This paper reviews the AIS 2024 Video Quality Assessment (VQA) Challenge, focused on User-Generated Content (UGC). The aim of this challenge is to gather deep learning-based methods capable of estimating the perceptual quality of UGC videos. The user-generated videos from the YouTube UGC Dataset include diverse content (sports, games, lyrics, anime, etc.), quality and resolutions. The proposed methods must process 30 FHD frames under 1 second. In the challenge, a total of 102 participants registered, and 15 submitted code and models. The performance of the top-5 submissions is reviewed and provided here as a survey of diverse deep models for efficient video quality assessment of user-generated content.
@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}
}
Comments
CVPR 2024 Workshop -- AI for Streaming (AIS) Video Quality Assessment Challenge