IGARSS 2019

258 papers
The 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) featured 288 papers focusing on advancements in multimodal data fusion and deep learning applications for Earth observation. A primary research direction involved the integration of radar and optical imagery to overcome environmental challenges, such as cloud cover and signal saturation in high-biomass regions. Methodological trends highlighted the use of parallel multi-branch architectures and temporal attention mechanisms to process heterogeneous data sequences and improve continuous satellite monitoring. Technical contributions emphasized high-resolution image analysis, including road network extraction, landslide geohazard assessment, and ship classification using Sentinel-1 and Sentinel-2 data. Notable work explored boundary adherence in segmentation and the extraction of urban functional zones through self-adaptive scaling. Prolific contributors included Licheng Jiao, Yanfei Zhong, and Liangpei Zhang, whose research addressed spectral-spatial classification and object detection in optical remote sensing videos. These efforts collectively focused on improving the accuracy of automated feature extraction and ecosystem analysis from complex geospatial datasets.

Top Research Directions

Research directions most represented by IGARSS 2019 papers.

Integrating Non-Visible Spectral Bands for Robust Visual Representations 2
Multi-Label Zero-Shot Learning for Complex Visual Scenes 2
Temporal Signature Analysis for Vegetation Monitoring 2
Temporal Data Misalignment in Multi-Modal Learning 2
Computational Fusion of Spatial and Spectral Imagery 2
Resolving Spectral Signature Confusion in Sensor Data 2
Auxiliary Unimodal Supervision for Balanced Multimodal Learning 1
Object Counting via Spatial Density Estimation 1
Multi-Label Classification with Independent Sigmoids 1
Exploiting Temporal Redundancy in Dynamic Image Reconstruction 1
Spatial Sequence Modeling with Recurrent Networks 1
Why Neural Networks Can Outperform Noisy Supervision 1
Microwave Signal Attenuation and Scattering by Vegetation Canopies 1
Maximizing Non-Gaussianity for Independent Component Analysis 1
Identifiability in Nonnegative Matrix Factorization 1

Top Authors

AuthorPapers
Liangpei Zhang16
Licheng Jiao11
Yanfei Zhong11
Jocelyn Chanussot8
Shaohui Mei8
Xiangrong Zhang7
Xu Tang7
Qiangqiang Yuan6
Jonathan Li5
Zhihui Wei5
Danfeng Hong4
Fang Liu4
Junwei Han4
Lei Guo4
Lei Zhang4
Naoto Yokoya4
Qi Wang4
Wei Wei4
Xiwen Yao4
Xuelong Li4

Impactful Papers

Papers from IGARSS 2019 that shaped research clusters.

Influential

Papers

Title
Visual Question Answering From Remote Sensing Images
Weakly Supervised Building Segmentation from Aerial Images
Weakly Supervised Deep Convolutional Networks for Fine-Grained Object Recognition in Multispectral Images
Weak Moving Object Detection In Optical Remote Sensing Video With Motion-Drive Fusion Network
Weighted Group Sparsity Regularized Low-Rank Tensor Decomposition for Hyperspectral Image Restoration
What information is important? A spatiotemporal inference for classification of satellite image time series
WU-Net: A Weakly-Supervised Unmixing Network for Remotely Sensed Hyperspectral Imagery
Zoom In, Zoom Out: Injecting Scale Invariance into Landuse Classification CNNs

« prev Page 6/6