AIS 2024 Challenge on Video Quality Assessment of User-Generated Content: Methods and Results

TL;DR

This paper reviews the AIS 2024 VQA Challenge focusing on deep learning methods for assessing the perceptual quality of diverse user-generated videos, highlighting top-performing models and their effectiveness.

Contribution

It provides a comprehensive survey of deep learning approaches for UGC video quality assessment, including challenge results and analysis of top models.

Findings

Top-5 models achieved significant accuracy in quality estimation.

Diverse deep learning architectures were effective for UGC VQA.

The challenge attracted over 100 participants, demonstrating high interest.

Abstract

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.