Publications by authors named "Fazeng Li"

Deep learning is becoming the most widely used technology for multi-sensor data fusion. Semantic correspondence has recently emerged as a foundational task, enabling a range of downstream applications, such as style or appearance transfer, robot manipulation, and pose estimation, through its ability to provide robust correspondence in RGB images with semantic information. However, current representations generated by self-supervised learning and generative models are often limited in their ability to capture and understand the geometric structure of objects, which is significant for matching the correct details in applications of semantic correspondence.

View Article and Find Full Text PDF

Objective: Classification and diagnostic study on Lepidiumn (Brassicaceae) from China.

Methods: Leaf epidermal mi-cromophology of 10 species of Lepidium from China were observed by using LM (light microscope) and SEM (scaning electron microscope).

Results: The stomatal apparatuses present both on the adaxial epidermis and the abaxial epidermis.

View Article and Find Full Text PDF