Matches in SemOpenAlex for { <https://semopenalex.org/work/W3110128680> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W3110128680 abstract "Watermarking is the procedure of encoding desired information into an image to resist potential noises while ensuring the embedded image has little perceptual perturbations from the original image. Recently, with the tremendous successes gained by deep neural networks in various fields, digital watermarking has attracted increasing number of attentions. The neglect of considering the pixel importance within the cover image of deep neural models will inevitably affect the model robustness for information hiding. Targeting at the problem, in this paper, we propose a novel deep watermarking scheme with Inverse Gradient Attention (IGA), combing the ideas of adversarial learning and attention mechanism to endow different importance to different pixels. With the proposed method, the model is able to spotlight pixels with more robustness for embedding data. Besides, from an orthogonal point of view, in order to increase the model embedding capacity, we propose a complementary message coding module. Empirically, extensive experiments show that the proposed model outperforms the state-of-the-art methods on two prevalent datasets under multiple settings." @default.
- W3110128680 created "2020-12-07" @default.
- W3110128680 creator A5006294869 @default.
- W3110128680 creator A5010019122 @default.
- W3110128680 creator A5019990791 @default.
- W3110128680 creator A5035296788 @default.
- W3110128680 creator A5036176166 @default.
- W3110128680 date "2020-11-21" @default.
- W3110128680 modified "2023-09-23" @default.
- W3110128680 title "Robust Watermarking Using Inverse Gradient Attention." @default.
- W3110128680 cites W1955882805 @default.
- W3110128680 cites W2025538567 @default.
- W3110128680 cites W2159390040 @default.
- W3110128680 cites W2165046009 @default.
- W3110128680 cites W2545788951 @default.
- W3110128680 cites W2741137940 @default.
- W3110128680 cites W2771036112 @default.
- W3110128680 cites W2883233582 @default.
- W3110128680 cites W2909676185 @default.
- W3110128680 cites W2963207607 @default.
- W3110128680 cites W2964121744 @default.
- W3110128680 cites W2997526307 @default.
- W3110128680 hasPublicationYear "2020" @default.
- W3110128680 type Work @default.
- W3110128680 sameAs 3110128680 @default.
- W3110128680 citedByCount "2" @default.
- W3110128680 countsByYear W31101286802021 @default.
- W3110128680 crossrefType "posted-content" @default.
- W3110128680 hasAuthorship W3110128680A5006294869 @default.
- W3110128680 hasAuthorship W3110128680A5010019122 @default.
- W3110128680 hasAuthorship W3110128680A5019990791 @default.
- W3110128680 hasAuthorship W3110128680A5035296788 @default.
- W3110128680 hasAuthorship W3110128680A5036176166 @default.
- W3110128680 hasConcept C104317684 @default.
- W3110128680 hasConcept C105795698 @default.
- W3110128680 hasConcept C108583219 @default.
- W3110128680 hasConcept C115961682 @default.
- W3110128680 hasConcept C150817343 @default.
- W3110128680 hasConcept C153180895 @default.
- W3110128680 hasConcept C154945302 @default.
- W3110128680 hasConcept C160633673 @default.
- W3110128680 hasConcept C179518139 @default.
- W3110128680 hasConcept C185592680 @default.
- W3110128680 hasConcept C3073032 @default.
- W3110128680 hasConcept C31972630 @default.
- W3110128680 hasConcept C33923547 @default.
- W3110128680 hasConcept C41008148 @default.
- W3110128680 hasConcept C41608201 @default.
- W3110128680 hasConcept C55493867 @default.
- W3110128680 hasConcept C63479239 @default.
- W3110128680 hasConceptScore W3110128680C104317684 @default.
- W3110128680 hasConceptScore W3110128680C105795698 @default.
- W3110128680 hasConceptScore W3110128680C108583219 @default.
- W3110128680 hasConceptScore W3110128680C115961682 @default.
- W3110128680 hasConceptScore W3110128680C150817343 @default.
- W3110128680 hasConceptScore W3110128680C153180895 @default.
- W3110128680 hasConceptScore W3110128680C154945302 @default.
- W3110128680 hasConceptScore W3110128680C160633673 @default.
- W3110128680 hasConceptScore W3110128680C179518139 @default.
- W3110128680 hasConceptScore W3110128680C185592680 @default.
- W3110128680 hasConceptScore W3110128680C3073032 @default.
- W3110128680 hasConceptScore W3110128680C31972630 @default.
- W3110128680 hasConceptScore W3110128680C33923547 @default.
- W3110128680 hasConceptScore W3110128680C41008148 @default.
- W3110128680 hasConceptScore W3110128680C41608201 @default.
- W3110128680 hasConceptScore W3110128680C55493867 @default.
- W3110128680 hasConceptScore W3110128680C63479239 @default.
- W3110128680 hasLocation W31101286801 @default.
- W3110128680 hasOpenAccess W3110128680 @default.
- W3110128680 hasPrimaryLocation W31101286801 @default.
- W3110128680 hasRelatedWork W113290662 @default.
- W3110128680 hasRelatedWork W114206516 @default.
- W3110128680 hasRelatedWork W1539296833 @default.
- W3110128680 hasRelatedWork W1744575521 @default.
- W3110128680 hasRelatedWork W1968320730 @default.
- W3110128680 hasRelatedWork W1975452309 @default.
- W3110128680 hasRelatedWork W2070745259 @default.
- W3110128680 hasRelatedWork W2560266880 @default.
- W3110128680 hasRelatedWork W2607126301 @default.
- W3110128680 hasRelatedWork W2782892321 @default.
- W3110128680 hasRelatedWork W2896145928 @default.
- W3110128680 hasRelatedWork W2997594966 @default.
- W3110128680 hasRelatedWork W2997717738 @default.
- W3110128680 hasRelatedWork W3038995955 @default.
- W3110128680 hasRelatedWork W3042950035 @default.
- W3110128680 hasRelatedWork W3086475144 @default.
- W3110128680 hasRelatedWork W3130180964 @default.
- W3110128680 hasRelatedWork W3131018823 @default.
- W3110128680 hasRelatedWork W3135820585 @default.
- W3110128680 hasRelatedWork W3189396597 @default.
- W3110128680 isParatext "false" @default.
- W3110128680 isRetracted "false" @default.
- W3110128680 magId "3110128680" @default.
- W3110128680 workType "article" @default.