Zhicheng Wang

4

Papers

36

Total Citations

Papers (4)

Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting

ConDense: Consistent 2D-3D Pre-training for Dense and Sparse Features from Multi-View Images

Exploring Contextual Attribute Density in Referring Expression Counting

SRefiner: Soft-Braid Attention for Multi-Agent Trajectory Refinement