FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3000373634> ?p ?o ?g. }

• W3000373634 endingPage "2949" @default.
• W3000373634 startingPage "2938" @default.
• W3000373634 abstract "The perceptual quality of stereoscopic images plays an essential role in the human perception of visual information. However, most available stereoscopic image quality assessment (SIQA) methods evaluate 3D visual experience using hand-crafted features or shallow architectures, which cannot model the visual properties of stereo images well. In this paper, we use convolutional neural networks (CNNs) to learn deeper local quality-aware structures for stereo images. With different inputs, two CNN models are designed for no-reference SIQA tasks. The one-column CNN model directly accepts a cyclopean view as the input, and the three-column CNN model jointly considers the cyclopean, left and right views as CNN inputs. The two SIQA frameworks share the same implementation approach: First, to overcome the obstacle of limited SIQA datasets, we accept image patches that have been cropped from corresponding stereopairs as inputs for local quality-sensitive feature extraction. Next, a local feature selection algorithm is used to remove related features on non-salient patches, which could cause large prediction errors. Finally, the reserved local visual structures of salient regions are aggregated into a final quality score in an end-to-end manner. Experimental results on three public SIQA databases demonstrate that our method outperforms most state-of-the-art no-reference (NR) SIQA methods. The results of a cross-database experiment also show the robustness and generality of the proposed method." @default.
• W3000373634 created "2020-01-23" @default.
• W3000373634 creator A5016678056 @default.
• W3000373634 creator A5034654778 @default.
• W3000373634 creator A5042394011 @default.
• W3000373634 creator A5051796014 @default.
• W3000373634 creator A5060770069 @default.
• W3000373634 date "2020-11-01" @default.
• W3000373634 modified "2023-10-02" @default.
• W3000373634 title "Learning Local Quality-Aware Structures of Salient Regions for Stereoscopic Images via Deep Neural Networks" @default.
• W3000373634 cites W1500458919 @default.
• W3000373634 cites W1972491016 @default.
• W3000373634 cites W1976420333 @default.
• W3000373634 cites W1981076008 @default.
• W3000373634 cites W1982471090 @default.
• W3000373634 cites W1993705360 @default.
• W3000373634 cites W1997349748 @default.
• W3000373634 cites W1998974609 @default.
• W3000373634 cites W2002366924 @default.
• W3000373634 cites W2043594938 @default.
• W3000373634 cites W2051596736 @default.
• W3000373634 cites W2065039464 @default.
• W3000373634 cites W2070322626 @default.
• W3000373634 cites W2073812468 @default.
• W3000373634 cites W2080225384 @default.
• W3000373634 cites W2099308462 @default.
• W3000373634 cites W2108598243 @default.
• W3000373634 cites W2129331753 @default.
• W3000373634 cites W2133665775 @default.
• W3000373634 cites W2258211000 @default.
• W3000373634 cites W2280408335 @default.
• W3000373634 cites W2293889938 @default.
• W3000373634 cites W2320663691 @default.
• W3000373634 cites W2323509952 @default.
• W3000373634 cites W2343278664 @default.
• W3000373634 cites W2395611524 @default.
• W3000373634 cites W2466226663 @default.
• W3000373634 cites W2481395713 @default.
• W3000373634 cites W2509123681 @default.
• W3000373634 cites W2566149141 @default.
• W3000373634 cites W2593290446 @default.
• W3000373634 cites W2605701576 @default.
• W3000373634 cites W2606244968 @default.
• W3000373634 cites W2735451741 @default.
• W3000373634 cites W2740756928 @default.
• W3000373634 cites W2767658402 @default.
• W3000373634 cites W2782385194 @default.
• W3000373634 cites W2810874584 @default.
• W3000373634 cites W2891749081 @default.
• W3000373634 doi "https://doi.org/10.1109/tmm.2020.2965461" @default.
• W3000373634 hasPublicationYear "2020" @default.
• W3000373634 type Work @default.
• W3000373634 sameAs 3000373634 @default.
• W3000373634 citedByCount "8" @default.
• W3000373634 countsByYear W30003736342020 @default.
• W3000373634 countsByYear W30003736342021 @default.
• W3000373634 countsByYear W30003736342022 @default.
• W3000373634 crossrefType "journal-article" @default.
• W3000373634 hasAuthorship W3000373634A5016678056 @default.
• W3000373634 hasAuthorship W3000373634A5034654778 @default.
• W3000373634 hasAuthorship W3000373634A5042394011 @default.
• W3000373634 hasAuthorship W3000373634A5051796014 @default.
• W3000373634 hasAuthorship W3000373634A5060770069 @default.
• W3000373634 hasConcept C104317684 @default.
• W3000373634 hasConcept C126057942 @default.
• W3000373634 hasConcept C138885662 @default.
• W3000373634 hasConcept C153180895 @default.
• W3000373634 hasConcept C154945302 @default.
• W3000373634 hasConcept C15744967 @default.
• W3000373634 hasConcept C185592680 @default.
• W3000373634 hasConcept C2776401178 @default.
• W3000373634 hasConcept C2780719617 @default.
• W3000373634 hasConcept C2780767217 @default.
• W3000373634 hasConcept C31972630 @default.
• W3000373634 hasConcept C36464697 @default.
• W3000373634 hasConcept C41008148 @default.
• W3000373634 hasConcept C41895202 @default.
• W3000373634 hasConcept C52622490 @default.
• W3000373634 hasConcept C542102704 @default.
• W3000373634 hasConcept C55493867 @default.
• W3000373634 hasConcept C63479239 @default.
• W3000373634 hasConcept C81363708 @default.
• W3000373634 hasConceptScore W3000373634C104317684 @default.
• W3000373634 hasConceptScore W3000373634C126057942 @default.
• W3000373634 hasConceptScore W3000373634C138885662 @default.
• W3000373634 hasConceptScore W3000373634C153180895 @default.
• W3000373634 hasConceptScore W3000373634C154945302 @default.
• W3000373634 hasConceptScore W3000373634C15744967 @default.
• W3000373634 hasConceptScore W3000373634C185592680 @default.
• W3000373634 hasConceptScore W3000373634C2776401178 @default.
• W3000373634 hasConceptScore W3000373634C2780719617 @default.
• W3000373634 hasConceptScore W3000373634C2780767217 @default.
• W3000373634 hasConceptScore W3000373634C31972630 @default.
• W3000373634 hasConceptScore W3000373634C36464697 @default.
• W3000373634 hasConceptScore W3000373634C41008148 @default.
• W3000373634 hasConceptScore W3000373634C41895202 @default.
• W3000373634 hasConceptScore W3000373634C52622490 @default.
• W3000373634 hasConceptScore W3000373634C542102704 @default.

• next