Haiping Wu

4

Papers

15

Total Citations

Papers (4)

Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Contrastive Learning of Image Representations With Cross-Video Cycle-Consistency

CvT: Introducing Convolutions to Vision Transformers