NTIRE 2024 挑战：短格式用户生成内容视频质量评估方法与结果综述
图像与视频处理
2024-04-18 v1 人工智能
摘要
本文综述了 NTIRE 2024 挑战中关于短格式用户生成内容视频质量评估（S-UGC VQA）的工作，其中包括提交的各类优秀解决方案，并在来自流行短视频平台——快手/快斗平台收集的数据集 KVQ 上进行评估。KVQ 数据集分为三部分：包括 2926 个训练视频、420 个验证视频和 854 个测试视频。旨在构建新基准并推动 S-UGC VQA 的发展。本次竞赛有 200 名参赛者，最终测试阶段共有 13 支队伍提交了有效解。所提出的解决方案在 S-UGC VQA 上取得了最新成果。项目地址为 https://github.com/lixinustc/KVQChallenge-CVPR-NTIRE2024。
引用
@article{arxiv.2404.11313,
title = {NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results},
author = {Xin Li and Kun Yuan and Yajing Pei and Yiting Lu and Ming Sun and Chao Zhou and Zhibo Chen and Radu Timofte and Wei Sun and Haoning Wu and Zicheng Zhang and Jun Jia and Zhichao Zhang and Linhan Cao and Qiubo Chen and Xiongkuo Min and Weisi Lin and Guangtao Zhai and Jianhui Sun and Tianyi Wang and Lei Li and Han Kong and Wenxuan Wang and Bing Li and Cheng Luo and Haiqiang Wang and Xiangguang Chen and Wenhui Meng and Xiang Pan and Huiying Shi and Han Zhu and Xiaozhong Xu and Lei Sun and Zhenzhong Chen and Shan Liu and Fangyuan Kong and Haotian Fan and Yifang Xu and Haoran Xu and Mengduo Yang and Jie Zhou and Jiaze Li and Shijie Wen and Mai Xu and Da Li and Shunyu Yao and Jiazhi Du and Wangmeng Zuo and Zhibo Li and Shuai He and Anlong Ming and Huiyuan Fu and Huadong Ma and Yong Wu and Fie Xue and Guozhi Zhao and Lina Du and Jie Guo and Yu Zhang and Huimin Zheng and Junhao Chen and Yue Liu and Dulan Zhou and Kele Xu and Qisheng Xu and Tao Sun and Zhixiang Ding and Yuhang Hu},
journal= {arXiv preprint arXiv:2404.11313},
year = {2024}
}
备注
Accepted by CVPR2024 Workshop. The challenge report for CVPR NTIRE2024 Short-form UGC Video Quality Assessment Challenge