Analytic Score Optimization for Multi Dimension Video Quality Assessment

2026-02-18

AI Summary

This work addresses the limitations of existing video quality assessment methods, which predominantly rely on a single mean opinion score and thus fail to capture the complex, multi-dimensional perceptual characteristics of user-generated content. To this end, the authors introduce UltraVQA, a large-scale multidimensional video quality dataset featuring fine-grained annotations across five perceptual dimensions along with explanatory rationales. They further propose Analytic Scoring Optimization (ASO), a novel approach that formulates multidimensional quality modeling as a regularized ordinal decision process admitting a closed-form solution. Experimental results demonstrate that ASO significantly outperforms both state-of-the-art open-source models and proprietary APIs in multidimensional quality prediction, achieving lower mean absolute error and higher consistency with human preferences.

Technology Category

• Computer Vision: Video Understanding & Activity Analysis
• Machine Learning: Multimodal Learning
• Knowledge Representation and Reasoning: Qualitative Reasoning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content

Abstract

Video Quality Assessment (VQA) is evolving beyond single-number mean opinion score toward richer, multi-faceted evaluations of video content. In this paper, we present a large-scale multi-dimensional VQA dataset UltraVQA that encompasses diverse User-Generated Content~(UGC) annotated across five key quality dimensions: Motion Quality, Motion Amplitude, Aesthetic Quality, Content Quality, and Clarity Quality. Each video in our dataset is scored by over 3 human raters on these dimensions, with fine-grained sub-attribute labels, and accompanied by an explanatory rationale generated by GPT based on the collective human judgments. To better leverage these rich annotations and improve discrete quality score assessment, we introduce Analytic Score Optimization (ASO), a theoretically grounded post-training objective derived for multi-dimensional VQA. By reframing quality assessment as a regularized decision-making process, we obtain a closed-form solution that naturally captures the ordinal nature of human ratings, ensuring alignment with human ranking preferences. In experiments, our method outperforms most baselines including closed-source APIs and open-source models, while also reducing mean absolute error (MAE) in quality prediction. Our work highlights the importance of multi-dimensional, interpretable annotations and reinforcement-based alignment in advancing video quality assessment.

Problem

• Video Quality Assessment
• Multi-dimensional Evaluation
• User-Generated Content
• Quality Dimensions
• Human Perception

Innovation

• Analytic Score Optimization
• Multi-dimensional VQA
• Ordinal Alignment
• Interpretable Annotations
• UltraVQA