VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations
Year: 2025
Type: preprint
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.
Source: arXiv (Cornell University)
Authors: Qiao, Qianqian, Zheng, DanDan, Bo, Yihang, Peng, Bao, Huang, Heng, Jiang, Longteng, Wang, Huaye, Chen, Jingdong, Zhou, Jun, Jin, Xin
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7102586478
Cites:
Cited by:
Related to: