Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Learning to Understand 2D/3D Facial Dynamics [Self Funded Students Only]

   Cardiff School of Computer Science & Informatics

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Prof Yukun Lai, Prof Paul Rosin  Applications accepted all year round  Self-Funded PhD Students Only

About the Project

Humans are particularly good at recognising faces, not only for identities but also for more subtle expressions and micro-expressions. These form a crucial part in non-verbal communication. Although AI-based face recognition and expression recognition have achieved great success, recognising more subtle expressions and micro-expressions remain challenging. Developing algorithms that can reliably understand human emotions from facial videos can support many applications such as human computer/robot interaction.

However, as visual clues can be subtle, it is essential to explore facial dynamics (i.e., change of face images over time) and 2D/3D visual information. The aim of the project is to develop novel computer vision algorithms for understanding and recognising subtle facial behaviour, such as expressions and micro-expressions. Specifically, the project will involve:

Exploiting facial dynamics from face videos for recognition of expressions and micro-expressions. Face videos are widely available, and the study will involve developing more effective features that characterise facial dynamics and utilise effective deep learning architectures and transfer learning to cope with limited training data, especially for micro-expressions.

Jointly utilising both 2D and 3D visual information for expression recognition. Faces are essentially deformable 3D objects, and the 3D information is crucial to describe facial deformations. The project will investigate the effectiveness of such 3D deformation information, and how to effectively combine both 2D appearance and 3D deformation information, as well as their temporal dynamics for subtle facial behaviour recognition. The complementary nature of 2D and 3D facial dynamics will also be exploited, to guide the development of novel algorithms.

Although 3D dynamic facial data is still relatively limited, some datasets are available (including the 4D CCDb from Cardiff). It will also be interesting to exploit the potential for combining prior knowledge from different data sources. 

Understanding emotions via 2D/3D facial dynamics have many applications, and we will in particular consider human robot interaction as a case study to evaluate the usefulness of such techniques. The robot can easily include sensors to capture both images and 3D data, allowing algorithms to be effectively utilised. This is also a topic of increasing practical importance, as recognising human emotions is crucial to ensure intelligent robots interact with humans in an appropriate way.

Please address enquiries to Prof. Yukun Lai, [Email Address Removed]

Keywords: Artificial Intelligence, Computer Vision, Machine Learning, Human Centred Computing

Academic criteria:  

A 2:1 Honours undergraduate degree or a master's degree, in computing or a related subject.  Applicants with appropriate professional experience are also considered. Degree-level mathematics (or equivalent) is required for research in some project areas. 

Applicants for whom English is not their first language must demonstrate proficiency by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component. 

This application is open to students worldwide. 

How to apply

Please contact the supervisors of the project prior to submitting your application to discuss and develop an individual research proposal that builds on the information provided in this advert. Once you have developed the proposal with support from the supervisors, please submit your application following the instructions provided below 

This project is accepting applications all year round, for self-funded candidates via  

In order to be considered candidates must submit the following information:  

  • Supporting statement  
  • CV  
  • In the ‘Research Proposal’ section of the application enter the name of the project you are applying to and upload your Individual research proposal, as mentioned above in BOLD 
  • Qualification certificates and Transcripts 
  • Proof of Funding. For example, a letter of intent from your sponsor or confirmation of self-funded status (In the funding field of your application, insert Self-Funded) 
  • References x 2  
  • Proof of English language (if applicable) 

If you have any questions or need more information, please contact [Email Address Removed] 

Computer Science (8)

Funding Notes

This project is offered for self-funded students only, or those with their own sponsorship or scholarship award.


• J. Vandeventer, A. J. Aubrey, P. L. Rosin, A. D. Marshall, 4D Cardiff Conversation Database (4D CCDb): a 4D database of natural, dyadic conversations. AVSP, 2015.
• Y.-J. Liu, B.-J. Li, Y.-K. Lai, Sparse MDMO: learning a discriminative feature for micro-expression recognition. IEEE Transactions on Affective Computing, 2021.

How good is research at Cardiff University in Computer Science and Informatics?

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

Where will I study?

Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.