NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results

Xin Li, Kun Yuan, Yajing Pei, Yiting Lu, Ming Sun, Chao Zhou, Zhibo Chen, Radu Timofte, Wei Sun, Haoning Wu, Zicheng Zhang, Jun Jia, Zhichao Zhang, Linhan Cao, Qiubo Chen, Xiongkuo Min, Weisi Lin, Guangtao Zhai, Jianhui Sun, Tianyi Wang, Lei Li, Han Kong, Wenxuan Wang, Bing Li, Cheng Luo, Haiqiang Wang, Xiangguang Chen, Wenhui Meng, Xiang Pan, Huiying Shi, Han Zhu, Xiaozhong Xu, Lei Sun, Zhenzhong Chen, Shan Liu, Fangyuan Kong, Haotian Fan, Yifang Xu, Haoran Xu, Mengduo Yang, Jie Zhou, Jiaze Li, Shijie Wen, Mai Xu, Da Li, Shunyu Yao, Jiazhi Du, Wangmeng Zuo, Zhibo Li, Shuai He, Anlong Ming, Huiyuan Fu, Huadong Ma, Yong Wu, Fie Xue, Guozhi Zhao, Lina Du, Jie Guo, Yu Zhang, Huimin Zheng, Junhao Chen, Yue Liu, Dulan Zhou, Kele Xu, Qisheng Xu, Tao Sun, Zhixiang Ding, Yuhang Hu; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 6415-6431

Abstract

This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA) where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform i.e. Kuaishou/Kwai Platform. The KVQ database is divided into three parts including 2926 videos for training 420 videos for validation and 854 videos for testing. The purpose is to build new benchmarks and advance the development of S-UGC VQA. The competition had 200 participants and 13 teams submitted valid solutions for the final testing phase. The proposed solutions achieved state-of-the-art performances for S-UGC VQA. The project can be found at https://github.com/lixinustc/KVQChallenge-CVPR-NTIRE2024.

Related Material

[pdf] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Xin and Yuan, Kun and Pei, Yajing and Lu, Yiting and Sun, Ming and Zhou, Chao and Chen, Zhibo and Timofte, Radu and Sun, Wei and Wu, Haoning and Zhang, Zicheng and Jia, Jun and Zhang, Zhichao and Cao, Linhan and Chen, Qiubo and Min, Xiongkuo and Lin, Weisi and Zhai, Guangtao and Sun, Jianhui and Wang, Tianyi and Li, Lei and Kong, Han and Wang, Wenxuan and Li, Bing and Luo, Cheng and Wang, Haiqiang and Chen, Xiangguang and Meng, Wenhui and Pan, Xiang and Shi, Huiying and Zhu, Han and Xu, Xiaozhong and Sun, Lei and Chen, Zhenzhong and Liu, Shan and Kong, Fangyuan and Fan, Haotian and Xu, Yifang and Xu, Haoran and Yang, Mengduo and Zhou, Jie and Li, Jiaze and Wen, Shijie and Xu, Mai and Li, Da and Yao, Shunyu and Du, Jiazhi and Zuo, Wangmeng and Li, Zhibo and He, Shuai and Ming, Anlong and Fu, Huiyuan and Ma, Huadong and Wu, Yong and Xue, Fie and Zhao, Guozhi and Du, Lina and Guo, Jie and Zhang, Yu and Zheng, Huimin and Chen, Junhao and Liu, Yue and Zhou, Dulan and Xu, Kele and Xu, Qisheng and Sun, Tao and Ding, Zhixiang and Hu, Yuhang}, title = {NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {6415-6431} }