectives are complementary, the technical perspective itself should be measured in semantic-aware manner. We hypothesize that existing technical branch struggles to perceive the semantics of high-resolution videos, as it is trained on local mini-patches sampled from videos. This issue can be hidden by apparently good results on low-resolution videos, but indeed becomes critical for high-resolution VQA. This work introduces SiamVQA, a simple but effective Siamese network for highre-solution VQA. SiamVQA shares weights between technical and aesthetic branches, enhancing the semantic perception ability of technical branch to facilitate technical-quality representation learning. Furthermore, it integrates a dual cross-attention layer for fusing technical and aesthetic features. SiamVQA achieves state-of-the-art accuracy on high-resolution benchmarks, and competitive results on lower-resolution benchmarks. Codes will be available at: https://github.com/srcn-ivl/SiamVQA |
| title | Exploring Simple Siamese Network for High-Resolution Video Quality Assessment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.02330 |