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

Data collected by different modalities can provide a wealth of complementaryinformation, such as hyperspectral image (HSI) to offer rich spectral-spatialproperties, synthetic aperture radar (SAR) to provide structural informationabout the Earth's surface, and light detection and ranging (LiDAR) to coveraltitude information about ground elevation. Therefore, a natural idea is tocombine multimodal images for refined and accurate land-cover interpretation.Although many efforts have been attempted to achieve multi-source remotesensing image classification, there are still three issues as follows: 1)indiscriminate feature representation without sufficiently considering modalheterogeneity, 2) abundant features and complex computations associated withmodeling long-range dependencies, and 3) overfitting phenomenon caused bysparsely labeled samples. To overcome the above barriers, a transformer-basedheterogeneously salient graph representation (THSGR) approach is proposed inthis paper. First, a multimodal heterogeneous graph encoder is presented toencode distinctively non-Euclidean structural features from heterogeneous data.Then, a self-attention-free multi-convolutional modulator is designed foreffective and efficient long-term dependency modeling. Finally, a mean forwardis put forward in order to avoid overfitting. Based on the above structures,the proposed model is able to break through modal gaps to obtain differentiatedgraph representation with competitive time cost, even for a small fraction oftraining samples. Experiments and analyses on three benchmark datasets withvarious state-of-the-art (SOTA) methods show the performance of the proposedapproach.

Learning transformer-based heterogeneously salient graph representation for multimodal fusion classification of hyperspectral image and LiDAR data