Scholarship: Fully-funded
Degree: Bachelor, Master, Ph.D
Nationality: International Students
Location: UK
Application deadlines: Open
Scholarship Description:
The University of Bristol invites outstanding scholars passionate about research in visual large models and wearable devices to apply for our PhD program. This project aims to develop intelligent accessibility systems for the visually impaired, leveraging cutting-edge computer vision and AI technologies combined with wearable devices to provide safer and more convenient navigation and environmental perception solutions.
The Visual Information Lab (VI-Lab) at the University of Bristol focuses on innovative, collaborative, and interdisciplinary research in global-leading technologies such as computer vision, image and video communication, content analysis, and distributed sensing systems. Established in 2010 through collaboration between the Department of Computer Science and the Department of Electrical and Electronic Engineering, the lab has around 70 researchers, making it one of the largest teams of its kind in the UK. This year, the University also opened a top-ten AI supercomputing center, featuring over 5,000 GH200 units, with an investment exceeding £200 million.
Join us at the University of Bristol to advance technology and create a more inclusive society!
Available Subjects:
- Visual Large Models: Research and develop advanced computer vision algorithms to construct large-scale visual models that understand and analyze complex environments, providing real-time environmental information for the visually impaired.
- Wearable Devices: Design and develop intelligent wearable devices that integrate closely with visual large models to offer dynamic navigation, object recognition, and environmental awareness for the visually impaired.
- Multimodal Long Video Understanding: Create efficient algorithms for multimodal understanding of long videos, aimed at building comprehensive models that cover subtitle transcription, video Q&A, anomaly detection, and precise segment retrieval.
Eligibility criteria:
- Educational Background:
- Master’s degree in Computer Science, Electronic Engineering, Artificial Intelligence, Machine Learning, or related fields.
- Candidates with a Bachelor’s degree from 985/211 universities in Computer Science, Mathematics, or Engineering, ranking in the top 15% of their class, may be considered.
- Technical Skills:
- Familiarity with deep learning frameworks (e.g., TensorFlow, PyTorch) and computer vision technologies.
- Strong programming skills in Python, C++, or other relevant languages.
- Experience in handling large datasets and training deep neural networks.
- Research Interests:
- Strong interest in assistive technologies, accessibility systems, or navigation technologies for the visually impaired, with a commitment to research in this area.
- Other Requirements:
- Ability to conduct independent research and collaborate effectively in a multidisciplinary environment.
- Publication history is not required, but a strong engineering foundation and coding skills are essential, along with a passion for research.
- Excellent spoken and written English communication skills.
Application Procedure:
Interested applicants should send a detailed CV, research proposal, and related materials to the following email:
Please format the email subject as follows: PhD Application | Name | University | Program, e.g., PhD Application | Xiao Wang | University of Cambridge | Computer Science.