PhD Studentship: Exploration of incremental knowledge addition for human activity analysis in open-world scenarios for public safety and surveillance

DoS: Dr Vivek Singh: (vivek.singh@plymouth.ac.uk)

2^nd Supervisor: Dr Amir Ali (amir.aly@plymouth.ac.uk)

3^rd Supervisor: Dr Michael Loizou (michael.loizou@plymouth.ac.uk)

4^th Supervisor: Professor Fabio Cuzzolin (fabio.cuzzolin@brookes.ac.uk)

Applications are invited for a 3.5-year PhD studentship.

The studentship will start on 1^st October 2025.

Project Description

This project explores open-world learning (OWL) to develop AI systems that can recognize and adapt to new activities in video data without requiring retraining. Unlike traditional closed-world AI, which relies on predefined categories, OWL enables models to incrementally learn new concepts while retaining previously acquired knowledge. Video-based activity analysis presents unique challenges due to high spatial-temporal complexity in data and computational demands of the models. This research will develop a framework for open-vocabulary learning, allowing AI to process video data efficiently and recognize diverse activities beyond a fixed set of labels.

To ensure adaptability, the project integrates continual learning techniques, preventing catastrophic forgetting and enabling models to improve over time. A key application of this research is in public safety and elderly care, where AI-driven monitoring systems can assist in real-world scenarios. The project is validated in collaboration with Plymouth Community Homes Digital Living Lab, ensuring practical impact and usability in real-world environments. This research advances AI system’s ability to handle dynamically evolving problem and makes it more reliable for real-world applications.

What you will working on:

• Building an open-world deep learning framework for human activity analysis.
• Implementing continual learning to seamlessly integrate new knowledge.
• Validating results on real-world surveillance and safety applications using data from Plymouth Community Homes Digital Living Lab.

Ideal candidate

• Strong background in deep learning, computer vision, and artificial intelligence.
• Experience with PyTorch/TensorFlow for neural network development.
• Proficiency in Python and working with large-scale datasets.
• Familiarity with spatio-temporal learning (Preferred but not essential).

Eligibility

Applicants should have a first or upper second class honours degree in an appropriate subject and preferably a relevant Masters qualification. Applications from both UK and overseas students are welcome.

The studentship is supported for 3.5 years and includes full Home tuition fees, Bench fee plus a stipend of £20,780 per annum 2025/26 rate.  The studentship will only fully fund those applicants who are eligible for Home fees with relevant qualifications.  Applicants normally required to cover International fees will have to cover the difference between the Home and the International tuition fee rates.  The international component of the fee may be waived for outstanding international applicants.

There is no additional funding available to cover NHS Immigration Health Surcharge (IHS) costs, visa costs, flights etc.

NB: The studentship is supported for 3.5 years of the four-year registration period.

The subsequent 6 months of registration is a self-funded ‘writing-up’ period.

If you wish to discuss this project further informally, please contact:

Dr Vivek Singh, vivek.singh@plymouth.ac.uk.

To apply for this position please click on the Apply button above.

Please clearly state the name of the studentship that you are applying for on your personal statement.

Please see here for a list of supporting documents to upload with your application.

For more information on the admissions process generally, please contact

research.degree.admissions@plymouth.ac.uk

The closing date for applications is 12 noon on 28^th March 2025.

Shortlisted candidates will be invited for interview shortly thereafter.

Advert information