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

This paper reviews the NTIRE 2024 Challenge on Short-form 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/KVQ-Challenge-CVPR-NTIRE2024.

1. Introduction

Short-from UGC video platforms, e.g., Kwai, and Tiktok have attained significant success and widespread popularity, attracting billions of users globally. In contrast to long-form UGC videos, short-form UGC (S-UGC) videos present several advantages, including mobile-friendly broadcasting, user-friendly engagement, kaleidoscope content creation, and snackable content, etc. [45]. However, S-UGC videos inevitably suffer from inconsistent and even poor subjective quality due to unprofessional creation, improper collection environments, or limited processing workflow. Building the quality assessment benchmarks tailed for S-UGC videos is crucial and urgent to advance the fast development of associated video processing techniques and quality control mechanisms for user-uploaded S-UGC videos.