IEEE JSTARS 2023

166 papers
The 2023 edition of the IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing featured 34 papers focused on advancing geospatial artificial intelligence and computational efficiency. A primary research theme involved addressing the geographic generalization gap and optimizing convolutional networks through spatially sparse computation and adaptive visual computation. Methodological trends highlighted the use of CNN-Transformer hybrid models, attentional feature fusion for multi-scale representations, and shared backbones for multi-task visual perception. These developments aimed to reduce spatial redundancy and mitigate detail loss in spatiotemporal forecasting. Practical applications in 2023 spanned diverse domains, including the introduction of the UAVPal dataset for urban semantic segmentation and the MoANet for detecting sea fog in time-series meteorological imagery. Research also covered high-resolution scene classification via hierarchical texture fusion, unsupervised pansharpening networks, and radiometric calibration for the SuperView Neo-2 SAR satellite. Prolific contributors such as Wanying Song, Chen Wu, and Chengxi Han led efforts in balancing model complexity with accuracy in tasks like rural building segmentation and PolSAR image classification.

Top Research Directions

Research directions most represented by IEEE JSTARS 2023 papers.

Overcoming Remote Sensing Saturation in High Biomass Canopies 2
Preserving Tiny Features Against Spatial Resolution Degradation 2
Resolution Preserving Convolutional Architectures 2
Attention Based Adaptive Feature Fusion 2
Parallel Multi Scale Convolutional Feature Extraction 2
Mitigating Speckle Noise in Coherent Imaging Systems 2
Synergistic Multi-Sensor Fusion for Earth Observation 2
Prediction Horizon Decay in Temporal Models 2
Sparse Angular Sampling for Efficient Visual Reconstruction 1
Geometry Aware Viewpoint Optimization 1
Bridging the Land Cover and Land Use Semantic Gap 1
Vector-Based Capsule Networks for Hierarchical Spatial Modeling 1
Beyond Appearance Matching in Domain Adaptation 1
Ensemble Aggregation of Heterogeneous Quality Metrics 1
Transforming Raw Sensor Intensity into Viewpoint Invariant Reflectivity 1

Top Authors

AuthorPapers
Licheng Jiao7
Fang Liu5
Biao Hou4
Dino Ienco4
Jocelyn Chanussot4
Lingling Li4
Xu Liu4
Xu Tang4
Hongwei Liu3
jinglin zhang3
Shaohui Mei3
Shengwu Xiong3
Shuyuan Yang3
Weipeng Jing3
Wenping Ma3
Yaxiong Chen3
Zhixi Feng3
Bing Li2
Bing Zhang2
Bo Huang2

Impactful Papers

Papers from IEEE JSTARS 2023 that shaped research clusters.

Influential

Papers

Title
Configurable 2D-3D CNNs Accelerator for FPGA-Based Hyperspectral Imagery Classification
Context Aware Edge-Enhanced GAN for Remote Sensing Image Super-Resolution
Continual Barlow Twins: Continual Self-Supervised Learning for Remote Sensing Semantic Segmentation
Cross-Modal Local Calibration and Global Context Modeling Network for RGB-Infrared Remote-Sensing Object Detection
Cross Spectral and Spatial Scale Non-local Attention-Based Unsupervised Pansharpening Network
CTMU-Net: An Improved U-Net for Semantic Segmentation of Remote-Sensing Images Based on the Combined Attention Mechanism
Data Augmentation and Few-Shot Change Detection in Forest Remote Sensing
Decoupled Feature Pyramid Learning for Multi-Scale Object Detection in Low-Altitude Remote Sensing Images
Decreased Sensitivity of Grassland Spring Phenology to Temperature on the Tibetan Plateau
Deep-Learning-Based Semantic Segmentation of Remote Sensing Images: A Survey
Deep Tensor Attention Prior Network for Hyperspectral Image Denoising
Domain Adaptive Remote Sensing Scene Classification With Middle-Layer Feature Extraction and Nuclear Norm Maximization
Drone-Aided Detection of Weeds: Transfer Learning for Embedded Image Processing
Dual-Branch Spectral-Spatial Adversarial Representation Learning for Hyperspectral Image Classification With Few Labeled Samples
Dual-Task Network for Road Extraction From High-Resolution Remote Sensing Images
Dynamic Mapping of Inland Freshwater Aquaculture Areas in Jianghan Plain, China
Efficient and Robust: A Cross-Modal Registration Deep Wavelet Learning Method for Remote Sensing Images
Efficient Rural Building Segmentation via a Multilevel Decoding Network
Enhanced Adaptive Graph Convolutional Network for Long-Term Fine-Grained SST Prediction
Enhanced Feature Extraction From Assimilated VTCI and LAI With a Particle Filter for Wheat Yield Estimation Using Cross-Wavelet Transform
Enhancing Efficient Global Understanding Network With CSWin Transformer for Urban Scene Images Segmentation
Enhancing Forest Attribute Prediction by Considering Terrain and Scan Angles From Lidar Point Clouds: A Neural Network Approach
Estimating Winter Wheat LAI Using Hyperspectral UAV Data and an Iterative Hybrid Method
Extracting Deciduous Forests Spring Phenology From Sentinel-1 Cross Ratio Index
Fast and Structured Block-Term Tensor Decomposition for Hyperspectral Unmixing
Faster and Lighter Meteorological Satellite Image Classification by a Lightweight Channel-Dilation-Concatenation Net
Feature Enhancement and Alignment for Oriented Object Detection
Fine-Grained Ship Detection in High-Resolution Satellite Images With Shape-Aware Feature Learning
FLOGA: A Machine-Learning-Ready Dataset, a Benchmark, and a Novel Deep Learning Model for Burnt Area Mapping With Sentinel-2
Forest Height Inversion by Convolutional Neural Networks Based on L-Band PolInSAR Data Without Prior Knowledge Dependency
From Plane to Hierarchy: Deformable Transformer for Remote Sensing Image Captioning
GateFormer: Gate Attention UNet With Transformer for Change Detection of Remote Sensing Images
GCRDN: Global Context-Driven Residual Dense Network for Remote Sensing Image Superresolution
Geological Mapping via Convolutional Neural Network Based on Remote Sensing and Geochemical Survey Data in Vegetation Coverage Areas
Gesture-ProxylessNAS: A Lightweight Network for Mid-Air Gesture Recognition Based on UWB Radar
Global Sea Surface Height Measurement From CYGNSS Based on Machine Learning
Gradient Prior Dilated Convolution Network for Remote Sensing Image Super-Resolution
HANet: A Hierarchical Attention Network for Change Detection With Bitemporal Very-High-Resolution Remote Sensing Images
HDTFF-Net: Hierarchical Deep Texture Features Fusion Network for High-Resolution Remote Sensing Scene Classification
Hierarchical Disentanglement-Alignment Network for Robust SAR Vehicle Recognition
Hypergraph-Enhanced Textual-Visual Matching Network for Cross-Modal Remote Sensing Image Retrieval via Dynamic Hypergraph Learning
Hyperspectral Image Denoising via Nonlocal Spectral Sparse Subspace Representation
Hyperspectral Image Superresolution via Subspace-Based Deep Prior Regularization
Individual Extraction of Street Trees From MLS Point Clouds Based on Tree Nonphotosynthetic Components Clustering
Intelligent Retrieval of Radar Reflectivity Factor With Privacy Protection Under Meteorological Satellite Remote Sensing
IVIU-Net: Implicit Variable Iterative Unrolling Network for Hyperspectral Sparse Unmixing
Landslide Risk Evaluation in Shenzhen Based on Stacking Ensemble Learning and InSAR
Learning to Find the Optimal Correspondence Between SAR and Optical Image Patches
LFD-Net: Lightweight Feature-Interaction Dehazing Network for Real-Time Remote Sensing Tasks
Local and Global Spatial Information for Land Cover Semisupervised Classification of Complex Polarimetric SAR Data

« prev Page 2/4 next »