English

Multilevel Semantic-Aware Model for AI-Generated Video Quality Assessment

Computer Vision and Pattern Recognition 2025-01-07 v1

Abstract

The rapid development of diffusion models has greatly advanced AI-generated videos in terms of length and consistency recently, yet assessing AI-generated videos still remains challenging. Previous approaches have often focused on User-Generated Content(UGC), but few have targeted AI-Generated Video Quality Assessment methods. In this work, we introduce MSA-VQA, a Multilevel Semantic-Aware Model for AI-Generated Video Quality Assessment, which leverages CLIP-based semantic supervision and cross-attention mechanisms. Our hierarchical framework analyzes video content at three levels: frame, segment, and video. We propose a Prompt Semantic Supervision Module using text encoder of CLIP to ensure semantic consistency between videos and conditional prompts. Additionally, we propose the Semantic Mutation-aware Module to capture subtle variations between frames. Extensive experiments demonstrate our method achieves state-of-the-art results.

Keywords

Cite

@article{arxiv.2501.02706,
  title  = {Multilevel Semantic-Aware Model for AI-Generated Video Quality Assessment},
  author = {Jiaze Li and Haoran Xu and Shiding Zhu and Junwei He and Haozhao Wang},
  journal= {arXiv preprint arXiv:2501.02706},
  year   = {2025}
}
R2 v1 2026-06-28T20:57:05.445Z