Xiangyuan Lan

6

Papers

101

Total Citations

Papers (6)

CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition

AlignMamba: Enhancing Multimodal Mamba with Local and Global Cross-modal Alignment

DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval

Transferable Adversarial Face Attack with Text Controlled Attribute

Deep Homography Estimation for Visual Place Recognition

Revisiting Context Aggregation for Image Matting