Xiang Xu

10

Papers

10

Total Citations

Papers (10)

Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations

Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels

Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofing

Model Diagnosis and Correction via Linguistic and Implicit Attribute Editing

d-SNE: Domain Adaptation Using Stochastic Neighborhood Embedding

Adversarial Representation Learning for Text-to-Image Matching

Learning Self-Consistency for Deepfake Detection

LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes

Structured Outdoor Architecture Reconstruction by Exploration and Classification

EventFly: Event Camera Perception from Ground to the Sky