FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2974018098> ?p ?o ?g. }

• W2974018098 abstract "In the past few years, deep convolutional neural networks (CNNs) have benefited great progress in salient object detection due to the strong ability of feature representation. As different level of features can be reflected in different layers, traditional CNNs based methods usually integrate features from multiple layers to obtain appealing results. However, the fine details of salient objects tend to be lost because of multiple subsampling operations such as convolution and pooling. Meanwhile, the non-salient regions reflected in the low level features would be easily integrated into the final results incorrectly. In order to address these issues, we propose a novel deep saliency detection network by recurrently aggregating and refining cross-layer residual features (RARCRF). Instead of directly refining the intermediate saliency map as many previous plain network based methods do, we design a residual learning module and embed it into RARCRF to learn residual features. Then, the residual features learned from multiple layers are aggregated and refined step by step in a cross-layer manner. By this way, the complementary information in deep features extracted from different layers can be fully captured for detecting salient objects with different scales, i.e., the features integrated from low-level layers can serve to refine the details of detected salient objects while the features integrated from high-level layers with semantic information can benefit the locating of salient objects. Finally, different saliency detection results from different layers are fused to generate the final saliency map. Experimental results with ablation analysis on five benchmark datasets demonstrate that our proposed RARCRF outperforms other 14 state-of-the-art competitors." @default.
• W2974018098 created "2019-09-26" @default.
• W2974018098 creator A5005304261 @default.
• W2974018098 creator A5033240507 @default.
• W2974018098 creator A5037717179 @default.
• W2974018098 creator A5069846711 @default.
• W2974018098 date "2019-08-01" @default.
• W2974018098 modified "2023-09-25" @default.
• W2974018098 title "Saliency Detection via Recurrently Aggregating and Refining Cross-layer Residual Features" @default.
• W2974018098 cites W1894057436 @default.
• W2974018098 cites W1931639407 @default.
• W2974018098 cites W1942214758 @default.
• W2974018098 cites W1947031653 @default.
• W2974018098 cites W2002781701 @default.
• W2974018098 cites W2011900468 @default.
• W2974018098 cites W2022651247 @default.
• W2974018098 cites W2035214377 @default.
• W2974018098 cites W2037954058 @default.
• W2974018098 cites W2039313011 @default.
• W2974018098 cites W2060095179 @default.
• W2974018098 cites W2086791339 @default.
• W2974018098 cites W2100470808 @default.
• W2974018098 cites W2121927366 @default.
• W2974018098 cites W2128272608 @default.
• W2974018098 cites W2155893237 @default.
• W2974018098 cites W2161185676 @default.
• W2974018098 cites W2163605009 @default.
• W2974018098 cites W2194775991 @default.
• W2974018098 cites W2338972621 @default.
• W2974018098 cites W2461475918 @default.
• W2974018098 cites W2532800065 @default.
• W2974018098 cites W2607333215 @default.
• W2974018098 cites W2740685955 @default.
• W2974018098 cites W2775906317 @default.
• W2974018098 cites W2780708736 @default.
• W2974018098 cites W2788154928 @default.
• W2974018098 cites W2798791651 @default.
• W2974018098 cites W2798825526 @default.
• W2974018098 cites W2807746031 @default.
• W2974018098 cites W2807798246 @default.
• W2974018098 cites W2884555738 @default.
• W2974018098 cites W2962835968 @default.
• W2974018098 cites W2962884579 @default.
• W2974018098 cites W2963162443 @default.
• W2974018098 cites W2963299740 @default.
• W2974018098 cites W2964101377 @default.
• W2974018098 doi "https://doi.org/10.1109/icist.2019.8836845" @default.
• W2974018098 hasPublicationYear "2019" @default.
• W2974018098 type Work @default.
• W2974018098 sameAs 2974018098 @default.
• W2974018098 citedByCount "0" @default.
• W2974018098 crossrefType "proceedings-article" @default.
• W2974018098 hasAuthorship W2974018098A5005304261 @default.
• W2974018098 hasAuthorship W2974018098A5033240507 @default.
• W2974018098 hasAuthorship W2974018098A5037717179 @default.
• W2974018098 hasAuthorship W2974018098A5069846711 @default.
• W2974018098 hasConcept C108583219 @default.
• W2974018098 hasConcept C11413529 @default.
• W2974018098 hasConcept C127313418 @default.
• W2974018098 hasConcept C13280743 @default.
• W2974018098 hasConcept C138885662 @default.
• W2974018098 hasConcept C153180895 @default.
• W2974018098 hasConcept C154945302 @default.
• W2974018098 hasConcept C155512373 @default.
• W2974018098 hasConcept C178790620 @default.
• W2974018098 hasConcept C185592680 @default.
• W2974018098 hasConcept C185798385 @default.
• W2974018098 hasConcept C2776151529 @default.
• W2974018098 hasConcept C2776401178 @default.
• W2974018098 hasConcept C2779227376 @default.
• W2974018098 hasConcept C2780719617 @default.
• W2974018098 hasConcept C41008148 @default.
• W2974018098 hasConcept C41895202 @default.
• W2974018098 hasConcept C45347329 @default.
• W2974018098 hasConcept C50644808 @default.
• W2974018098 hasConcept C52622490 @default.
• W2974018098 hasConcept C70437156 @default.
• W2974018098 hasConcept C81363708 @default.
• W2974018098 hasConceptScore W2974018098C108583219 @default.
• W2974018098 hasConceptScore W2974018098C11413529 @default.
• W2974018098 hasConceptScore W2974018098C127313418 @default.
• W2974018098 hasConceptScore W2974018098C13280743 @default.
• W2974018098 hasConceptScore W2974018098C138885662 @default.
• W2974018098 hasConceptScore W2974018098C153180895 @default.
• W2974018098 hasConceptScore W2974018098C154945302 @default.
• W2974018098 hasConceptScore W2974018098C155512373 @default.
• W2974018098 hasConceptScore W2974018098C178790620 @default.
• W2974018098 hasConceptScore W2974018098C185592680 @default.
• W2974018098 hasConceptScore W2974018098C185798385 @default.
• W2974018098 hasConceptScore W2974018098C2776151529 @default.
• W2974018098 hasConceptScore W2974018098C2776401178 @default.
• W2974018098 hasConceptScore W2974018098C2779227376 @default.
• W2974018098 hasConceptScore W2974018098C2780719617 @default.
• W2974018098 hasConceptScore W2974018098C41008148 @default.
• W2974018098 hasConceptScore W2974018098C41895202 @default.
• W2974018098 hasConceptScore W2974018098C45347329 @default.
• W2974018098 hasConceptScore W2974018098C50644808 @default.
• W2974018098 hasConceptScore W2974018098C52622490 @default.
• W2974018098 hasConceptScore W2974018098C70437156 @default.
• W2974018098 hasConceptScore W2974018098C81363708 @default.

• next