Grounding referring expression in computer vision

This project studies the integration of language and vision in computer vision, focusing on Grounding Referring Expressions utilising the state-of-the-art GroundingDINO model. We address the topic of object identification and segmentation, emphasising zero-shot models’ ability to recognise items...

Volledige beschrijving

Bibliografische gegevens
Hoofdauteur: Yuen, Shaun Chien Wee
Andere auteurs: Hanwang Zhang
Formaat: Final Year Project (FYP)
Taal:English
Gepubliceerd in: Nanyang Technological University 2024
Onderwerpen:
Online toegang:https://hdl.handle.net/10356/174979