Unsupervised category learning in perceived video quality

• Autorzy: Vejar Andres , Konaszyński Tomasz , Juszka Dawid , Leszczuk Mikołaj

Identyfikatory

DOI

10.15199/59.2023.4.74

• Konferencja: Konferencja Radiokomunikacji i Teleinformatyki (20-22.09.2023 ; Kraków, Polska)
• Języki publikacji: EN

Abstrakty

EN

In video quality evaluation, the perceived quality is ranked by the participants using a categorical scale of five levels. To study the category learning dependency, the participants were divided into learners and no-learners, with respect to their classification accuracy. An analysis of the performance of the human unsupervised learning from machine learning models is presented in order to study the effects of category learning in the video assessment.

Słowa kluczowe

EN

category learning; video quality; machine learning

PL

kategoria; jakość wideo; uczenie maszynowe

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne
• Rocznik: 2023
• Tom: nr 4
• Strony: 329--332
• Opis fizyczny: Bibliogr. 16 poz., rys.

Twórcy

autor

Vejar Andres

• Institute of Telecommunication, AGH University of Krakow

autor

Konaszyński Tomasz

• Institute of Telecommunication, AGH University of Krakow

autor

Juszka Dawid

• Institute of Telecommunication, AGH University of Krakow

autor

Leszczuk Mikołaj

• Institute of Telecommunication, AGH University of Krakow

Bibliografia

• [1] James L. Gould and Peter Marler. Learning by instinct. Scientific American, 256(1):74–85, 1987.
• [2] Todd M. Gureckis and Douglas B. Markant. Self directed learning: A cognitive and computational perspective. Perspectives on Psychological Science, 7(5):464–481, 2012. PMID: 26168504.
• [3] ITU-T. Recommendation ITU-T P.910: Subjective video quality assessment methods for multimedia applications. Recommendation, International Telecommunication Union, 2022.
• [4] Kenneth R Livingston, Janet K Andrews, and Stevan Harnad. Categorical perception effects induced by category learning. Journal of Experimental Psychology: Learning, Memory, and Cognition, 24(3):732, 1998.
• [5] Robert L Goldstone, Yvonne Lippa, and Richard M Shiffrin. Altering object representations through category learning. Cognition, 78(1):27–43, 2001.
• [6] Fernanda Pérez-Gay Juárez, Tomy Sicotte, Christian Thériault, and Stevan Harnad. Category learning can alter perception and its neural correlates. PLOS ONE, 14(12):1–29, 12 2019.
• [7] RI Damper and SR Harnad. Neural network models of categorical perception. Perception & psychophysics, 62(4):843–867, 2000.
• [8] Christian Thériault, Fernanda Pérez-Gay, Dan Rivas, and Stevan Harnad. Learning-induced categorical perception in a neural network model, 2018.
• [9] Laurent Bonnasse-Gahot and Jean-Pierre Nadal. Categorical Perception: A Groundwork for Deep Learning. Neural Computation, 34(2):437–475, 01 2022.
• [10] P. Topiwala, W. Dai, J. Pian, K. Biondi, and A. Krovvidi. VMAF and variants: towards a unified VQA. In Andrew G. Tescher and Touradj Ebrahimi, editors, Applications of Digital Image Processing XLIV, volume 11842, page 118420F. International Society for Optics and Photonics, SPIE, 2021.
• [11] Wim J. van der Linden. A lognormal model for response times on test items. Journal of Educational and Behavioral Statistics, 31(2):181–204, 2006.
• [12] Jean-Paul Fox, Rinke Klein Entink, and Wilm van der Linden. Modeling of responses and response times with the package cirt. Journal of Statistical Software, 20(7):1–14, 2007.
• [13] Sandip Sinharay and Peter W. van Rijn. Assessing fit of the lognormal model for response times. Journal of Educational and Behavioral Statistics, 45(5):534– 568, 2020.
• [14] Paul De Boeck and Minjeong Jeon. An overview of models for response times and processes in cognitive tests. Frontiers in Psychology, 10, 2019.
• [15] Stefano Gualandi and Giuseppe Toscani. Human behavior and lognormal distribution. a kinetic description. Mathematical Models and Methods in Applied Sciences, 29(04):717–753, 2019.
• [16] Stefano Gualandi and Giuseppe Toscani. Call center service times are lognormal: A Fokker–Planck description. Mathematical Models and Methods in Applied Sciences, 28(08):1513–1527, 2018.

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).