Video aesthetic assessment, a vital area in multimedia computing, integrates computer vision with human cognition. Its progress is limited by the lack of standardized datasets and robust models, as the temporal dynamics of video and multimodal fusion challenges hinder direct application of image-based methods. This study introduces VADB, the largest video aesthetic database with 10,490 diverse videos annotated by 37 professionals across multiple aesthetic dimensions, including overall and attribute-specific aesthetic scores, rich language comments and objective tags. We propose VADB-Net, a dual-modal pre-training framework with a two-stage training strategy, which outperforms existing video quality assessment models in scoring tasks and supports downstream video aesthetic assessment tasks. The dataset and source code are available at https://github.com/BestiVictory/VADB.
@article{arxiv.2510.25238,
title = {VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations},
author = {Qianqian Qiao and DanDan Zheng and Yihang Bo and Bao Peng and Heng Huang and Longteng Jiang and Huaye Wang and Jingdong Chen and Jun Zhou and Xin Jin},
journal= {arXiv preprint arXiv:2510.25238},
year = {2025}
}