# Multiview Contrastive Learning for Completely Blind Video Quality Assessment of User Generated Content

arXiv: https://arxiv.org/abs/2207.06148 · HTML: https://mlsanity.com/paper/2207.06148/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2022.

## Built on by (most cited first, 5 of 5)

- [Perceptual Video Quality Assessment: A Survey](https://mlsanity.com/paper/2402.03413/) (2024)
- [FineVQ: Fine-Grained User Generated Content Video Quality Assessment](https://mlsanity.com/paper/2412.19238/) (2024)
- [Knowledge Guided Semi-Supervised Learning for Quality Assessment of User Generated Videos](https://mlsanity.com/paper/2312.15425/) (2023)
- [Image and Video Quality Assessment using Prompt-Guided Latent Diffusion Models for Cross-Dataset Generalization](https://mlsanity.com/paper/2406.04654/) (2024)
- [Contrastive learning-based video quality assessment-jointed video vision transformer for video recognition](https://mlsanity.com/paper/2603.10965/) (2026)

## Abstract (arXiv)

Completely blind video quality assessment (VQA) refers to a class of quality assessment methods that do not use any reference videos, human opinion scores or training videos from the target database to learn a quality model. The design of this class of methods is particularly important since it can allow for superior generalization in performance across various datasets. We consider the design of completely blind VQA for user generated content. While several deep feature extraction methods have been considered in supervised and weakly supervised settings, such approaches have not been studied in the context of completely blind VQA. We bridge this gap by presenting a self-supervised multiview contrastive learning framework to learn spatio-temporal quality representations. In particular, we capture the common information between frame differences and frames by treating them as a pair of views and similarly obtain the shared representations between frame differences and optical flow. The resulting features are then compared with a corpus of pristine natural video patches to predict the quality of the distorted video. Detailed experiments on multiple camera captured VQA datasets reveal the superior performance of our method over other features when evaluated without training on human scores.