Zichang Tan

6

Papers

6

Total Citations

Papers (6)

Make Your ViT-based Multi-view 3D Detectors Faster via Token Compression

Unleashing the Potential of Consistency Learning for Detecting and Grounding Multi-Modal Media Manipulation

Recover and Match: Open-Vocabulary Multi-Label Recognition through Knowledge-Constrained Optimal Transport

Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection

CAMEL: CAusal Motion Enhancement Tailored for Lifting Text-driven Video Editing

BEVSpread: Spread Voxel Pooling for Bird’s-Eye-View Representation in Vision-based Roadside 3D Object Detection