Open-Vocabulary Scene Understanding
Project Description
Mainstream computer vision methods can achieve good performance on closed-set scene understanding, this project tries to design novel algorithms to extend them to the open-vocabulary setting.
Supervisor
CHEN, Long
Quota
3
Course type
UROP1000
UROP1100
UROP2100
UROP3100
UROP3200
UROP4100
Applicant's Roles
Design algorithms to solve the open-vocabulary scene understanding tasks.
Prerequisite: Basic deep learning and machine learning knowledge, strong Python programming ability
Applicant's Learning Objectives
Understand the state-of-the-art methods for this direction, and try to propose another effective solution.
Complexity of the project
Moderate