Changxin Gao

5 papers Huazhong University of Science and Technology

• Continual Gaussian Mixture Distribution Modeling for Class Incremental Semantic Segmentation
• ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model
• Towards Reliable and Holistic Visual In-Context Learning Prompt Selection
• Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts
• VideoLucy: Deep Memory Backtracking for Long Video Understanding