---

Short Bio

I am currently a Postdoctoral Researcher at DMLab, Sungkyunkwan University, advised by Prof. Byeungwoo Jeon. I received my Ph.D. degree from MILab, the School of Computer Science and Engineering at Nanjing University of Science and Technology, under the supervision of Prof. Zhenmin Tang and Prof. Yazhou Yao. Before that, I received my M.S. degree from the School of Computer and Information, Anqing Normal University, under the guidance of Prof. Yibin Wang.

---

News

• 2025/11: Our paper “ChangeTitans: Towards Remote Sensing Change Detection with Neural Memory” is accepted by TGRS.

• 2025/11: Our paper “Beyond Quadratic: Linear-Time Change Detection with RWKV” is accepted by AAAI 2026.

• 2025/06: Our paper “Cycle-Consistent Learning for Joint Layout-to-Image Generation and Object Detection” is accepted by ICCV 2025.

• 2025/02: Our paper “Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection” is accepted by CVPR 2025.

• 2024/07: Our paper “Enhancing Robustness in Learning with Noisy Labels: An Asymmetric Co-Training Approach” is accepted by ACM-MM 2024.

• 2024/04: Our paper “LTFormer: A Light-weight Transformer-based Self-supervised Matching Network for Heterogeneous Remote Sensing Images” is accepted by Information Fusion.

• 2024/03: Our paper “Universal Organizer of Segment Anything Model for Unsupervised Semantic Segmentation” is accepted by ICME 2024.

• 2024/03: Our paper “Relating CNN-Transformer Fusion Network for Remote Sensing Change Detection” is accepted by ICME 2024.

• 2024/02: Our paper “VideoMAC: Video Masked Autoencoders Meet ConvNets” is accepted by CVPR 2024.

• 2023/10: Our paper “Hierarchical Graph Pattern Understanding for Zero-Shot Video Object Segmentation” is accepted by TIP.

• 2023/05: Our paper “Automated Object Recognition in High-resolution Optical Remote Sensing Imagery” is accepted by NSR.

• 2023/04: Our paper “Hierarchical Co-attention Propagation Network for Zero-Shot Video Object Segmentation” is accepted by TIP.

• 2022/07: Our paper “Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation” is accepted by ECCV 2022.

---

Research Interests

• Video segmentation (including but not limited to
  unsupervised learning, semi-supervised learning, and self-supervised learning)

• Change detection

• Self-supervised learning

• Vision-Language Model

---

Education

• Doctor of Engineering, April 2025
  School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China.
  Supervised by Prof. Zhenmin Tang.

• Master of Science, July 2019
  School of Computer and Information, Anqing Normal University, Anqing, China.
  Supervised by Prof. Yibin Wang.

• Bachelor of Engineering, July 2016
  School of Computer and Information, Anqing Normal University, Anqing, China.