Junjue Wang 王俊珏

Project Researcher
The University of Tokyo, Japan
E-mail: kingdrone@edu.k.u-tokyo.ac.jp

I am now working as a project researcher at Machine Learning and Statistical Data Analysis Lab, The University of Tokyo, supervised by Prof. Naoto Yokoya. I received my doctoral degree in Photogrammetry and Remote Sensing from Wuhan University in 2024, advised by Prof. Yanfei Zhong and Liangpei Zhang. I achieved my B.S. degree from the School of Geography and Information Engineering, China University of Geosciences (Wuhan), in 2019.

My interests include multi-modal remote sensing processing and computer vision, focusing on creative datasets and algorithms for various applications, such as large-scale land-cover mapping, agricultural analysis, rural/urban planning, and landslide detection, etc.

Recent News

[2024.10] We host a special issue Advancement of Multi-Source Remote Sensing Data Fusion in Environmental Monitoring at [Remote Sensing] (IF: 4.2). Please feel free to contribute :)

[2024.05] The Code and Dataset of EarthVQA (AAAI'2024) are released here.

[2024.01] Our LoveNAS was accepted by ISPRS'2024.

[2023.12] Our EarthVQA was accepted by AAAI'2024.

[2023.09] Our LoveCS has become ESI highly cited paper (Top 1%).

[2023.07] Our FarSeg++ has been accepted by TPAMI'2023.

Selected Publications

EarthVQANet: Multi-task visual question answering for remote sensing image understanding

ISPRS Journal of Photogrammetry and Remote Sensing (ISPRS P&RS), 2024

Paper  

LoveNAS: Towards Multi-Scene Land-Cover Mapping via Hierarchical Searching Adaptive Network

ISPRS Journal of Photogrammetry and Remote Sensing (ISPRS P&RS), 2024

Paper   Code  

EarthVQA: Towards Queryable Earth via Relational Reasoning-based Remote Sensing Visual Question Answering

The 38th Annual AAAI Conference on Artificial Intelligence (AAAI), 2024

Paper   Video   Data

Cross-sensor domain adaptation for high spatial resolution urban land-cover mapping: From airborne to spaceborne imagery (ESI highly cited paper)

Remote Sensing of Environment (RSE), 2022

Paper   Code   Product  

LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation

Advances in Neural Information Processing Systems (NeurIPS), 2021

Paper  Video  Code  Data 

FactSeg: Foreground Activation Driven Small Object Semantic Segmentation in Large-Scale Remote Sensing Imagery

IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2022

Paper  Code 

RSNet: The Search for Remote Sensing Deep Neural Networks in Recognition Tasks (ESI highly cited paper)

IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2021

Award

[2022.9]

2022 Graduate Academic Innovation First Prize, Wuhan University (“武汉大学研究生学术创新奖”一等奖)

[2022.4-2022.6]

2022 IJCAI LandSlide4Sense CDCEO workshop Challenge

1st Place

[2022.2-2022.3]

2022 Ali Tianchi Real World Image Forgery Localization Challenge

1st Place (1/1149)

[2020.10-2020.12]

2021 IEEE GRSS Data Fusion Contest, Track: Multitemporal Semantic Change Detection

4th Place

[2020.03-2020.05]

SpaceNet 6 EarthVision workshop challenge at CVPR 2020

Top Graduate Award (__EVER__)

[2019.10-2019.12]

xView2 Challenge

4th Place (4/3500+), overall

[2019.10-2019.12]

2019 IEEE GRSS Data Fusion Contest, Single-view Semantic 3D Challenge

2nd Place (2/400+)

Academic Service

Journal Reviewer
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)
Remote Sensing of Environment (RSE)
IEEE Transactions on Image Processing (TIP)
IEEE Transactions on Geoscience and Remote Sensing (TGRS)
Engineering Applications of Artificial Intelligence
Visual Computer
Remote Sensing
Remote Sensing Letters
International Journal of Remote Sensing (IJRS)
Section Editor for ''Medical Imaging Process & Technology''
Conference Reviewer
European Conference on Computer Vision (ECCV) 2024
Conference on Neural Information Processing Systems (NeurIPS) 2021-2024
IEEE Computer Vision and Pattern Recognition Conference (CVPR) 2022-2024
IEEE International Conference on Computer Vision (ICCV) 2023
Flag Counter Flag Counter