AIS 2024用户生成内容视频质量评估挑战赛：方法与结果
计算机视觉与模式识别
2024-04-26 v1 多媒体
摘要
本文回顾了AIS 2024视频质量评估(VQA)挑战赛，重点关注用户生成内容(UGC)。该挑战赛旨在收集能够估计UGC视频感知质量的深度学习方法。来自YouTube UGC数据集的用户生成视频包含多样化的内容（体育、游戏、歌词、动漫等）、质量和分辨率。所提出的方法必须在1秒内处理30帧全高清(FHD)帧。在挑战赛中，共有102名参与者注册，15名提交了代码和模型。本文回顾了前5名提交方案的性能，并作为针对用户生成内容的高效视频质量评估的各种深度模型的综述提供。
引用
@article{arxiv.2404.16205,
title = {AIS 2024 Challenge on Video Quality Assessment of User-Generated Content: Methods and Results},
author = {Marcos V. Conde and Saman Zadtootaghaj and Nabajeet Barman and Radu Timofte and Chenlong He and Qi Zheng and Ruoxi Zhu and Zhengzhong Tu 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 Zicheng Zhang and Haoning Wu and Yingjie Zhou and Chunyi Li and Xiaohong Liu and Weisi Lin and Guangtao Zhai and Wei Sun and Yuqin Cao and Yanwei Jiang and Jun Jia and Zhichao Zhang and Zijian Chen and Weixia Zhang and Xiongkuo Min and Steve Göring and Zihao Qi and Chen Feng},
journal= {arXiv preprint arXiv:2404.16205},
year = {2024}
}
备注
CVPR 2024 Workshop -- AI for Streaming (AIS) Video Quality Assessment Challenge