VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations
Abstract
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.
Cite
Text
Qiao et al. "VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations." Advances in Neural Information Processing Systems, 2025.Markdown
[Qiao et al. "VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations." Advances in Neural Information Processing Systems, 2025.](https://mlanthology.org/neurips/2025/qiao2025neurips-vadb/)BibTeX
@inproceedings{qiao2025neurips-vadb,
title = {{VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations}},
author = {Qiao, Qianqian and Zheng, DanDan and Bo, Yihang and Peng, Bao and Huang, Heng and Jiang, Longteng and Wang, Huaye and Chen, Jingdong and Zhou, Jun and Jin, Xin},
booktitle = {Advances in Neural Information Processing Systems},
year = {2025},
url = {https://mlanthology.org/neurips/2025/qiao2025neurips-vadb/}
}