Zikun Zhou

8

Papers

30

Total Citations

Papers (8)

Bilateral Event Mining and Complementary for Event Stream Super-Resolution

Robust 3D Tracking with Quality-Aware Shape Completion

Instruction-guided Multi-Granularity Segmentation and Captioning with Large Multimodal Model

MambaVLT: Time-Evolving Multimodal State Space Model for Vision-Language Tracking

Improving Federated Domain Generalization Through Dynamical Weights Calculated from Data Influences on Global Model Update

RTracker: Recoverable Tracking via PN Tree Structured Memory

Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval

Interaction-based Retrieval-augmented Diffusion Models for Protein-specific 3D Molecule Generation