信号处理2026，Vol.42Issue(2)：148-157,10.DOI:10.12466/xhcl.2026.02.003
基于多维时空特征的双支路无参考屏幕内容视频质量评价方法
Dual-Branch No-Reference Quality Assessment Method for Screen Content Videos Based on Multi-Dimensional Spatiotemporal Features
摘要
Abstract
The widespread adoption of smart devices has led to the extensive application of screen content videos in fields such as remote education and live streaming.Thus the quality assessment of these videos is crucial for ensuring a satisfactory visual experience.Unlike natural scene videos,screen content contains many synthetic elements such as text and graphics,resulting in more complex distortion types.Therefore,there is a need to develop a no-reference quality as-sessment model that aligns with human visual characteristics.However,existing methods struggle to effectively handle a high dynamic range and composite distortions,and the high redundancy and strong temporal dependencies in video data constrain feature extraction efficiency and the accuracy of quality perception.To address these challenges,this study proposed a dual-branch architecture for no-reference screen content video quality assessment.For complex distor-tion patterns,we constructed a spatial perception branch to extract spatial structural information and noise distribution from key frames.To reduce video redundancy and suppress shallow dependencies,we introduced a tube-based masked spatiotemporal encoding mechanism that captures deeper motion features.To address the difficulties encountered in tem-poral modeling,we designed a temporal perception enhancement module that integrates multi-dimensional features to generate final quality scores.Experimental findings revealed that our method achieved a 2.3%improvement in the weighted Spearman Rank-Order Correlation Coefficient(SROCC)compared with the second-best model on two main-stream datasets,significantly enhancing both the perceptual consistency and generalization capability in screen content video quality assessment.关键词
质量评价/屏幕内容视频/多维特征Key words
quality assessment/screen content videos/multi-dimensional feature分类
信息技术与安全科学引用本文复制引用
赖伊琳,陈瑜萍,刘智鸿,朱显丞,曾焕强..基于多维时空特征的双支路无参考屏幕内容视频质量评价方法[J].信号处理,2026,42(2):148-157,10.基金项目
福建省"揭榜挂帅"重大专项项目(2024HZ022007) （2024HZ022007）
福建省自然科学基金重点项目(2023J02022) （2023J02022）
泉州市引进高层次人才团队(2023CT001) The Key Science and Technology Project of Fujian Province(2024HZ022007) （2023CT001）
The Key Program of Natural Science Foundation of Fujian Province(2023J02022) （2023J02022）
The High-level Talent Team Project of Quanzhou City(2023CT001) （2023CT001）
