FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381198923> ?p ?o ?g. }

• W4381198923 endingPage "17" @default.
• W4381198923 startingPage "1" @default.
• W4381198923 abstract "In the existing deep learning based watermarking models, extracted image features for fusing with watermark are not abundant enough and more critically, essential features are not highlighted to be learned with the purpose of robust watermarking, both of which limit the watermarking performance. To solve those two drawbacks, this paper proposes an attention-guided robust image watermarking model based on generative adversarial network (ARWGAN). To acquire a great deal of representational image features, a feature fusion module (FFM) is devised to learn shallow and deep features effectively for multi-layer fusion with watermark, and meanwhile, reuse of those features by the dense connection enhances robustness. To alleviate image distortion caused by embedding watermark, an attention module (AM) is deployed to compute the attention mask by mining the global features of the original image. Specifically, with the guidance of the attention mask, image features representing inconspicuous regions and texture regions are enhanced for embedding the high strength of watermark, and simultaneously other features are suppressed to improve the watermarking performance. Furthermore, the noise sub-network is adopted for robustness enhancement by simulating various image attacks in iterative training. The discriminator is used to distinguish the encoded image from the original image for improving watermarking invisibility continuously. Experimental results demonstrate that ARWGAN is superior to the existing state-of-the-art watermarking models, and ablation experiments prove the effectiveness of the FFM and the AM. The code is avaliable in https://github.com/river-huang/ARWGAN." @default.
• W4381198923 created "2023-06-20" @default.
• W4381198923 creator A5030642173 @default.
• W4381198923 creator A5038550838 @default.
• W4381198923 creator A5048048449 @default.
• W4381198923 creator A5060792504 @default.
• W4381198923 creator A5068732216 @default.
• W4381198923 creator A5089539281 @default.
• W4381198923 date "2023-01-01" @default.
• W4381198923 modified "2023-10-17" @default.
• W4381198923 title "ARWGAN: Attention-Guided Robust Image Watermarking Model Based on GAN" @default.
• W4381198923 cites W2025657104 @default.
• W4381198923 cites W2108598243 @default.
• W4381198923 cites W2194775991 @default.
• W4381198923 cites W2424641053 @default.
• W4381198923 cites W2752782242 @default.
• W4381198923 cites W2779084106 @default.
• W4381198923 cites W2807910487 @default.
• W4381198923 cites W2883233582 @default.
• W4381198923 cites W2905915339 @default.
• W4381198923 cites W2909479956 @default.
• W4381198923 cites W2910688461 @default.
• W4381198923 cites W2928947536 @default.
• W4381198923 cites W2944049061 @default.
• W4381198923 cites W2944646475 @default.
• W4381198923 cites W2946512930 @default.
• W4381198923 cites W2956175719 @default.
• W4381198923 cites W2963446712 @default.
• W4381198923 cites W2963495494 @default.
• W4381198923 cites W2963728414 @default.
• W4381198923 cites W2966561013 @default.
• W4381198923 cites W2973268792 @default.
• W4381198923 cites W2973850056 @default.
• W4381198923 cites W2982163850 @default.
• W4381198923 cites W2989416700 @default.
• W4381198923 cites W2989909796 @default.
• W4381198923 cites W2997526307 @default.
• W4381198923 cites W2997594966 @default.
• W4381198923 cites W2999057796 @default.
• W4381198923 cites W3003177380 @default.
• W4381198923 cites W3034873438 @default.
• W4381198923 cites W3035671550 @default.
• W4381198923 cites W3038637120 @default.
• W4381198923 cites W3086944392 @default.
• W4381198923 cites W3090538384 @default.
• W4381198923 cites W3091781356 @default.
• W4381198923 cites W3097390462 @default.
• W4381198923 cites W3109263210 @default.
• W4381198923 cites W3121751387 @default.
• W4381198923 cites W3126855404 @default.
• W4381198923 cites W3128902306 @default.
• W4381198923 cites W3134591410 @default.
• W4381198923 cites W3136792391 @default.
• W4381198923 cites W3142659587 @default.
• W4381198923 cites W3150495862 @default.
• W4381198923 cites W3151130473 @default.
• W4381198923 cites W3158383274 @default.
• W4381198923 cites W3163519726 @default.
• W4381198923 cites W3168491317 @default.
• W4381198923 cites W3174531399 @default.
• W4381198923 cites W3199955888 @default.
• W4381198923 cites W3204217431 @default.
• W4381198923 cites W3206855633 @default.
• W4381198923 cites W3206857664 @default.
• W4381198923 cites W3213236098 @default.
• W4381198923 cites W4205513722 @default.
• W4381198923 cites W4220993084 @default.
• W4381198923 cites W4224918846 @default.
• W4381198923 cites W4225672218 @default.
• W4381198923 cites W4226232129 @default.
• W4381198923 cites W4285739711 @default.
• W4381198923 cites W4292387496 @default.
• W4381198923 doi "https://doi.org/10.1109/tim.2023.3285981" @default.
• W4381198923 hasPublicationYear "2023" @default.
• W4381198923 type Work @default.
• W4381198923 citedByCount "1" @default.
• W4381198923 crossrefType "journal-article" @default.
• W4381198923 hasAuthorship W4381198923A5030642173 @default.
• W4381198923 hasAuthorship W4381198923A5038550838 @default.
• W4381198923 hasAuthorship W4381198923A5048048449 @default.
• W4381198923 hasAuthorship W4381198923A5060792504 @default.
• W4381198923 hasAuthorship W4381198923A5068732216 @default.
• W4381198923 hasAuthorship W4381198923A5089539281 @default.
• W4381198923 hasConcept C104317684 @default.
• W4381198923 hasConcept C108583219 @default.
• W4381198923 hasConcept C115961682 @default.
• W4381198923 hasConcept C150817343 @default.
• W4381198923 hasConcept C153180895 @default.
• W4381198923 hasConcept C154945302 @default.
• W4381198923 hasConcept C164112704 @default.
• W4381198923 hasConcept C185592680 @default.
• W4381198923 hasConcept C2779803651 @default.
• W4381198923 hasConcept C31972630 @default.
• W4381198923 hasConcept C41008148 @default.
• W4381198923 hasConcept C41608201 @default.
• W4381198923 hasConcept C55493867 @default.
• W4381198923 hasConcept C63479239 @default.
• W4381198923 hasConcept C76155785 @default.

• next