PhD Studentship - Vision Language Models for Micro-Expression Analysis

Manchester Metropolitan University; Manchester; On-site; GBP 28,000 - 34,000; Full time

Job summary

Manchester Metropolitan University in Manchester is seeking a Doctoral Teaching Assistant to integrate PhD research with a university teaching contract. Time is split roughly 60% research and 40% teaching, supporting core activities across classroom and lab sessions.

The role is designed to prepare candidates for an academic career, with teaching commitments spread over 22 weeks of teaching and 4 weeks of assessment per year.

Qualifications

• A high-grade undergraduate degree (first class or upper second) in computer science or MSc in related field.
• Strong programming and ML background with knowledge of vision-language models considered a plus.

Responsibilities

• Support research outputs and contribute to PhD research activities.
• Assist with course delivery, classroom and lab teaching, and assessment.
• Collaborate with lead academics on project milestones and dissemination.

Skills

Programming

Computer vision

Machine learning

PyTorch

TensorFlow

VLM experience

Education

BSc in Computer Science

MSc in related field

Tools

Python

PyTorch

TensorFlow

Job description

Micro-expressions are tiny, involuntary facial movements that can occur when a person tries to hide an emotion, but are difficult to analyse because they are subtle, short-lived, and easily confused with ordinary facial movement. While many methods have been developed to recognise and localise micro-expressions, these results remain difficult to understand.

The proposed models will be designed to identify where the relevant facial evidence occurs, describe what subtle change has been observed, and explain why a prediction has been made.

The project will deliver new methods, benchmark protocols, and evaluation frameworks for explainable and trustworthy micro-expression analysis, with relevance to human-centred AI, and healthcare-related affect analysis. The core novelty of the project is to shift micro-expression research from predominantly vision-only pipelines towards multimodal foundation-model approaches that combine subtle visual motion with structured language-level representations such as action units, temporal descriptions, prompt templates, and evidence-based explanations.

Objectives

We will investigate whether vision-language models (VLMs) can improve micro-expression analysis by combining video understanding with language-based reasoning.

• Process micro-facial expression data more efficiently in computer vision and vision language models.
• Create a language-guided representation for subtle facial motion, exploring multimodal data
• Create a spot-then-recognise approach to detect micro-expression intervals and interpret language-aware recognition.
• Evaluate novel methods and validate against the state-of-the-art in a real-world setting.

Funding

These are doctoral teaching assistant positions that combine a PhD programme with a university teaching contract. Your time will be split approximately 60% on research and 40% on teaching. This provides excellent preparation for candidates considering an academic career at a university. The teaching component will typically run over the 22 teaching weeks per year and the 4 assessment weeks. You will help deliver an outstanding student experience by supporting lead academics with classroom and lab teaching and assessment, further building the skills developed within your PhD research programme.

The position is grade 6 with a current salary of £31,236 and includes payment of home PhD tuition fees for the duration of the 6-year award. Home students can apply. Applicants must have the right to work in the UK. We are unable to offer visa sponsorship for this role.

Candidate requirements

Candidates must have expertise in developing computer vision and machine learning algorithms. Vision Language Model (VLM) experience is desirable.

Qualifications

• A high-grade undergraduate degree (first class or upper second) in computer science or MSc in related field.

Skills

• Knowledge of programming, computer vision, machine learning, or related discipline.
• Experience with Python and relevant AI/ML libraries (such as PyTorch, TensorFlow).
• Demonstrated knowledge of multimodal data processing (such as vision, language, 3D).