Picture for Hongguang Zhu

Hongguang Zhu

Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation

Add code
Aug 01, 2024
Viaarxiv icon

CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation

Add code
Aug 14, 2023
Viaarxiv icon

Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline

Add code
Apr 13, 2021
Figure 1 for Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline
Figure 2 for Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline
Figure 3 for Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline
Figure 4 for Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline
Viaarxiv icon