DAPnet: A double self-attention convolutional network for point cloud semantic labeling (IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021)
Lie to me: A soft threshold defense method for adversarial examples of remote sensing images (IEEE Geoscience and Remote Sensing Letters, 2021)
Estimation of the Potential Achievable Solar Energy of the Buildings Using Photogrammetric Mesh Models (Remote Sensing, 2021)
An attention U-Net model for detection of fine-scale hydrologic streamlines (Environmental Modelling & Software, 2021)
EFCNet: Ensemble Full Convolutional Network for Semantic Segmentation of High-Resolution Remote Sensing Images (IEEE Geoscience and Remote Sensing Letters, 2021)
Contextual information-preserved architecture learning for remote-sensing scene classification (IEEE Transactions on Geoscience and Remote Sensing, 2021)
A multiple subspaces-based model: Interpreting urban functional regions with big geospatial data (ISPRS International Journal of Geo-Information, 2021)
Research Experience
Working as a Research Scientist at ByteDance, involved in intelligent creation.
Education
Received Ph.D. from the School of Geosciences and Info-Physics, Central South University.
Background
Currently a Research Scientist at ByteDance, focusing on CV, multimodal, and interpretability.