Yaohua Zha

7

Papers

63

Total Citations

Papers (7)

Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders

Embracing Collaboration Over Competition: Condensing Multiple Prompts for Visual In-Context Learning

MambaIRv2: Attentive State Space Restoration

GCD-Sampling: A General Cross-scale Decoupled Sampling for Point Cloud

Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models

Adapting Pre-trained 3D Models for Point Cloud Video Understanding via Cross-frame Spatio-temporal Perception

PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter