FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3186100195> ?p ?o ?g. }

• W3186100195 endingPage "518" @default.
• W3186100195 startingPage "507" @default.
• W3186100195 abstract "Current top-performing saliency prediction methods of omnidirectional images (ODIs) depend on deep feedforward convolutional neural networks (CNNs), benefiting from their powerful multiscale representation ability. Although these methods adopt deep feedforward CNNs to achieve superb performance in saliency prediction task, they have the following limitations: 1) these deep feedforward CNNs are difficult to map to ventral stream structure of the brain visual system due to their vast number of layers and missing biologically important connections, such as recurrence and 2) most deep feedforward CNNs represent the multiscale features in a layerwise manner. To tackle these issues, models that could learn multiscale features yet share the similarities with human brain are needed. In this article, we propose a novel multiscale brain-like network (MBN) model to predict saliency of head fixations on ODIs. Specifically, our proposed model consists of two major modules: 1) a brain-like CORnet-S module and 2) a multiscale feature extraction module. The CORnet-S module is a lightweight backbone network with four anatomically mapped areas (V1, V2, V4, and IT) and it can simulate the visual processing mechanism of ventral visual stream in the human brain. The multiscale feature extraction module is inspired by the multiscale brain structure, which represents multiscale features at a granular level and increases the range of receptive fields for each network layer. Extensive experiments and ablation studies conducted on two major benchmarks demonstrate the superiority of the proposed MBN model over the state-of-the-art methods." @default.
• W3186100195 created "2021-08-02" @default.
• W3186100195 creator A5002554183 @default.
• W3186100195 creator A5019708391 @default.
• W3186100195 creator A5034718093 @default.
• W3186100195 creator A5060342917 @default.
• W3186100195 creator A5062094448 @default.
• W3186100195 creator A5064168853 @default.
• W3186100195 creator A5085080585 @default.
• W3186100195 date "2022-06-01" @default.
• W3186100195 modified "2023-10-16" @default.
• W3186100195 title "Multiscale Brain-Like Neural Network for Saliency Prediction on Omnidirectional Images" @default.
• W3186100195 cites W1510835000 @default.
• W3186100195 cites W1965305672 @default.
• W3186100195 cites W1996031228 @default.
• W3186100195 cites W2008066834 @default.
• W3186100195 cites W2020676607 @default.
• W3186100195 cites W2041719651 @default.
• W3186100195 cites W2055111849 @default.
• W3186100195 cites W2078903912 @default.
• W3186100195 cites W2111997583 @default.
• W3186100195 cites W2119228922 @default.
• W3186100195 cites W2128272608 @default.
• W3186100195 cites W2138046011 @default.
• W3186100195 cites W2212216676 @default.
• W3186100195 cites W2332175535 @default.
• W3186100195 cites W2469524028 @default.
• W3186100195 cites W2516705110 @default.
• W3186100195 cites W2528092473 @default.
• W3186100195 cites W2557792085 @default.
• W3186100195 cites W2561270043 @default.
• W3186100195 cites W2622036627 @default.
• W3186100195 cites W2791826171 @default.
• W3186100195 cites W2794956947 @default.
• W3186100195 cites W2795350989 @default.
• W3186100195 cites W2803485280 @default.
• W3186100195 cites W2962716998 @default.
• W3186100195 cites W2963828885 @default.
• W3186100195 cites W2964114039 @default.
• W3186100195 cites W2964279441 @default.
• W3186100195 cites W2965392395 @default.
• W3186100195 cites W2979473621 @default.
• W3186100195 cites W2980565715 @default.
• W3186100195 cites W3035101153 @default.
• W3186100195 cites W3035140436 @default.
• W3186100195 cites W3103753223 @default.
• W3186100195 cites W3122238731 @default.
• W3186100195 doi "https://doi.org/10.1109/tcds.2021.3052526" @default.
• W3186100195 hasPublicationYear "2022" @default.
• W3186100195 type Work @default.
• W3186100195 sameAs 3186100195 @default.
• W3186100195 citedByCount "2" @default.
• W3186100195 countsByYear W31861001952021 @default.
• W3186100195 countsByYear W31861001952023 @default.
• W3186100195 crossrefType "journal-article" @default.
• W3186100195 hasAuthorship W3186100195A5002554183 @default.
• W3186100195 hasAuthorship W3186100195A5019708391 @default.
• W3186100195 hasAuthorship W3186100195A5034718093 @default.
• W3186100195 hasAuthorship W3186100195A5060342917 @default.
• W3186100195 hasAuthorship W3186100195A5062094448 @default.
• W3186100195 hasAuthorship W3186100195A5064168853 @default.
• W3186100195 hasAuthorship W3186100195A5085080585 @default.
• W3186100195 hasConcept C108583219 @default.
• W3186100195 hasConcept C111472728 @default.
• W3186100195 hasConcept C127413603 @default.
• W3186100195 hasConcept C133731056 @default.
• W3186100195 hasConcept C138885662 @default.
• W3186100195 hasConcept C153180895 @default.
• W3186100195 hasConcept C154945302 @default.
• W3186100195 hasConcept C189950617 @default.
• W3186100195 hasConcept C2776401178 @default.
• W3186100195 hasConcept C38858127 @default.
• W3186100195 hasConcept C41008148 @default.
• W3186100195 hasConcept C41895202 @default.
• W3186100195 hasConcept C47702885 @default.
• W3186100195 hasConcept C50644808 @default.
• W3186100195 hasConcept C52622490 @default.
• W3186100195 hasConcept C81363708 @default.
• W3186100195 hasConceptScore W3186100195C108583219 @default.
• W3186100195 hasConceptScore W3186100195C111472728 @default.
• W3186100195 hasConceptScore W3186100195C127413603 @default.
• W3186100195 hasConceptScore W3186100195C133731056 @default.
• W3186100195 hasConceptScore W3186100195C138885662 @default.
• W3186100195 hasConceptScore W3186100195C153180895 @default.
• W3186100195 hasConceptScore W3186100195C154945302 @default.
• W3186100195 hasConceptScore W3186100195C189950617 @default.
• W3186100195 hasConceptScore W3186100195C2776401178 @default.
• W3186100195 hasConceptScore W3186100195C38858127 @default.
• W3186100195 hasConceptScore W3186100195C41008148 @default.
• W3186100195 hasConceptScore W3186100195C41895202 @default.
• W3186100195 hasConceptScore W3186100195C47702885 @default.
• W3186100195 hasConceptScore W3186100195C50644808 @default.
• W3186100195 hasConceptScore W3186100195C52622490 @default.
• W3186100195 hasConceptScore W3186100195C81363708 @default.
• W3186100195 hasFunder F4320321001 @default.
• W3186100195 hasIssue "2" @default.
• W3186100195 hasLocation W31861001951 @default.
• W3186100195 hasOpenAccess W3186100195 @default.

• next