FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2473697052> ?p ?o ?g. }

• W2473697052 endingPage "4457" @default.
• W2473697052 startingPage "4444" @default.
• W2473697052 abstract "Blind image quality assessment (BIQA) research aims to develop a perceptual model to evaluate the quality of distorted images automatically and accurately without access to the non-distorted reference images. The state-of-the-art general purpose BIQA methods can be classified into two categories according to the types of features used. The first includes handcrafted features which rely on the statistical regularities of natural images. These, however, are not suitable for images containing text and artificial graphics. The second includes learning-based features which invariably require large codebook or supervised codebook updating procedures to obtain satisfactory performance. These are time-consuming and not applicable in practice. In this paper, we propose a novel general purpose BIQA method based on high order statistics aggregation (HOSA), requiring only a small codebook. HOSA consists of three steps. First, local normalized image patches are extracted as local features through a regular grid, and a codebook containing 100 codewords is constructed by K-means clustering. In addition to the mean of each cluster, the diagonal covariance and coskewness (i.e., dimension-wise variance and skewness) of clusters are also calculated. Second, each local feature is softly assigned to several nearest clusters and the differences of high order statistics (mean, variance and skewness) between local features and corresponding clusters are softly aggregated to build the global quality aware image representation. Finally, support vector regression is adopted to learn the mapping between perceptual features and subjective opinion scores. The proposed method has been extensively evaluated on ten image databases with both simulated and realistic image distortions, and shows highly competitive performance to the state-of-the-art BIQA methods." @default.
• W2473697052 created "2016-07-22" @default.
• W2473697052 creator A5003875781 @default.
• W2473697052 creator A5011650323 @default.
• W2473697052 creator A5014961410 @default.
• W2473697052 creator A5029594222 @default.
• W2473697052 creator A5044052726 @default.
• W2473697052 creator A5063499064 @default.
• W2473697052 date "2016-09-01" @default.
• W2473697052 modified "2023-10-14" @default.
• W2473697052 title "Blind Image Quality Assessment Based on High Order Statistics Aggregation" @default.
• W2473697052 cites W1493093959 @default.
• W2473697052 cites W1561538450 @default.
• W2473697052 cites W1964859077 @default.
• W2473697052 cites W1968590503 @default.
• W2473697052 cites W1976921161 @default.
• W2473697052 cites W1977246677 @default.
• W2473697052 cites W1977725648 @default.
• W2473697052 cites W1982471090 @default.
• W2473697052 cites W1984066865 @default.
• W2473697052 cites W1992869494 @default.
• W2473697052 cites W1997974943 @default.
• W2473697052 cites W1999601189 @default.
• W2473697052 cites W1999668761 @default.
• W2473697052 cites W2006902599 @default.
• W2473697052 cites W2012592962 @default.
• W2473697052 cites W2018918151 @default.
• W2473697052 cites W2022377161 @default.
• W2473697052 cites W2037243393 @default.
• W2473697052 cites W2037932104 @default.
• W2473697052 cites W2048835603 @default.
• W2473697052 cites W2051596736 @default.
• W2473697052 cites W2052287864 @default.
• W2473697052 cites W2068403421 @default.
• W2473697052 cites W2080369988 @default.
• W2473697052 cites W2092377492 @default.
• W2473697052 cites W2107476778 @default.
• W2473697052 cites W2114338738 @default.
• W2473697052 cites W2123649031 @default.
• W2473697052 cites W2129644086 @default.
• W2473697052 cites W2133665775 @default.
• W2473697052 cites W2137186219 @default.
• W2473697052 cites W2138088051 @default.
• W2473697052 cites W2138885645 @default.
• W2473697052 cites W2141983208 @default.
• W2473697052 cites W2143901157 @default.
• W2473697052 cites W2145057702 @default.
• W2473697052 cites W2147238549 @default.
• W2473697052 cites W2150593711 @default.
• W2473697052 cites W2161907179 @default.
• W2473697052 cites W2162692770 @default.
• W2473697052 cites W2163370434 @default.
• W2473697052 cites W2303076655 @default.
• W2473697052 cites W2343155526 @default.
• W2473697052 cites W2546855109 @default.
• W2473697052 cites W3100404621 @default.
• W2473697052 cites W4238491817 @default.
• W2473697052 doi "https://doi.org/10.1109/tip.2016.2585880" @default.
• W2473697052 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/27362977" @default.
• W2473697052 hasPublicationYear "2016" @default.
• W2473697052 type Work @default.
• W2473697052 sameAs 2473697052 @default.
• W2473697052 citedByCount "304" @default.
• W2473697052 countsByYear W24736970522016 @default.
• W2473697052 countsByYear W24736970522017 @default.
• W2473697052 countsByYear W24736970522018 @default.
• W2473697052 countsByYear W24736970522019 @default.
• W2473697052 countsByYear W24736970522020 @default.
• W2473697052 countsByYear W24736970522021 @default.
• W2473697052 countsByYear W24736970522022 @default.
• W2473697052 countsByYear W24736970522023 @default.
• W2473697052 crossrefType "journal-article" @default.
• W2473697052 hasAuthorship W2473697052A5003875781 @default.
• W2473697052 hasAuthorship W2473697052A5011650323 @default.
• W2473697052 hasAuthorship W2473697052A5014961410 @default.
• W2473697052 hasAuthorship W2473697052A5029594222 @default.
• W2473697052 hasAuthorship W2473697052A5044052726 @default.
• W2473697052 hasAuthorship W2473697052A5063499064 @default.
• W2473697052 hasConcept C104267543 @default.
• W2473697052 hasConcept C105795698 @default.
• W2473697052 hasConcept C115961682 @default.
• W2473697052 hasConcept C122342681 @default.
• W2473697052 hasConcept C124101348 @default.
• W2473697052 hasConcept C127759330 @default.
• W2473697052 hasConcept C153180895 @default.
• W2473697052 hasConcept C154945302 @default.
• W2473697052 hasConcept C2780576426 @default.
• W2473697052 hasConcept C33923547 @default.
• W2473697052 hasConcept C41008148 @default.
• W2473697052 hasConcept C55020928 @default.
• W2473697052 hasConcept C554190296 @default.
• W2473697052 hasConcept C73555534 @default.
• W2473697052 hasConcept C76155785 @default.
• W2473697052 hasConceptScore W2473697052C104267543 @default.
• W2473697052 hasConceptScore W2473697052C105795698 @default.
• W2473697052 hasConceptScore W2473697052C115961682 @default.
• W2473697052 hasConceptScore W2473697052C122342681 @default.
• W2473697052 hasConceptScore W2473697052C124101348 @default.

• next