Hacking VMAF and VMAF NEG: Vulnerability to Different Preprocessing Methods

被引:6
|
作者
Siniukov, Maksim [1 ]
Antsiferova, Anastasia [1 ]
Kulikov, Dmitriy [1 ,2 ]
Vatolin, Dmitriy [1 ]
机构
[1] Lomonosov Moscow State Univ, Moscow, Russia
[2] Dubna State Univ, Dubna, Russia
基金
俄罗斯基础研究基金会;
关键词
video quality; VMAF; quality improvement; codecs tuning; objective full-reference metric; video quality measurement; video codecs comparisons;
D O I
10.1145/3508259.3508272
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Video quality measurement plays a critical role in the development of video processing applications. In this paper, we show how popular quality metrics VMAF and its tuning-resistant version VMAF NEG can be artificially increased by video preprocessing. We propose a pipeline for tuning parameters of processing algorithms which allows to increase VMAF by up to 218.8%. A subjective comparison of preprocessed videos showed that with the majority of methods visual quality drops down or stays unchanged. We show that VMAF NEG scores can also be increased by some preprocessing methods by up to 21.9%.
引用
收藏
页码:89 / 96
页数:8
相关论文
共 37 条
  • [21] Systematic Comparison of the Influence of Different Data Preprocessing Methods on the Performance of Gait Classifications Using Machine Learning
    Burdack, Johannes
    Horst, Fabian
    Giesselbach, Sven
    Hassan, Ibrahim
    Daffner, Sabrina
    Schoellhorn, Wolfgang I.
    FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY, 2020, 8
  • [22] Nonlinear, Non-stationary and Seasonal Time Series Forecasting Using Different Methods Coupled with Data Preprocessing
    Stepehenko, Arthur
    Chizhov, Jurij
    Aleksejeva, Ludmila
    Tolujew, Juni
    ICTE 2016, 2017, 104 : 578 - 585
  • [23] Seismic Vulnerability Assessment of Mexican Vernacular Adobe Buildings: Application and Comparison of Different Methods
    Sanchez-Calvillo, Adria
    Heras, Javier Ortega
    Guzman, Elia M. Alonso
    INTERNATIONAL JOURNAL OF ARCHITECTURAL HERITAGE, 2025,
  • [24] EFFECT OF DIFFERENT PREPROCESSING METHODS FOR PRINCIPAL COMPONENT ANALYSIS APPLIED TO THE COMPOSITION OF MIXTURES - DETECTION OF IMPURITIES IN HPLC-DAD
    SANCHEZ, FC
    LEWI, PJ
    MASSART, DL
    CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1994, 25 (02) : 157 - 177
  • [25] Assessing structural uncertainty caused by different weighting methods on the Standardized Drought Vulnerability Index (SDVI)
    Demetrios E. Tsesmelis
    Panagiotis D. Oikonomou
    Constantina G. Vasilakou
    Nikolaos A. Skondras
    Vassilia Fassouli
    Stavros G. Alexandris
    Neil S. Grigg
    Christos A. Karavitis
    Stochastic Environmental Research and Risk Assessment, 2019, 33 : 515 - 533
  • [26] Assessing structural uncertainty caused by different weighting methods on the Standardized Drought Vulnerability Index (SDVI)
    Tsesmelis, Demetrios E.
    Oikonomou, Panagiotis D.
    Vasilakou, Constantina G.
    Skondras, Nikolaos A.
    Fassouli, Vassilia
    Alexandris, Stavros G.
    Grigg, Neil S.
    Karavitis, Christos A.
    STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT, 2019, 33 (02) : 515 - 533
  • [27] Vulnerability of Voice Verification System with STC Anti-spoofing Detector to Different Methods of Spoofing Attacks
    Shchemelinin, Vadim
    Kozlov, Alexandr
    Lavrentyeva, Galina
    Novoselov, Sergey
    Simonchik, Konstantin
    SPEECH AND COMPUTER (SPECOM 2015), 2015, 9319 : 480 - 486
  • [28] ASSESSING THE PREDICTIVE PERFORMANCE OF ARTIFICIAL NEURAL NETWORK-BASED CLASSIFIERS BASED ON DIFFERENT DATA PREPROCESSING METHODS, DISTRIBUTIONS AND TRAINING MECHANISMS
    Costea, Adrian
    Nastac, Iulian
    INTELLIGENT SYSTEMS IN ACCOUNTING FINANCE & MANAGEMENT, 2005, 13 (04): : 217 - 250
  • [29] Seismic Risk Assessment of Multiple Cities: Biases in the Vulnerability Derivation Methods for Urban Areas With Different Hazard Levels
    Hoyos, Maria Camila
    Hernandez, Andres Felipe
    FRONTIERS IN EARTH SCIENCE, 2022, 10
  • [30] Sweeping-frequency ultrasonic preprocessing improves removal rate and stability of pigment removed from okra powders by different drying and sieving methods
    Zhang, Lei
    Zhang, Ao
    Zhou, Shanshan
    Wang, Qianqian
    Hu, Zhenyuan
    Li, Chenglin
    Hu, Yang
    Ma, Haile
    Zhou, Cunshan
    DRYING TECHNOLOGY, 2024, 42 (01) : 19 - 33