English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Unlike hiding bit-level messages, hiding image-level messages is morechallenging, which requires large capacity, high imperceptibility, and highsecurity. Although recent advances in hiding image-level messages have beenremarkable, existing schemes are limited to lossless spatial images as coversand cannot be directly applied to JPEG images, the ubiquitous lossy formatimages in daily life. The difficulties of migration are caused by the lack oftargeted design and the loss of details due to lossy decompression andre-compression. Considering that taking DCT densely on $8\times8$ image patchesis the core of the JPEG compression standard, we design a novel model called\textsf{EFDR}, which can comprehensively \underline{E}xploit\underline{F}ine-grained \underline{D}CT \underline{R}epresentations and embedthe secret image into quantized DCT coefficients to avoid the lossy process.Specifically, we transform the JPEG cover image and hidden secret image intofine-grained DCT representations that compact the frequency and are associatedwith the inter-block and intra-block correlations. Subsequently, thefine-grained DCT representations are further enhanced by a sub-band featuresenhancement module. Afterward, a transformer-based invertibility module isdesigned to fuse enhanced sub-band features. Such a design enables afine-grained self-attention on each sub-band and captures long-rangedependencies while maintaining excellent reversibility for hiding and recovery.To our best knowledge, this is the first attempt to embed a color image ofequal size in a color JPEG image. Extensive experiments demonstrate theeffectiveness of our \textsf{EFDR} with superior performance.

Exploiting Fine-Grained DCT Representations for Hiding Image-Level Messages within JPEG Images