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...

पूर्ण विवरण

ग्रंथसूची विवरण
मुख्य लेखक: Yuen, Shaun Chien Wee
अन्य लेखक: Hanwang Zhang
स्वरूप: Final Year Project (FYP)
भाषा:English
प्रकाशित: Nanyang Technological University 2024
विषय:
ऑनलाइन पहुंच:https://hdl.handle.net/10356/174979