Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199775471> ?p ?o ?g. }
- W3199775471 endingPage "3421" @default.
- W3199775471 startingPage "3407" @default.
- W3199775471 abstract "Stereoscopic omnidirectional content, as a novel visual media, has drawn wide attention in recent years due to its ability in providing strong immersive experience. Since Stereoscopic Omnidirectional Images (SOIs) involve the properties from panoramic and stereoscopic visual perception, it is very challenging to establish an efficient and effective visual quality evaluation model for SOIs. To better measure the user’s experience in virtual reality, we put forward a novel deep learning framework to assess the quality of SOIs in this paper. Firstly, the deformable convolutions instead of standard convolutions are adopted to ensure the invariant receptive fields of convolutional kernels on Equi-Rectangular Projection (ERP). Secondly, according to the stereoscopic property, we use binocular-difference information and a coarse-to-fine mechanism to construct the binocular feature extraction network. Thirdly, a three-channel network involving left-view, right-view and binocular-difference channels is presented to simulate the process of monocular and binocular interactions, in which independent quality labels are provided for each channel to reflect the individual effect of monocular and binocular visions on the whole visual quality. Finally, experimental results on two available benchmark databases demonstrate the superiority of the proposed metric over the state-of-the-art blind quality assessment models in predicting the quality of SOIs. Moreover, our model is efficient in computational cost as the feature extraction is directly applied on ERP images." @default.
- W3199775471 created "2021-09-27" @default.
- W3199775471 creator A5000581688 @default.
- W3199775471 creator A5018282808 @default.
- W3199775471 creator A5030554236 @default.
- W3199775471 creator A5049898953 @default.
- W3199775471 creator A5061745929 @default.
- W3199775471 date "2022-06-01" @default.
- W3199775471 modified "2023-10-15" @default.
- W3199775471 title "Monocular and Binocular Interactions Oriented Deformable Convolutional Networks for Blind Quality Assessment of Stereoscopic Omnidirectional Images" @default.
- W3199775471 cites W1964859077 @default.
- W3199775471 cites W1981076008 @default.
- W3199775471 cites W1982471090 @default.
- W3199775471 cites W1993721485 @default.
- W3199775471 cites W2040617105 @default.
- W3199775471 cites W2051596736 @default.
- W3199775471 cites W2102166818 @default.
- W3199775471 cites W2133665775 @default.
- W3199775471 cites W2141983208 @default.
- W3199775471 cites W2172058006 @default.
- W3199775471 cites W2194775991 @default.
- W3199775471 cites W2258211000 @default.
- W3199775471 cites W2310059960 @default.
- W3199775471 cites W2327452692 @default.
- W3199775471 cites W2417022726 @default.
- W3199775471 cites W2473697052 @default.
- W3199775471 cites W2513500606 @default.
- W3199775471 cites W2561270043 @default.
- W3199775471 cites W2601564443 @default.
- W3199775471 cites W2612870373 @default.
- W3199775471 cites W2733888878 @default.
- W3199775471 cites W2750972358 @default.
- W3199775471 cites W2768340063 @default.
- W3199775471 cites W2777280533 @default.
- W3199775471 cites W2888995598 @default.
- W3199775471 cites W2890110575 @default.
- W3199775471 cites W2895696451 @default.
- W3199775471 cites W2896663560 @default.
- W3199775471 cites W2905544033 @default.
- W3199775471 cites W2912340292 @default.
- W3199775471 cites W2917103012 @default.
- W3199775471 cites W2919786679 @default.
- W3199775471 cites W2920014186 @default.
- W3199775471 cites W2951131556 @default.
- W3199775471 cites W2964171031 @default.
- W3199775471 cites W2990246360 @default.
- W3199775471 cites W2990391914 @default.
- W3199775471 cites W2990900847 @default.
- W3199775471 cites W2995180830 @default.
- W3199775471 cites W2999254410 @default.
- W3199775471 cites W3002876662 @default.
- W3199775471 cites W3010456684 @default.
- W3199775471 cites W3011598741 @default.
- W3199775471 cites W3020521460 @default.
- W3199775471 cites W3020845803 @default.
- W3199775471 cites W3034882073 @default.
- W3199775471 cites W3048688174 @default.
- W3199775471 cites W3091452821 @default.
- W3199775471 cites W3095427077 @default.
- W3199775471 cites W3098560717 @default.
- W3199775471 cites W3104262360 @default.
- W3199775471 cites W3118542935 @default.
- W3199775471 cites W3122686848 @default.
- W3199775471 cites W3127726806 @default.
- W3199775471 cites W3128473149 @default.
- W3199775471 cites W3129217345 @default.
- W3199775471 cites W3135479537 @default.
- W3199775471 cites W3137710672 @default.
- W3199775471 doi "https://doi.org/10.1109/tcsvt.2021.3112120" @default.
- W3199775471 hasPublicationYear "2022" @default.
- W3199775471 type Work @default.
- W3199775471 sameAs 3199775471 @default.
- W3199775471 citedByCount "4" @default.
- W3199775471 countsByYear W31997754712022 @default.
- W3199775471 countsByYear W31997754712023 @default.
- W3199775471 crossrefType "journal-article" @default.
- W3199775471 hasAuthorship W3199775471A5000581688 @default.
- W3199775471 hasAuthorship W3199775471A5018282808 @default.
- W3199775471 hasAuthorship W3199775471A5030554236 @default.
- W3199775471 hasAuthorship W3199775471A5049898953 @default.
- W3199775471 hasAuthorship W3199775471A5061745929 @default.
- W3199775471 hasConcept C115961682 @default.
- W3199775471 hasConcept C126057942 @default.
- W3199775471 hasConcept C127162648 @default.
- W3199775471 hasConcept C138885662 @default.
- W3199775471 hasConcept C154945302 @default.
- W3199775471 hasConcept C21822782 @default.
- W3199775471 hasConcept C24027999 @default.
- W3199775471 hasConcept C2776401178 @default.
- W3199775471 hasConcept C31258907 @default.
- W3199775471 hasConcept C31972630 @default.
- W3199775471 hasConcept C36464697 @default.
- W3199775471 hasConcept C41008148 @default.
- W3199775471 hasConcept C41895202 @default.
- W3199775471 hasConcept C55020928 @default.
- W3199775471 hasConcept C65909025 @default.
- W3199775471 hasConcept C76155785 @default.
- W3199775471 hasConcept C81363708 @default.