Wei Ji

Degradation-Aware Dynamic Schrödinger Bridge for Unpaired Image Restoration

SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcal{O}(T)$ Complexity

Unleashing Multispectral Video's Potential in Semantic Segmentation: A Semi-supervised Viewpoint and New UAV-View Benchmark

Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading

Learning Frequency-Adapted Vision Foundation Model for Domain Generalized Semantic Segmentation