KVQ: Kwai Video Quality Assessment for Short-form Videos

TL;DR

This paper introduces KVQ, a large-scale database for short-form video quality assessment, and proposes KSVQE, a new quality evaluation method leveraging vision-language models to address content ambiguity and complex distortions.

Contribution

The paper creates the first comprehensive short-video quality database and develops a novel evaluator using CLIP-based content and distortion understanding.

Findings

KSVQE outperforms existing methods on KVQ and other VQA datasets.

The database includes 600 user videos and 3600 processed videos with quality scores.

KSVQE effectively identifies quality-related semantics and distortions.

Abstract

Short-form UGC video platforms, like Kwai and TikTok, have been an emerging and irreplaceable mainstream media form, thriving on user-friendly engagement, and kaleidoscope creation, etc. However, the advancing content-generation modes, e.g., special effects, and sophisticated processing workflows, e.g., de-artifacts, have introduced significant challenges to recent UGC video quality assessment: (i) the ambiguous contents hinder the identification of quality-determined regions. (ii) the diverse and complicated hybrid distortions are hard to distinguish. To tackle the above challenges and assist in the development of short-form videos, we establish the first large-scale Kaleidoscope short Video database for Quality assessment, termed KVQ, which comprises 600 user-uploaded short videos and 3600 processed videos through the diverse practical processing workflows, including pre-processing, transcoding, and enhancement. Among them, the absolute quality score of each video and partial ranking score among indistinguishable samples are provided by a team of professional researchers specializing in image processing. Based on this database, we propose the first short-form video quality evaluator, i.e., KSVQE, which enables the quality evaluator to identify the quality-determined semantics with the content understanding of large vision language models (i.e., CLIP) and distinguish the distortions with the distortion understanding module. Experimental results have shown the effectiveness of KSVQE on our KVQ database and popular VQA databases.