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.
@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}
}