Výsledky vyhledávání

Report

Half of an image is enough for quality assessment

Autor: You, Junyong, Lin, Yuan, Korhonen, Jari

Publikováno v: IEEE Int. Conference on Image Processing, 2023

Deep networks have demonstrated promising results in the field of Image Quality Assessment (IQA). However, there has been limited research on understanding how deep models in IQA work. This study introduces a novel positional masked transformer for I

Externí odkaz: http://arxiv.org/abs/2301.12891

Zobrazit plný text záznamu

Report

Apples and Oranges? Assessing Image Quality over Content Recognition

Autor: You, Junyong, Zhang, Zheng

Image recognition and quality assessment are two important viewing tasks, while potentially following different visual mechanisms. This paper investigates if the two tasks can be performed in a multitask learning manner. A sequential spatial-channel

Externí odkaz: http://arxiv.org/abs/2301.09190

Zobrazit plný text záznamu

Report

Visual Mechanisms Inspired Efficient Transformers for Image and Video Quality Assessment

Autor: You, Junyong, Zhang, Zheng

Publikováno v: Future of Information and Communication Conference (FICC) 2023

Visual (image, video) quality assessments can be modelled by visual features in different domains, e.g., spatial, frequency, and temporal domains. Perceptual mechanisms in the human visual system (HVS) play a crucial role in generation of quality per

Externí odkaz: http://arxiv.org/abs/2203.14557

Zobrazit plný text záznamu

Report

Consumer Image Quality Prediction using Recurrent Neural Networks for Spatial Pooling

Autor: Korhonen, Jari, Su, Yicheng, You, Junyong

Promising results for subjective image quality prediction have been achieved during the past few years by using convolutional neural networks (CNN). However, the use of CNNs for high resolution image quality assessment remains a challenge, since typi

Externí odkaz: http://arxiv.org/abs/2106.00918

Zobrazit plný text záznamu

Report

Transformer for Image Quality Assessment

Autor: You, Junyong, Korhonen, Jari

Publikováno v: IEEE Int. Conf. on Image Processing (ICIP) 2021

Transformer has become the new standard method in natural language processing (NLP), and it also attracts research interests in computer vision area. In this paper we investigate the application of Transformer in Image Quality (TRIQ) assessment. Foll

Externí odkaz: http://arxiv.org/abs/2101.01097

Zobrazit plný text záznamu

Akademický článek

Comparing apples and oranges: assessment of the relative video quality in the presence of different types of distortions

Autor: Korhonen Jari, Reiter Ulrich, You Junyong

Publikováno v: EURASIP Journal on Image and Video Processing, Vol 2011, Iss 1, p 8 (2011)

Abstract Video quality assessment is essential for the performance analysis of visual communication applications. Objective metrics can be used for estimating the relative quality differences, but they typically give reliable results only if the comp

Externí odkaz: https://doaj.org/article/59248c1d31c644a88aed5951626a523c