ZREC : Robust Recovery of Mean and Percentile Opinion Scores - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

ZREC : Robust Recovery of Mean and Percentile Opinion Scores

Résumé

Observer screening and subject opinion score recovery is essential for collecting a reliable QoE database. This paper proposes a new method, ZREC * , which uses Z-scores to estimate subject bias, inconsistency, and content ambiguity. Additionally, we propose Mean Opinion Score (MOS) recovery and Percentile Opinion Score (POS) recovery scheme based on the three estimated parameters. ZREC does not fully reject subjects, rather adjust their coefficients in the MOS/POS recovery, allowing for more efficient use of data collection. The estimated parameters of ZREC are highly correlated with more complex solver-based methods and standards. In addition, ZREC recovers MOS with smaller confidence intervals than the state of the art. Experimental results also demonstrate that using recovered p th POS as ground truth during training improves the performance of Satisfied User Ratio (SUR) prediction.
Fichier principal
Vignette du fichier
ICIP2023_zrec_preprint.pdf (191.44 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04017583 , version 1 (07-03-2023)

Identifiants

Citer

Jingwen Zhu, Ali Ak, Patrick Le Callet, Sriram Sethuraman, Kumar Rahul. ZREC : Robust Recovery of Mean and Percentile Opinion Scores. IEEE International Conference on Image Processing 2023 (ICIP 2023), Oct 2023, Kuala Lumpur, Malaysia. ⟨10.1109/ICIP49359.2023.10222033⟩. ⟨hal-04017583⟩
62 Consultations
95 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More