FineVD
收藏资源简介:
FineVD是一个细粒度的用户生成内容视频质量评估数据库,用于视频质量评估领域的研究和应用。
FineVD is a fine-grained user-generated content video quality assessment database intended for research and applications in the field of video quality assessment.
FineVQ数据集概述
基本信息
- 数据集名称: FineVQ (Fine-Grained User Generated Content Video Quality Assessment)
- 发布会议: CVPR 2025 Highlight
- 论文链接: FineVQ论文
- Hugging Face数据集地址: FineVD
数据集内容
- FineVD数据库: 用户生成内容(UGC)视频质量评估数据集
- 数据下载方式: bash huggingface-cli download IntMeGroup/FineVD --repo-type dataset --local-dir ./FineVD
预训练权重
| 数据集 | 权重链接 | 描述 |
|---|---|---|
| KoNViD | FineVQ_KoNViD | Konstanz自然视频数据库 |
| LIVE-VQC | FineVQ_LIVE-VQC | 大规模感知视频质量研究 |
| LSVQ | FineVQ_LSVQ | 视频质量评估数据集 |
| LIVE-YT-Gaming | FineVQ_LIVE-YT-Gaming | 游戏视频流主观和客观分析 |
| YouTubeUGC | FineVQ_YouTubeUGC | 视频压缩研究数据集 |
| FineVQ Score | FineVQ_Score | UGC视频质量评分预测 |
| FineVQ QA (Yes/No) | FineVQ_QA_yn | 二元问答任务评估 |
| FineVQ QA (Which) | FineVQ_QA_which | 选择类问题评估 |
使用方法
-
安装: bash git clone https://github.com/IntMeGroup/FineVQ.git conda create -n FineVQ python=3.9 -y conda activate FineVQ pip install -r requirements.txt pip install flash-attn==2.3.6
-
训练:
- 阶段1训练:
sh shell/stage1_train.sh - 阶段2训练:
sh shell/stage2_train.sh
- 阶段1训练:
-
评估: bash sh shell/eval.sh
引用
bibtex @InProceedings{Duan_2025_CVPR, author = {Duan, Huiyu and Hu, Qiang and Wang, Jiarui and Yang, Liu and Xu, Zitong and Liu, Lu and Min, Xiongkuo and Cai, Chunlei and Ye, Tianxiao and Zhang, Xiaoyun and Zhai, Guangtao}, title = {FineVQ: Fine-Grained User Generated Content Video Quality Assessment}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)}, month = {June}, year = {2025}, pages = {3206-3217} }
联系方式
- 邮箱: wangjiarui@sjtu.edu.cn




