paper-with-me

홈 › Papers

VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations

2025-10-29 · Qianqian Qiao, DanDan Zheng, Yihang Bo, Bao Peng, Heng Huang, Longteng Jiang, Huaye Wang, Jingdong Chen, Jun Zhou, Xin Jin arxiv

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.

📄 PDF Abstract BibTeX arXiv:2510.25238

Code (0)

등록된 구현이 없습니다.

Tasks

Video Quality Assessment

Similar Papers 제목 키워드 기반

Detection of pose orientation across single and multiple axes in case of 3D face images

2013-09-18 · Parama Bagchi, Debotosh Bhattacharjee, Mita Nasipuri, Dipak Kumar Basu

In this paper, we propose a new approach that takes as input a 3D face image across X, Y and Z axes as well as both Y and X axes and gives output as its pose i.e. it tells whether the face is oriented with respect the X,…

Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives

2022-11-09 · ICCV 2023 1 · HaoNing Wu, Erli Zhang, Liang Liao, Chaofeng Chen 외

The rapid increase in user-generated-content (UGC) videos calls for the development of effective video quality assessment (VQA) algorithms. However, the objective of the UGC-VQA problem is still ambiguous and can be view…

DisentanglementVideo GenerationVideo Quality AssessmentVisual Question Answering (VQA)

ILGNet: Inception Modules with Connected Local and Global Features for Efficient Image Aesthetic Quality Classification using Domain Adaptation

2016-10-07 · Xin Jin, Le Wu, Xiao-Dong Li, Xiaokun Zhang 외

In this paper, we address a challenging problem of aesthetic image classification, which is to label an input image as high or low aesthetic quality. We take both the local and global features of images into consideratio…

Aesthetics Quality AssessmentDomain AdaptationGeneral Classificationimage-classification+1

AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception

2024-04-15 · Yipo Huang, Xiangfei Sheng, Zhichao Yang, Quan Yuan 외

The highly abstract nature of image aesthetics perception (IAP) poses significant challenge for current multimodal large language models (MLLMs). The lack of human-annotated multi-modality aesthetic data further exacerba…

AesRM: Improving Video Aesthetics with Expert-Level Feedback

2026-04-30 · Yujin Han, Yujie Wei, Yefei He, Xinyu Liu 외 arxiv

Despite rapid advances in photorealistic video generation, real-world applications such as filmmaking require video aesthetics, e.g., harmonious colors and cinematic lighting, beyond visual fidelity. Prior work on visual…

Video Generation