Search Results for author:
Found 18 papers, 8 papers with code
Tensor Decompositions for Hyperspectral Data Processing in Remote Sensing: A Comprehensive Review
Owing to the rapid development of sensor technology, hyperspectral (HS) remote sensing (RS) imaging has provided a significant amount of spatial and spectral information for the observation and analysis of the Earth's surface at a distance of data acquisition devices, such as aircraft, spacecraft, and satellite.
Decoupled-and-Coupled Networks: Self-Supervised Hyperspectral Image Super-Resolution with Subpixel Fusion
Enormous efforts have been recently made to super-resolve hyperspectral (HS) images with the aid of high spatial resolution multispectral (MS) images.
Hyperspectral Image Super-Resolution
Image Super-Resolution
+1
Deep Learning in Multimodal Remote Sensing Data Fusion: A Comprehensive Review
With the extremely rapid advances in remote sensing (RS) technology, a great quantity of Earth observation (EO) data featuring considerable and complicated heterogeneity is readily available nowadays, which renders researchers an opportunity to tackle current geoscience applications in a fresh way.
DynamicRetriever: A Pre-training Model-based IR System with Neither Sparse nor Dense Index
Web search provides a promising way for people to obtain information and has been extensively studied.
AWSnet: An Auto-weighted Supervision Attention Network for Myocardial Scar and Edema Segmentation in Multi-sequence Cardiac Magnetic Resonance Images
Extensive experimental results on a publicly available dataset from Myocardial pathology segmentation combining multi-sequence CMR (MyoPS 2020) demonstrate our method can achieve promising performance compared with other state-of-the-art methods.
Learning to Select Historical News Articles for Interaction based Neural News Recommendation
The key to personalized news recommendation is to match the user's interests with the candidate news precisely and efficiently.
USER: A Unified Information Search and Recommendation Model based on Integrated Behavior Sequence
Search and recommendation are the two most common approaches used by people to obtain information.
SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers
Hyperspectral (HS) images are characterized by approximately contiguous spectral information, enabling the fine identification of materials by capturing subtle spectral discrepancies.
Endmember-Guided Unmixing Network (EGU-Net): A General Deep Learning Framework for Self-Supervised Hyperspectral Unmixing
Over the past decades, enormous efforts have been made to improve the performance of linear or nonlinear mixing models for hyperspectral unmixing, yet their ability to simultaneously generalize various spectral variabilities and extract physically meaningful endmembers still remains limited due to the poor ability in data fitting and reconstruction and the sensitivity to various spectral variabilities.
Multimodal Remote Sensing Benchmark Datasets for Land Cover Classification with A Shared and Specific Feature Learning Model
Moreover, to better assess multimodal baselines and the newly-proposed S2FL model, three multimodal RS benchmark datasets, i. e., Houston2013 -- hyperspectral and multispectral data, Berlin -- hyperspectral and synthetic aperture radar (SAR) data, Augsburg -- hyperspectral, SAR, and digital surface model (DSM) data, are released and used for land cover classification.
Interpretable Hyperspectral AI: When Non-Convex Modeling meets Hyperspectral Remote Sensing
Hyperspectral imaging, also known as image spectrometry, is a landmark technique in geoscience and remote sensing (RS).
Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects
Therefore, this survey discusses some strategies to improve the generalization performance of DL strategies which can provide some future guidelines.
PolSAR Image Classification Based on Robust Low-Rank Feature Extraction and Markov Random Field
Polarimetric synthetic aperture radar (PolSAR) image classification has been investigated vigorously in various remote sensing applications.
More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification
In particular, we also investigate a special case of multi-modality learning (MML) -- cross-modality learning (CML) that exists widely in RS image classification applications.
Graph Convolutional Networks for Hyperspectral Image Classification
Convolutional neural networks (CNNs) have been attracting increasing attention in hyperspectral (HS) image classification, owing to their ability to capture spatial-spectral feature representations.
Spectral Superresolution of Multispectral Imagery with Joint Sparse and Low-Rank Learning
However, the ability in the fusion of HS and MS images remains to be improved, particularly in large-scale scenes, due to the limited acquisition of HS images.
Spatial-Spectral Manifold Embedding of Hyperspectral Data
In recent years, hyperspectral imaging, also known as imaging spectroscopy, has been paid an increasing interest in geoscience and remote sensing community.
Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution
The recent advancement of deep learning techniques has made great progress on hyperspectral image super-resolution (HSI-SR).
