- ⭐️ A lecturer at the School of Computer Science, Guangdong Polytechnic Normal University.
- 📚 Current research interests include computer vision, pattern recognition, and multimodal data fusion.
- 🌱 Received the Ph. D. degree in Electronics Information from Sun Yat-sen University.
- 💬 Ask me about Matlab, Python and my projects on jinping_wang@foxmail.com, wangjp@gpnu.edu.cn, wangjp29@mail2.sysu.edu.cn
- FusDreamer [Under Review] Holding
- World models significantly enhance hierarchical understanding, improving data integration and learning efficiency. To explore the potential of the world model in the RS field, this paper proposes a label-efficient remote sensing world model for multimodal data fusion (FusDreamer).
- InScope Dataset [Under Review] Released
- A large-scale dataset (InScope) featuring multi-position LiDARs in a real-world setting is presented in this paper, specifically developed to address the current research gap concerning occlusion challenges within the I2I perception systems in open traffic scenarios.
- MBFormer [IEEE TCSVT'2023] Holding
- This paper is the first time that dynamic region-aware convolution is introduced for spatial guide mask generation, and the acquired mask is used as an elevation salience agent to guide another branch for spatial contextual-aware information exploration.
- AM3Net_Multimodal_Data_Fusion [IEEE TCSVT'2022] Released
- Proposing multimodal data fusion methods pay more attention to the specificity of HSI spectral channels and the complementarity of HSI and LiDAR spatial information and consider more feature transmission processes among different modalities collaboratively.
- ASPCNet_HSIC [Neurocomuting'2022] Released
- This paper proposes an adaptive spatial pattern capsule network (ASPCNet) architecture by developing an adaptive spatial pattern (ASP) unit, that can rotate the sampling location of convolutional kernels based on an enlarged receptive field. It could adaptively change according to the inconsistent semantic information of HSIs.
- TPS-HSIC [IEEE JSTARS'2019] Released
- This paper introduces a new feature extraction method called TPS into HSI to address the layer-separation problem.
- KNNRS-HSIC [IEEE JSTARS'2018] Released
- To further explore the optimal representations of superpixels, the KNNRS method based on two k selection rules is proposed to find the most representative training and test samples.
- Cimy_PPtools
- This is a Python toolbox that supports data preprocessing for tasks such as hyperspectral classification and fusion, as well as model saving and result visualization.
😊